initial
Browse files- config.json +65 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +809 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +3533 -0
config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/shapla/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
|
| 3 |
+
"action_dim": 32,
|
| 4 |
+
"action_head_cfg": {
|
| 5 |
+
"action_dim": 32,
|
| 6 |
+
"action_horizon": 16,
|
| 7 |
+
"add_pos_embed": true,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"dropout": 0.2,
|
| 11 |
+
"final_dropout": true,
|
| 12 |
+
"interleave_self_attention": true,
|
| 13 |
+
"norm_type": "ada_norm",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_layers": 16,
|
| 16 |
+
"output_dim": 1024,
|
| 17 |
+
"positional_embeddings": null
|
| 18 |
+
},
|
| 19 |
+
"freeze_decode_layer": false,
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"load_pretrained_det_decode_layer_path": null,
|
| 23 |
+
"max_action_dim": 32,
|
| 24 |
+
"max_state_dim": 64,
|
| 25 |
+
"model_dtype": "float32",
|
| 26 |
+
"noise_beta_alpha": 1.5,
|
| 27 |
+
"noise_beta_beta": 1.0,
|
| 28 |
+
"noise_s": 0.999,
|
| 29 |
+
"num_inference_timesteps": 16,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true
|
| 33 |
+
},
|
| 34 |
+
"action_horizon": 16,
|
| 35 |
+
"architectures": [
|
| 36 |
+
"GR00T_N1"
|
| 37 |
+
],
|
| 38 |
+
"attn_implementation": null,
|
| 39 |
+
"backbone_cfg": {
|
| 40 |
+
"allow_reshape_visual": true,
|
| 41 |
+
"load_pretrained_det_eagle_path": null,
|
| 42 |
+
"model_name": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 43 |
+
"processor_cfg": {
|
| 44 |
+
"max_input_tiles": 1,
|
| 45 |
+
"model_path": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 46 |
+
"model_spec": {
|
| 47 |
+
"num_image_token": 64,
|
| 48 |
+
"template": "qwen2-chat"
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"projector_dim": 2048,
|
| 52 |
+
"remove_llm": false,
|
| 53 |
+
"reproject_vision": false,
|
| 54 |
+
"scale_image_resolution": 1,
|
| 55 |
+
"select_layer": 12,
|
| 56 |
+
"tune_llm": false,
|
| 57 |
+
"tune_visual": true
|
| 58 |
+
},
|
| 59 |
+
"compute_dtype": "bfloat16",
|
| 60 |
+
"hidden_size": 1536,
|
| 61 |
+
"model_dtype": "float32",
|
| 62 |
+
"model_type": "gr00t_n1",
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.45.2"
|
| 65 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38a465489f8040d084956a55de5f2cad268fb6f477aa7de3d14e183603f60514
|
| 3 |
+
size 4938446392
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f67d00eaaef4e1030e793840ad3139d881868bf0dc6c1dd5f3c2e9978f0e303
|
| 3 |
+
size 3821736024
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,809 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8760067008
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 7 |
+
"action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 8 |
+
"action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 9 |
+
"action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 10 |
+
"action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors",
|
| 11 |
+
"action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors",
|
| 12 |
+
"action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors",
|
| 13 |
+
"action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors",
|
| 14 |
+
"action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors",
|
| 15 |
+
"action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors",
|
| 16 |
+
"action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors",
|
| 17 |
+
"action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors",
|
| 18 |
+
"action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors",
|
| 19 |
+
"action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors",
|
| 20 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00002.safetensors",
|
| 21 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00002.safetensors",
|
| 22 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00002.safetensors",
|
| 23 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00002.safetensors",
|
| 24 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 25 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 26 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 27 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 28 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 29 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 30 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 31 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 32 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 33 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 34 |
+
"action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 35 |
+
"action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 36 |
+
"action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 37 |
+
"action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 38 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 39 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 40 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 41 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 42 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 43 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 44 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 45 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 46 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 47 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 49 |
+
"action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 50 |
+
"action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 51 |
+
"action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 52 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 53 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 54 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 55 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 56 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 57 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 58 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 59 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 60 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 61 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 62 |
+
"action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 63 |
+
"action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 64 |
+
"action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 65 |
+
"action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 66 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 67 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 68 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 69 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 70 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 71 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 72 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 73 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 74 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 75 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 76 |
+
"action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 77 |
+
"action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 78 |
+
"action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 79 |
+
"action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 80 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 81 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 82 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 83 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 84 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 85 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 86 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 87 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 88 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 89 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 91 |
+
"action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 92 |
+
"action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 93 |
+
"action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 95 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 97 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 99 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 101 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 102 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 103 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 105 |
+
"action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 107 |
+
"action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 109 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 111 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 113 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 115 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 117 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 119 |
+
"action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 121 |
+
"action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 123 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 125 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 127 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 129 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 131 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 133 |
+
"action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 135 |
+
"action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 137 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 139 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 141 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 143 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 145 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 147 |
+
"action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 149 |
+
"action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 151 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 153 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 155 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 157 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 159 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 161 |
+
"action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 163 |
+
"action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 165 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 167 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 169 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 171 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 173 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 175 |
+
"action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 177 |
+
"action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 179 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 181 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 183 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 187 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 189 |
+
"action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 191 |
+
"action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 195 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 201 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 203 |
+
"action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 207 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 215 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 219 |
+
"action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 225 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 227 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 231 |
+
"action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 237 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 239 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 241 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 243 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"action_head.position_embedding.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 250 |
+
"action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 251 |
+
"action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 252 |
+
"action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 253 |
+
"backbone.linear.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"backbone.linear.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"backbone.model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"backbone.model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"backbone.model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"backbone.model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"backbone.model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"backbone.model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"backbone.model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"backbone.model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"backbone.model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"backbone.model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"backbone.model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"backbone.model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"backbone.model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"backbone.model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"backbone.model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"backbone.model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"backbone.model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"backbone.model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"backbone.model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"backbone.model.language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"backbone.model.language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"backbone.model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"backbone.model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"backbone.model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"backbone.model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"backbone.model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"backbone.model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"backbone.model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"backbone.model.language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"backbone.model.language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"backbone.model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"backbone.model.language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"backbone.model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"backbone.model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"backbone.model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"backbone.model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"backbone.model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"backbone.model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"backbone.model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"backbone.model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"backbone.model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"backbone.model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"backbone.model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"backbone.model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"backbone.model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"backbone.model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"backbone.model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"backbone.model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"backbone.model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"backbone.model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"backbone.model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"backbone.model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"backbone.model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"backbone.model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"backbone.model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"backbone.model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"backbone.model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"backbone.model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"backbone.model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"backbone.model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"backbone.model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"backbone.model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"backbone.model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"backbone.model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"backbone.model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"backbone.model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"backbone.model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"backbone.model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"backbone.model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"backbone.model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"backbone.model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"backbone.model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"backbone.model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"backbone.model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"backbone.model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"backbone.model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"backbone.model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"backbone.model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"backbone.model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"backbone.model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"backbone.model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"backbone.model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"backbone.model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"backbone.model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"backbone.model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"backbone.model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"backbone.model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"backbone.model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"backbone.model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"backbone.model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"backbone.model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"backbone.model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"backbone.model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"backbone.model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"backbone.model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"backbone.model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"backbone.model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"backbone.model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"backbone.model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"backbone.model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"backbone.model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"backbone.model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"backbone.model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"backbone.model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"backbone.model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"backbone.model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"backbone.model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"backbone.model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"backbone.model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"backbone.model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"backbone.model.mlp1.0.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"backbone.model.mlp1.0.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"backbone.model.mlp1.1.bias": "model-00002-of-00002.safetensors",
|
| 368 |
+
"backbone.model.mlp1.1.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"backbone.model.mlp1.3.bias": "model-00002-of-00002.safetensors",
|
| 370 |
+
"backbone.model.mlp1.3.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"backbone.model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 381 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 393 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 395 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 405 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 407 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 511 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 547 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 559 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 595 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 607 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 619 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 631 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 643 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 655 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 667 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 679 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 691 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 703 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 715 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 725 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 727 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 729 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 731 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 735 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 737 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 739 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 741 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 745 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 747 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 749 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 751 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 753 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 759 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 761 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 763 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 767 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 771 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 775 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 777 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 779 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 781 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 785 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 787 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 789 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 794 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 797 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 798 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 799 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 801 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 802 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 804 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 805 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"backbone.model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 807 |
+
"backbone.model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
|
| 808 |
+
}
|
| 809 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eed7c9147abe79a8025285d96c7908488f8659350f47ed553a6f6a0b121eaef6
|
| 3 |
+
size 10272357262
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b977f7fce3669acc32859ceb2be9f798a641f04fcd6b848dc97cf2cfca1b9cc
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50875594b892047c8e46a61b82a18becc1a9e9c9af6ce75ec5a292af0d5a8cd2
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.434782608695652,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.010869565217391304,
|
| 13 |
+
"grad_norm": 6.545120716094971,
|
| 14 |
+
"learning_rate": 4.000000000000001e-06,
|
| 15 |
+
"loss": 1.0169,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.021739130434782608,
|
| 20 |
+
"grad_norm": 31.165016174316406,
|
| 21 |
+
"learning_rate": 8.000000000000001e-06,
|
| 22 |
+
"loss": 0.994,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03260869565217391,
|
| 27 |
+
"grad_norm": 3.4593701362609863,
|
| 28 |
+
"learning_rate": 1.2e-05,
|
| 29 |
+
"loss": 0.7425,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.043478260869565216,
|
| 34 |
+
"grad_norm": 1.7162226438522339,
|
| 35 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 36 |
+
"loss": 0.426,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05434782608695652,
|
| 41 |
+
"grad_norm": 1.7646105289459229,
|
| 42 |
+
"learning_rate": 2e-05,
|
| 43 |
+
"loss": 0.2894,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06521739130434782,
|
| 48 |
+
"grad_norm": 1.069878101348877,
|
| 49 |
+
"learning_rate": 2.4e-05,
|
| 50 |
+
"loss": 0.2568,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07608695652173914,
|
| 55 |
+
"grad_norm": 0.7048421502113342,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 57 |
+
"loss": 0.2031,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08695652173913043,
|
| 62 |
+
"grad_norm": 0.8065099120140076,
|
| 63 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 64 |
+
"loss": 0.1889,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09782608695652174,
|
| 69 |
+
"grad_norm": 0.5573766231536865,
|
| 70 |
+
"learning_rate": 3.6e-05,
|
| 71 |
+
"loss": 0.1703,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.10869565217391304,
|
| 76 |
+
"grad_norm": 0.7829588055610657,
|
| 77 |
+
"learning_rate": 4e-05,
|
| 78 |
+
"loss": 0.1541,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.11956521739130435,
|
| 83 |
+
"grad_norm": 0.7068309783935547,
|
| 84 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 85 |
+
"loss": 0.1548,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.13043478260869565,
|
| 90 |
+
"grad_norm": 0.8238246440887451,
|
| 91 |
+
"learning_rate": 4.8e-05,
|
| 92 |
+
"loss": 0.1285,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14130434782608695,
|
| 97 |
+
"grad_norm": 0.6554062962532043,
|
| 98 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 99 |
+
"loss": 0.1248,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.15217391304347827,
|
| 104 |
+
"grad_norm": 0.7113671898841858,
|
| 105 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 106 |
+
"loss": 0.1257,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.16304347826086957,
|
| 111 |
+
"grad_norm": 0.5627883672714233,
|
| 112 |
+
"learning_rate": 6e-05,
|
| 113 |
+
"loss": 0.1154,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.17391304347826086,
|
| 118 |
+
"grad_norm": 0.5287997722625732,
|
| 119 |
+
"learning_rate": 6.400000000000001e-05,
|
| 120 |
+
"loss": 0.108,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.18478260869565216,
|
| 125 |
+
"grad_norm": 0.5217707753181458,
|
| 126 |
+
"learning_rate": 6.800000000000001e-05,
|
| 127 |
+
"loss": 0.1046,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1956521739130435,
|
| 132 |
+
"grad_norm": 0.834353506565094,
|
| 133 |
+
"learning_rate": 7.2e-05,
|
| 134 |
+
"loss": 0.1027,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.20652173913043478,
|
| 139 |
+
"grad_norm": 0.6808788776397705,
|
| 140 |
+
"learning_rate": 7.6e-05,
|
| 141 |
+
"loss": 0.0856,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.21739130434782608,
|
| 146 |
+
"grad_norm": 0.639272153377533,
|
| 147 |
+
"learning_rate": 8e-05,
|
| 148 |
+
"loss": 0.0938,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.22826086956521738,
|
| 153 |
+
"grad_norm": 0.7152073383331299,
|
| 154 |
+
"learning_rate": 8.4e-05,
|
| 155 |
+
"loss": 0.0951,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2391304347826087,
|
| 160 |
+
"grad_norm": 0.47022637724876404,
|
| 161 |
+
"learning_rate": 8.800000000000001e-05,
|
| 162 |
+
"loss": 0.0893,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.25,
|
| 167 |
+
"grad_norm": 0.7306397557258606,
|
| 168 |
+
"learning_rate": 9.200000000000001e-05,
|
| 169 |
+
"loss": 0.084,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2608695652173913,
|
| 174 |
+
"grad_norm": 0.5324788093566895,
|
| 175 |
+
"learning_rate": 9.6e-05,
|
| 176 |
+
"loss": 0.082,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2717391304347826,
|
| 181 |
+
"grad_norm": 0.46213847398757935,
|
| 182 |
+
"learning_rate": 0.0001,
|
| 183 |
+
"loss": 0.0781,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2826086956521739,
|
| 188 |
+
"grad_norm": 0.6270459294319153,
|
| 189 |
+
"learning_rate": 9.999890641901125e-05,
|
| 190 |
+
"loss": 0.0761,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.29347826086956524,
|
| 195 |
+
"grad_norm": 0.6771764159202576,
|
| 196 |
+
"learning_rate": 9.99956257238817e-05,
|
| 197 |
+
"loss": 0.0807,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.30434782608695654,
|
| 202 |
+
"grad_norm": 0.4983552396297455,
|
| 203 |
+
"learning_rate": 9.999015805811965e-05,
|
| 204 |
+
"loss": 0.0785,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.31521739130434784,
|
| 209 |
+
"grad_norm": 0.6947988271713257,
|
| 210 |
+
"learning_rate": 9.998250366089848e-05,
|
| 211 |
+
"loss": 0.0819,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.32608695652173914,
|
| 216 |
+
"grad_norm": 0.7602576017379761,
|
| 217 |
+
"learning_rate": 9.997266286704631e-05,
|
| 218 |
+
"loss": 0.0718,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.33695652173913043,
|
| 223 |
+
"grad_norm": 0.5555041432380676,
|
| 224 |
+
"learning_rate": 9.996063610703137e-05,
|
| 225 |
+
"loss": 0.0763,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.34782608695652173,
|
| 230 |
+
"grad_norm": 0.4837249219417572,
|
| 231 |
+
"learning_rate": 9.994642390694308e-05,
|
| 232 |
+
"loss": 0.0713,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.358695652173913,
|
| 237 |
+
"grad_norm": 0.3204691410064697,
|
| 238 |
+
"learning_rate": 9.993002688846913e-05,
|
| 239 |
+
"loss": 0.0702,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3695652173913043,
|
| 244 |
+
"grad_norm": 0.522548258304596,
|
| 245 |
+
"learning_rate": 9.991144576886823e-05,
|
| 246 |
+
"loss": 0.0664,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.3804347826086957,
|
| 251 |
+
"grad_norm": 0.43463149666786194,
|
| 252 |
+
"learning_rate": 9.989068136093873e-05,
|
| 253 |
+
"loss": 0.0589,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.391304347826087,
|
| 258 |
+
"grad_norm": 0.509681761264801,
|
| 259 |
+
"learning_rate": 9.986773457298311e-05,
|
| 260 |
+
"loss": 0.0664,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.40217391304347827,
|
| 265 |
+
"grad_norm": 0.4732968509197235,
|
| 266 |
+
"learning_rate": 9.984260640876821e-05,
|
| 267 |
+
"loss": 0.0654,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.41304347826086957,
|
| 272 |
+
"grad_norm": 0.3513120114803314,
|
| 273 |
+
"learning_rate": 9.981529796748134e-05,
|
| 274 |
+
"loss": 0.0591,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.42391304347826086,
|
| 279 |
+
"grad_norm": 0.33960211277008057,
|
| 280 |
+
"learning_rate": 9.97858104436822e-05,
|
| 281 |
+
"loss": 0.0574,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.43478260869565216,
|
| 286 |
+
"grad_norm": 0.4988704025745392,
|
| 287 |
+
"learning_rate": 9.975414512725057e-05,
|
| 288 |
+
"loss": 0.056,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.44565217391304346,
|
| 293 |
+
"grad_norm": 0.41242533922195435,
|
| 294 |
+
"learning_rate": 9.972030340333001e-05,
|
| 295 |
+
"loss": 0.0625,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.45652173913043476,
|
| 300 |
+
"grad_norm": 0.48576557636260986,
|
| 301 |
+
"learning_rate": 9.968428675226714e-05,
|
| 302 |
+
"loss": 0.0574,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4673913043478261,
|
| 307 |
+
"grad_norm": 0.7005183696746826,
|
| 308 |
+
"learning_rate": 9.964609674954696e-05,
|
| 309 |
+
"loss": 0.057,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.4782608695652174,
|
| 314 |
+
"grad_norm": 0.37756964564323425,
|
| 315 |
+
"learning_rate": 9.96057350657239e-05,
|
| 316 |
+
"loss": 0.0559,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.4891304347826087,
|
| 321 |
+
"grad_norm": 0.4204326868057251,
|
| 322 |
+
"learning_rate": 9.956320346634876e-05,
|
| 323 |
+
"loss": 0.0547,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5,
|
| 328 |
+
"grad_norm": 0.3505024015903473,
|
| 329 |
+
"learning_rate": 9.95185038118915e-05,
|
| 330 |
+
"loss": 0.061,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5108695652173914,
|
| 335 |
+
"grad_norm": 0.3341296315193176,
|
| 336 |
+
"learning_rate": 9.94716380576598e-05,
|
| 337 |
+
"loss": 0.06,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5217391304347826,
|
| 342 |
+
"grad_norm": 0.5188870429992676,
|
| 343 |
+
"learning_rate": 9.942260825371358e-05,
|
| 344 |
+
"loss": 0.0572,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.532608695652174,
|
| 349 |
+
"grad_norm": 0.42490994930267334,
|
| 350 |
+
"learning_rate": 9.937141654477528e-05,
|
| 351 |
+
"loss": 0.0537,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5434782608695652,
|
| 356 |
+
"grad_norm": 0.4381064474582672,
|
| 357 |
+
"learning_rate": 9.931806517013612e-05,
|
| 358 |
+
"loss": 0.0507,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5543478260869565,
|
| 363 |
+
"grad_norm": 0.3873785436153412,
|
| 364 |
+
"learning_rate": 9.926255646355804e-05,
|
| 365 |
+
"loss": 0.0521,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5652173913043478,
|
| 370 |
+
"grad_norm": 0.3180992007255554,
|
| 371 |
+
"learning_rate": 9.92048928531717e-05,
|
| 372 |
+
"loss": 0.0482,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5760869565217391,
|
| 377 |
+
"grad_norm": 0.34632715582847595,
|
| 378 |
+
"learning_rate": 9.914507686137019e-05,
|
| 379 |
+
"loss": 0.0526,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5869565217391305,
|
| 384 |
+
"grad_norm": 0.4718571603298187,
|
| 385 |
+
"learning_rate": 9.90831111046988e-05,
|
| 386 |
+
"loss": 0.0486,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.5978260869565217,
|
| 391 |
+
"grad_norm": 0.36883848905563354,
|
| 392 |
+
"learning_rate": 9.901899829374047e-05,
|
| 393 |
+
"loss": 0.0461,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6086956521739131,
|
| 398 |
+
"grad_norm": 0.36269769072532654,
|
| 399 |
+
"learning_rate": 9.895274123299723e-05,
|
| 400 |
+
"loss": 0.0439,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6195652173913043,
|
| 405 |
+
"grad_norm": 0.3643960654735565,
|
| 406 |
+
"learning_rate": 9.888434282076758e-05,
|
| 407 |
+
"loss": 0.0448,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6304347826086957,
|
| 412 |
+
"grad_norm": 0.2864445745944977,
|
| 413 |
+
"learning_rate": 9.881380604901964e-05,
|
| 414 |
+
"loss": 0.0459,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6413043478260869,
|
| 419 |
+
"grad_norm": 0.41547855734825134,
|
| 420 |
+
"learning_rate": 9.87411340032603e-05,
|
| 421 |
+
"loss": 0.0493,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6521739130434783,
|
| 426 |
+
"grad_norm": 0.23883788287639618,
|
| 427 |
+
"learning_rate": 9.86663298624003e-05,
|
| 428 |
+
"loss": 0.05,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6630434782608695,
|
| 433 |
+
"grad_norm": 0.3606937527656555,
|
| 434 |
+
"learning_rate": 9.858939689861506e-05,
|
| 435 |
+
"loss": 0.0552,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6739130434782609,
|
| 440 |
+
"grad_norm": 0.3378564715385437,
|
| 441 |
+
"learning_rate": 9.851033847720166e-05,
|
| 442 |
+
"loss": 0.0445,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6847826086956522,
|
| 447 |
+
"grad_norm": 0.3886934816837311,
|
| 448 |
+
"learning_rate": 9.842915805643155e-05,
|
| 449 |
+
"loss": 0.0398,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6956521739130435,
|
| 454 |
+
"grad_norm": 0.34393632411956787,
|
| 455 |
+
"learning_rate": 9.834585918739936e-05,
|
| 456 |
+
"loss": 0.0423,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7065217391304348,
|
| 461 |
+
"grad_norm": 0.37075570225715637,
|
| 462 |
+
"learning_rate": 9.826044551386744e-05,
|
| 463 |
+
"loss": 0.0474,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.717391304347826,
|
| 468 |
+
"grad_norm": 0.45477569103240967,
|
| 469 |
+
"learning_rate": 9.817292077210659e-05,
|
| 470 |
+
"loss": 0.0491,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7282608695652174,
|
| 475 |
+
"grad_norm": 0.3451235890388489,
|
| 476 |
+
"learning_rate": 9.808328879073251e-05,
|
| 477 |
+
"loss": 0.0532,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7391304347826086,
|
| 482 |
+
"grad_norm": 0.31069430708885193,
|
| 483 |
+
"learning_rate": 9.799155349053851e-05,
|
| 484 |
+
"loss": 0.0481,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.75,
|
| 489 |
+
"grad_norm": 0.33381545543670654,
|
| 490 |
+
"learning_rate": 9.789771888432375e-05,
|
| 491 |
+
"loss": 0.0439,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7608695652173914,
|
| 496 |
+
"grad_norm": 0.3076520264148712,
|
| 497 |
+
"learning_rate": 9.780178907671789e-05,
|
| 498 |
+
"loss": 0.0413,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.7717391304347826,
|
| 503 |
+
"grad_norm": 0.4080972969532013,
|
| 504 |
+
"learning_rate": 9.77037682640015e-05,
|
| 505 |
+
"loss": 0.0524,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.782608695652174,
|
| 510 |
+
"grad_norm": 0.4061325490474701,
|
| 511 |
+
"learning_rate": 9.760366073392246e-05,
|
| 512 |
+
"loss": 0.0436,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.7934782608695652,
|
| 517 |
+
"grad_norm": 0.32753169536590576,
|
| 518 |
+
"learning_rate": 9.750147086550844e-05,
|
| 519 |
+
"loss": 0.0456,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8043478260869565,
|
| 524 |
+
"grad_norm": 0.255860835313797,
|
| 525 |
+
"learning_rate": 9.739720312887535e-05,
|
| 526 |
+
"loss": 0.0368,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.8152173913043478,
|
| 531 |
+
"grad_norm": 0.3491983115673065,
|
| 532 |
+
"learning_rate": 9.729086208503174e-05,
|
| 533 |
+
"loss": 0.0419,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8260869565217391,
|
| 538 |
+
"grad_norm": 0.38648349046707153,
|
| 539 |
+
"learning_rate": 9.718245238567939e-05,
|
| 540 |
+
"loss": 0.0377,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.8369565217391305,
|
| 545 |
+
"grad_norm": 0.28146737813949585,
|
| 546 |
+
"learning_rate": 9.707197877300974e-05,
|
| 547 |
+
"loss": 0.0391,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8478260869565217,
|
| 552 |
+
"grad_norm": 0.32342949509620667,
|
| 553 |
+
"learning_rate": 9.695944607949649e-05,
|
| 554 |
+
"loss": 0.0393,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8586956521739131,
|
| 559 |
+
"grad_norm": 0.320584774017334,
|
| 560 |
+
"learning_rate": 9.684485922768422e-05,
|
| 561 |
+
"loss": 0.0387,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8695652173913043,
|
| 566 |
+
"grad_norm": 0.34208914637565613,
|
| 567 |
+
"learning_rate": 9.672822322997305e-05,
|
| 568 |
+
"loss": 0.0417,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8804347826086957,
|
| 573 |
+
"grad_norm": 0.27788016200065613,
|
| 574 |
+
"learning_rate": 9.660954318839933e-05,
|
| 575 |
+
"loss": 0.044,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.8913043478260869,
|
| 580 |
+
"grad_norm": 0.3619558811187744,
|
| 581 |
+
"learning_rate": 9.648882429441257e-05,
|
| 582 |
+
"loss": 0.0418,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.9021739130434783,
|
| 587 |
+
"grad_norm": 0.3278563618659973,
|
| 588 |
+
"learning_rate": 9.636607182864827e-05,
|
| 589 |
+
"loss": 0.0439,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9130434782608695,
|
| 594 |
+
"grad_norm": 0.3712303936481476,
|
| 595 |
+
"learning_rate": 9.624129116069694e-05,
|
| 596 |
+
"loss": 0.0404,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9239130434782609,
|
| 601 |
+
"grad_norm": 0.23256783187389374,
|
| 602 |
+
"learning_rate": 9.611448774886924e-05,
|
| 603 |
+
"loss": 0.0463,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9347826086956522,
|
| 608 |
+
"grad_norm": 0.3841691017150879,
|
| 609 |
+
"learning_rate": 9.598566713995718e-05,
|
| 610 |
+
"loss": 0.038,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9456521739130435,
|
| 615 |
+
"grad_norm": 0.4116934835910797,
|
| 616 |
+
"learning_rate": 9.58548349689915e-05,
|
| 617 |
+
"loss": 0.0397,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.9565217391304348,
|
| 622 |
+
"grad_norm": 0.3569575846195221,
|
| 623 |
+
"learning_rate": 9.572199695899522e-05,
|
| 624 |
+
"loss": 0.0373,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.967391304347826,
|
| 629 |
+
"grad_norm": 0.32062098383903503,
|
| 630 |
+
"learning_rate": 9.558715892073323e-05,
|
| 631 |
+
"loss": 0.0382,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9782608695652174,
|
| 636 |
+
"grad_norm": 0.3369348347187042,
|
| 637 |
+
"learning_rate": 9.545032675245813e-05,
|
| 638 |
+
"loss": 0.0469,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9891304347826086,
|
| 643 |
+
"grad_norm": 0.3673070967197418,
|
| 644 |
+
"learning_rate": 9.531150643965223e-05,
|
| 645 |
+
"loss": 0.0328,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.0,
|
| 650 |
+
"grad_norm": 0.4159371554851532,
|
| 651 |
+
"learning_rate": 9.517070405476575e-05,
|
| 652 |
+
"loss": 0.0403,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.0108695652173914,
|
| 657 |
+
"grad_norm": 0.19767124950885773,
|
| 658 |
+
"learning_rate": 9.502792575695112e-05,
|
| 659 |
+
"loss": 0.0322,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.0217391304347827,
|
| 664 |
+
"grad_norm": 0.32694023847579956,
|
| 665 |
+
"learning_rate": 9.488317779179361e-05,
|
| 666 |
+
"loss": 0.0345,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.0326086956521738,
|
| 671 |
+
"grad_norm": 0.2887076735496521,
|
| 672 |
+
"learning_rate": 9.473646649103818e-05,
|
| 673 |
+
"loss": 0.0407,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.0434782608695652,
|
| 678 |
+
"grad_norm": 0.22730398178100586,
|
| 679 |
+
"learning_rate": 9.458779827231237e-05,
|
| 680 |
+
"loss": 0.0302,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.0543478260869565,
|
| 685 |
+
"grad_norm": 0.3960530757904053,
|
| 686 |
+
"learning_rate": 9.443717963884569e-05,
|
| 687 |
+
"loss": 0.0317,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.065217391304348,
|
| 692 |
+
"grad_norm": 0.21886062622070312,
|
| 693 |
+
"learning_rate": 9.428461717918511e-05,
|
| 694 |
+
"loss": 0.0336,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.0760869565217392,
|
| 699 |
+
"grad_norm": 0.2685090899467468,
|
| 700 |
+
"learning_rate": 9.413011756690685e-05,
|
| 701 |
+
"loss": 0.0367,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.0869565217391304,
|
| 706 |
+
"grad_norm": 0.2610633373260498,
|
| 707 |
+
"learning_rate": 9.397368756032445e-05,
|
| 708 |
+
"loss": 0.0343,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.0978260869565217,
|
| 713 |
+
"grad_norm": 0.2550532817840576,
|
| 714 |
+
"learning_rate": 9.381533400219318e-05,
|
| 715 |
+
"loss": 0.0338,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.108695652173913,
|
| 720 |
+
"grad_norm": 0.2943401038646698,
|
| 721 |
+
"learning_rate": 9.365506381941066e-05,
|
| 722 |
+
"loss": 0.0336,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.1195652173913044,
|
| 727 |
+
"grad_norm": 0.22352245450019836,
|
| 728 |
+
"learning_rate": 9.349288402271388e-05,
|
| 729 |
+
"loss": 0.0311,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.1304347826086956,
|
| 734 |
+
"grad_norm": 0.2989339828491211,
|
| 735 |
+
"learning_rate": 9.332880170637252e-05,
|
| 736 |
+
"loss": 0.0352,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.141304347826087,
|
| 741 |
+
"grad_norm": 0.28045058250427246,
|
| 742 |
+
"learning_rate": 9.316282404787871e-05,
|
| 743 |
+
"loss": 0.0305,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.1521739130434783,
|
| 748 |
+
"grad_norm": 0.3019992709159851,
|
| 749 |
+
"learning_rate": 9.299495830763286e-05,
|
| 750 |
+
"loss": 0.0392,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.1630434782608696,
|
| 755 |
+
"grad_norm": 0.17657537758350372,
|
| 756 |
+
"learning_rate": 9.282521182862629e-05,
|
| 757 |
+
"loss": 0.0361,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.1739130434782608,
|
| 762 |
+
"grad_norm": 0.30781546235084534,
|
| 763 |
+
"learning_rate": 9.265359203611987e-05,
|
| 764 |
+
"loss": 0.0337,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.184782608695652,
|
| 769 |
+
"grad_norm": 0.2609535753726959,
|
| 770 |
+
"learning_rate": 9.248010643731935e-05,
|
| 771 |
+
"loss": 0.0269,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.1956521739130435,
|
| 776 |
+
"grad_norm": 0.28583014011383057,
|
| 777 |
+
"learning_rate": 9.230476262104677e-05,
|
| 778 |
+
"loss": 0.0306,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.2065217391304348,
|
| 783 |
+
"grad_norm": 0.4076569974422455,
|
| 784 |
+
"learning_rate": 9.212756825740873e-05,
|
| 785 |
+
"loss": 0.0359,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.2173913043478262,
|
| 790 |
+
"grad_norm": 0.41756731271743774,
|
| 791 |
+
"learning_rate": 9.194853109746074e-05,
|
| 792 |
+
"loss": 0.0338,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.2282608695652173,
|
| 797 |
+
"grad_norm": 0.363546222448349,
|
| 798 |
+
"learning_rate": 9.176765897286813e-05,
|
| 799 |
+
"loss": 0.0386,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.2391304347826086,
|
| 804 |
+
"grad_norm": 0.3960663378238678,
|
| 805 |
+
"learning_rate": 9.158495979556358e-05,
|
| 806 |
+
"loss": 0.0369,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.25,
|
| 811 |
+
"grad_norm": 0.260600209236145,
|
| 812 |
+
"learning_rate": 9.140044155740101e-05,
|
| 813 |
+
"loss": 0.0357,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.2608695652173914,
|
| 818 |
+
"grad_norm": 0.24292735755443573,
|
| 819 |
+
"learning_rate": 9.121411232980588e-05,
|
| 820 |
+
"loss": 0.0339,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.2717391304347827,
|
| 825 |
+
"grad_norm": 0.27685248851776123,
|
| 826 |
+
"learning_rate": 9.102598026342222e-05,
|
| 827 |
+
"loss": 0.0341,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.2826086956521738,
|
| 832 |
+
"grad_norm": 0.26668187975883484,
|
| 833 |
+
"learning_rate": 9.083605358775612e-05,
|
| 834 |
+
"loss": 0.032,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.2934782608695652,
|
| 839 |
+
"grad_norm": 0.27872323989868164,
|
| 840 |
+
"learning_rate": 9.064434061081562e-05,
|
| 841 |
+
"loss": 0.033,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.3043478260869565,
|
| 846 |
+
"grad_norm": 0.2735164761543274,
|
| 847 |
+
"learning_rate": 9.045084971874738e-05,
|
| 848 |
+
"loss": 0.0354,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.315217391304348,
|
| 853 |
+
"grad_norm": 0.28554099798202515,
|
| 854 |
+
"learning_rate": 9.025558937546988e-05,
|
| 855 |
+
"loss": 0.0318,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.3260869565217392,
|
| 860 |
+
"grad_norm": 0.30446696281433105,
|
| 861 |
+
"learning_rate": 9.005856812230304e-05,
|
| 862 |
+
"loss": 0.0285,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.3369565217391304,
|
| 867 |
+
"grad_norm": 0.3049046993255615,
|
| 868 |
+
"learning_rate": 8.98597945775948e-05,
|
| 869 |
+
"loss": 0.0345,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.3478260869565217,
|
| 874 |
+
"grad_norm": 0.29424118995666504,
|
| 875 |
+
"learning_rate": 8.965927743634391e-05,
|
| 876 |
+
"loss": 0.0304,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.358695652173913,
|
| 881 |
+
"grad_norm": 0.350027471780777,
|
| 882 |
+
"learning_rate": 8.945702546981969e-05,
|
| 883 |
+
"loss": 0.037,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.3695652173913042,
|
| 888 |
+
"grad_norm": 0.24161510169506073,
|
| 889 |
+
"learning_rate": 8.92530475251784e-05,
|
| 890 |
+
"loss": 0.0296,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.3804347826086958,
|
| 895 |
+
"grad_norm": 0.28369140625,
|
| 896 |
+
"learning_rate": 8.90473525250761e-05,
|
| 897 |
+
"loss": 0.0338,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.391304347826087,
|
| 902 |
+
"grad_norm": 0.2735034227371216,
|
| 903 |
+
"learning_rate": 8.883994946727849e-05,
|
| 904 |
+
"loss": 0.0327,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.4021739130434783,
|
| 909 |
+
"grad_norm": 0.26561832427978516,
|
| 910 |
+
"learning_rate": 8.863084742426719e-05,
|
| 911 |
+
"loss": 0.0357,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.4130434782608696,
|
| 916 |
+
"grad_norm": 0.22670572996139526,
|
| 917 |
+
"learning_rate": 8.842005554284296e-05,
|
| 918 |
+
"loss": 0.0309,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.4239130434782608,
|
| 923 |
+
"grad_norm": 0.3178609311580658,
|
| 924 |
+
"learning_rate": 8.820758304372557e-05,
|
| 925 |
+
"loss": 0.0307,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.434782608695652,
|
| 930 |
+
"grad_norm": 0.2610357999801636,
|
| 931 |
+
"learning_rate": 8.799343922115044e-05,
|
| 932 |
+
"loss": 0.0321,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.4456521739130435,
|
| 937 |
+
"grad_norm": 0.2457573115825653,
|
| 938 |
+
"learning_rate": 8.77776334424621e-05,
|
| 939 |
+
"loss": 0.0279,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.4565217391304348,
|
| 944 |
+
"grad_norm": 0.28615960478782654,
|
| 945 |
+
"learning_rate": 8.756017514770443e-05,
|
| 946 |
+
"loss": 0.0312,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.4673913043478262,
|
| 951 |
+
"grad_norm": 0.24879348278045654,
|
| 952 |
+
"learning_rate": 8.73410738492077e-05,
|
| 953 |
+
"loss": 0.026,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.4782608695652173,
|
| 958 |
+
"grad_norm": 0.31809213757514954,
|
| 959 |
+
"learning_rate": 8.71203391311725e-05,
|
| 960 |
+
"loss": 0.0304,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.4891304347826086,
|
| 965 |
+
"grad_norm": 0.28537970781326294,
|
| 966 |
+
"learning_rate": 8.689798064925049e-05,
|
| 967 |
+
"loss": 0.0234,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.5,
|
| 972 |
+
"grad_norm": 0.2417411208152771,
|
| 973 |
+
"learning_rate": 8.6674008130122e-05,
|
| 974 |
+
"loss": 0.0294,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.5108695652173914,
|
| 979 |
+
"grad_norm": 0.3035632371902466,
|
| 980 |
+
"learning_rate": 8.644843137107059e-05,
|
| 981 |
+
"loss": 0.0261,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.5217391304347827,
|
| 986 |
+
"grad_norm": 0.2237926870584488,
|
| 987 |
+
"learning_rate": 8.622126023955446e-05,
|
| 988 |
+
"loss": 0.0321,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.5326086956521738,
|
| 993 |
+
"grad_norm": 0.23017100989818573,
|
| 994 |
+
"learning_rate": 8.599250467277483e-05,
|
| 995 |
+
"loss": 0.0261,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.5434782608695652,
|
| 1000 |
+
"grad_norm": 0.3059643805027008,
|
| 1001 |
+
"learning_rate": 8.576217467724128e-05,
|
| 1002 |
+
"loss": 0.0317,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.5543478260869565,
|
| 1007 |
+
"grad_norm": 0.24075447022914886,
|
| 1008 |
+
"learning_rate": 8.553028032833397e-05,
|
| 1009 |
+
"loss": 0.03,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.5652173913043477,
|
| 1014 |
+
"grad_norm": 0.2758166491985321,
|
| 1015 |
+
"learning_rate": 8.529683176986295e-05,
|
| 1016 |
+
"loss": 0.0292,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.5760869565217392,
|
| 1021 |
+
"grad_norm": 0.3072378933429718,
|
| 1022 |
+
"learning_rate": 8.506183921362443e-05,
|
| 1023 |
+
"loss": 0.0304,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.5869565217391304,
|
| 1028 |
+
"grad_norm": 0.31627902388572693,
|
| 1029 |
+
"learning_rate": 8.482531293895412e-05,
|
| 1030 |
+
"loss": 0.0305,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.5978260869565217,
|
| 1035 |
+
"grad_norm": 0.2496868222951889,
|
| 1036 |
+
"learning_rate": 8.458726329227747e-05,
|
| 1037 |
+
"loss": 0.0294,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.608695652173913,
|
| 1042 |
+
"grad_norm": 0.22909675538539886,
|
| 1043 |
+
"learning_rate": 8.434770068665723e-05,
|
| 1044 |
+
"loss": 0.037,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.6195652173913042,
|
| 1049 |
+
"grad_norm": 0.2690674960613251,
|
| 1050 |
+
"learning_rate": 8.410663560133784e-05,
|
| 1051 |
+
"loss": 0.0295,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.6304347826086958,
|
| 1056 |
+
"grad_norm": 0.24377554655075073,
|
| 1057 |
+
"learning_rate": 8.386407858128706e-05,
|
| 1058 |
+
"loss": 0.0352,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.641304347826087,
|
| 1063 |
+
"grad_norm": 0.2325594425201416,
|
| 1064 |
+
"learning_rate": 8.362004023673474e-05,
|
| 1065 |
+
"loss": 0.0306,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.6521739130434783,
|
| 1070 |
+
"grad_norm": 0.2231265902519226,
|
| 1071 |
+
"learning_rate": 8.337453124270863e-05,
|
| 1072 |
+
"loss": 0.0283,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.6630434782608696,
|
| 1077 |
+
"grad_norm": 0.23302611708641052,
|
| 1078 |
+
"learning_rate": 8.31275623385675e-05,
|
| 1079 |
+
"loss": 0.0312,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.6739130434782608,
|
| 1084 |
+
"grad_norm": 0.27481865882873535,
|
| 1085 |
+
"learning_rate": 8.287914432753123e-05,
|
| 1086 |
+
"loss": 0.0325,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.6847826086956523,
|
| 1091 |
+
"grad_norm": 0.2550845742225647,
|
| 1092 |
+
"learning_rate": 8.262928807620843e-05,
|
| 1093 |
+
"loss": 0.031,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.6956521739130435,
|
| 1098 |
+
"grad_norm": 0.22116337716579437,
|
| 1099 |
+
"learning_rate": 8.237800451412095e-05,
|
| 1100 |
+
"loss": 0.0279,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.7065217391304348,
|
| 1105 |
+
"grad_norm": 0.3845021724700928,
|
| 1106 |
+
"learning_rate": 8.212530463322583e-05,
|
| 1107 |
+
"loss": 0.0297,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.7173913043478262,
|
| 1112 |
+
"grad_norm": 0.3023184835910797,
|
| 1113 |
+
"learning_rate": 8.18711994874345e-05,
|
| 1114 |
+
"loss": 0.0284,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.7282608695652173,
|
| 1119 |
+
"grad_norm": 0.21632587909698486,
|
| 1120 |
+
"learning_rate": 8.161570019212921e-05,
|
| 1121 |
+
"loss": 0.0292,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.7391304347826086,
|
| 1126 |
+
"grad_norm": 0.2863970398902893,
|
| 1127 |
+
"learning_rate": 8.135881792367686e-05,
|
| 1128 |
+
"loss": 0.0287,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.75,
|
| 1133 |
+
"grad_norm": 0.20062358677387238,
|
| 1134 |
+
"learning_rate": 8.110056391894005e-05,
|
| 1135 |
+
"loss": 0.0246,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.7608695652173914,
|
| 1140 |
+
"grad_norm": 0.2996312379837036,
|
| 1141 |
+
"learning_rate": 8.084094947478556e-05,
|
| 1142 |
+
"loss": 0.0234,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.7717391304347827,
|
| 1147 |
+
"grad_norm": 0.2715204060077667,
|
| 1148 |
+
"learning_rate": 8.057998594759022e-05,
|
| 1149 |
+
"loss": 0.0267,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.7826086956521738,
|
| 1154 |
+
"grad_norm": 0.27594679594039917,
|
| 1155 |
+
"learning_rate": 8.031768475274413e-05,
|
| 1156 |
+
"loss": 0.0274,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.7934782608695652,
|
| 1161 |
+
"grad_norm": 0.25428059697151184,
|
| 1162 |
+
"learning_rate": 8.005405736415126e-05,
|
| 1163 |
+
"loss": 0.0326,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.8043478260869565,
|
| 1168 |
+
"grad_norm": 0.241542249917984,
|
| 1169 |
+
"learning_rate": 7.978911531372765e-05,
|
| 1170 |
+
"loss": 0.0209,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.8152173913043477,
|
| 1175 |
+
"grad_norm": 0.2677355408668518,
|
| 1176 |
+
"learning_rate": 7.952287019089685e-05,
|
| 1177 |
+
"loss": 0.0268,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.8260869565217392,
|
| 1182 |
+
"grad_norm": 0.19579513370990753,
|
| 1183 |
+
"learning_rate": 7.925533364208309e-05,
|
| 1184 |
+
"loss": 0.0284,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.8369565217391304,
|
| 1189 |
+
"grad_norm": 0.21474671363830566,
|
| 1190 |
+
"learning_rate": 7.898651737020166e-05,
|
| 1191 |
+
"loss": 0.0274,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.8478260869565217,
|
| 1196 |
+
"grad_norm": 0.24959373474121094,
|
| 1197 |
+
"learning_rate": 7.871643313414718e-05,
|
| 1198 |
+
"loss": 0.0257,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.858695652173913,
|
| 1203 |
+
"grad_norm": 0.24523958563804626,
|
| 1204 |
+
"learning_rate": 7.844509274827907e-05,
|
| 1205 |
+
"loss": 0.0253,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.8695652173913042,
|
| 1210 |
+
"grad_norm": 0.29573023319244385,
|
| 1211 |
+
"learning_rate": 7.817250808190483e-05,
|
| 1212 |
+
"loss": 0.0298,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.8804347826086958,
|
| 1217 |
+
"grad_norm": 0.3292531669139862,
|
| 1218 |
+
"learning_rate": 7.789869105876083e-05,
|
| 1219 |
+
"loss": 0.029,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.891304347826087,
|
| 1224 |
+
"grad_norm": 0.24724705517292023,
|
| 1225 |
+
"learning_rate": 7.762365365649067e-05,
|
| 1226 |
+
"loss": 0.0244,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.9021739130434783,
|
| 1231 |
+
"grad_norm": 0.21725831925868988,
|
| 1232 |
+
"learning_rate": 7.734740790612136e-05,
|
| 1233 |
+
"loss": 0.0286,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.9130434782608696,
|
| 1238 |
+
"grad_norm": 0.2548612058162689,
|
| 1239 |
+
"learning_rate": 7.70699658915369e-05,
|
| 1240 |
+
"loss": 0.0298,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.9239130434782608,
|
| 1245 |
+
"grad_norm": 0.27427971363067627,
|
| 1246 |
+
"learning_rate": 7.679133974894983e-05,
|
| 1247 |
+
"loss": 0.0285,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.9347826086956523,
|
| 1252 |
+
"grad_norm": 0.2469799667596817,
|
| 1253 |
+
"learning_rate": 7.651154166637025e-05,
|
| 1254 |
+
"loss": 0.0285,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.9456521739130435,
|
| 1259 |
+
"grad_norm": 0.27580276131629944,
|
| 1260 |
+
"learning_rate": 7.623058388307269e-05,
|
| 1261 |
+
"loss": 0.0295,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.9565217391304348,
|
| 1266 |
+
"grad_norm": 0.2752760350704193,
|
| 1267 |
+
"learning_rate": 7.594847868906076e-05,
|
| 1268 |
+
"loss": 0.0293,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.9673913043478262,
|
| 1273 |
+
"grad_norm": 0.24122604727745056,
|
| 1274 |
+
"learning_rate": 7.566523842452958e-05,
|
| 1275 |
+
"loss": 0.028,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.9782608695652173,
|
| 1280 |
+
"grad_norm": 0.34590691328048706,
|
| 1281 |
+
"learning_rate": 7.538087547932585e-05,
|
| 1282 |
+
"loss": 0.023,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.9891304347826086,
|
| 1287 |
+
"grad_norm": 0.217288076877594,
|
| 1288 |
+
"learning_rate": 7.509540229240601e-05,
|
| 1289 |
+
"loss": 0.0241,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.0,
|
| 1294 |
+
"grad_norm": 0.2541623115539551,
|
| 1295 |
+
"learning_rate": 7.480883135129211e-05,
|
| 1296 |
+
"loss": 0.0241,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.010869565217391,
|
| 1301 |
+
"grad_norm": 0.27332010865211487,
|
| 1302 |
+
"learning_rate": 7.452117519152542e-05,
|
| 1303 |
+
"loss": 0.0232,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.0217391304347827,
|
| 1308 |
+
"grad_norm": 0.18972714245319366,
|
| 1309 |
+
"learning_rate": 7.423244639611826e-05,
|
| 1310 |
+
"loss": 0.0273,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.032608695652174,
|
| 1315 |
+
"grad_norm": 0.19656722247600555,
|
| 1316 |
+
"learning_rate": 7.394265759500348e-05,
|
| 1317 |
+
"loss": 0.027,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.0434782608695654,
|
| 1322 |
+
"grad_norm": 0.22846871614456177,
|
| 1323 |
+
"learning_rate": 7.365182146448205e-05,
|
| 1324 |
+
"loss": 0.0225,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.0543478260869565,
|
| 1329 |
+
"grad_norm": 0.21889623999595642,
|
| 1330 |
+
"learning_rate": 7.335995072666848e-05,
|
| 1331 |
+
"loss": 0.0212,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.0652173913043477,
|
| 1336 |
+
"grad_norm": 0.15208809077739716,
|
| 1337 |
+
"learning_rate": 7.30670581489344e-05,
|
| 1338 |
+
"loss": 0.0284,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.0760869565217392,
|
| 1343 |
+
"grad_norm": 0.30196961760520935,
|
| 1344 |
+
"learning_rate": 7.277315654334997e-05,
|
| 1345 |
+
"loss": 0.0256,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.0869565217391304,
|
| 1350 |
+
"grad_norm": 0.3277256190776825,
|
| 1351 |
+
"learning_rate": 7.247825876612353e-05,
|
| 1352 |
+
"loss": 0.0234,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.097826086956522,
|
| 1357 |
+
"grad_norm": 0.24114277958869934,
|
| 1358 |
+
"learning_rate": 7.218237771703921e-05,
|
| 1359 |
+
"loss": 0.0251,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.108695652173913,
|
| 1364 |
+
"grad_norm": 0.27464061975479126,
|
| 1365 |
+
"learning_rate": 7.188552633889259e-05,
|
| 1366 |
+
"loss": 0.0272,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.119565217391304,
|
| 1371 |
+
"grad_norm": 0.24296048283576965,
|
| 1372 |
+
"learning_rate": 7.158771761692464e-05,
|
| 1373 |
+
"loss": 0.024,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.130434782608696,
|
| 1378 |
+
"grad_norm": 0.17170515656471252,
|
| 1379 |
+
"learning_rate": 7.128896457825364e-05,
|
| 1380 |
+
"loss": 0.0198,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.141304347826087,
|
| 1385 |
+
"grad_norm": 0.20415639877319336,
|
| 1386 |
+
"learning_rate": 7.09892802913053e-05,
|
| 1387 |
+
"loss": 0.0278,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.1521739130434785,
|
| 1392 |
+
"grad_norm": 0.20857463777065277,
|
| 1393 |
+
"learning_rate": 7.068867786524116e-05,
|
| 1394 |
+
"loss": 0.0314,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.1630434782608696,
|
| 1399 |
+
"grad_norm": 0.293731153011322,
|
| 1400 |
+
"learning_rate": 7.038717044938519e-05,
|
| 1401 |
+
"loss": 0.0227,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.1739130434782608,
|
| 1406 |
+
"grad_norm": 0.18717971444129944,
|
| 1407 |
+
"learning_rate": 7.008477123264848e-05,
|
| 1408 |
+
"loss": 0.0195,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.1847826086956523,
|
| 1413 |
+
"grad_norm": 0.22212952375411987,
|
| 1414 |
+
"learning_rate": 6.978149344295242e-05,
|
| 1415 |
+
"loss": 0.0216,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.1956521739130435,
|
| 1420 |
+
"grad_norm": 0.2290237843990326,
|
| 1421 |
+
"learning_rate": 6.947735034665002e-05,
|
| 1422 |
+
"loss": 0.0255,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.2065217391304346,
|
| 1427 |
+
"grad_norm": 0.1830049455165863,
|
| 1428 |
+
"learning_rate": 6.917235524794558e-05,
|
| 1429 |
+
"loss": 0.0294,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.217391304347826,
|
| 1434 |
+
"grad_norm": 0.16847161948680878,
|
| 1435 |
+
"learning_rate": 6.886652148831279e-05,
|
| 1436 |
+
"loss": 0.0277,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.2282608695652173,
|
| 1441 |
+
"grad_norm": 0.17339234054088593,
|
| 1442 |
+
"learning_rate": 6.855986244591104e-05,
|
| 1443 |
+
"loss": 0.0236,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.239130434782609,
|
| 1448 |
+
"grad_norm": 0.19348445534706116,
|
| 1449 |
+
"learning_rate": 6.825239153500029e-05,
|
| 1450 |
+
"loss": 0.0216,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.25,
|
| 1455 |
+
"grad_norm": 0.2270950973033905,
|
| 1456 |
+
"learning_rate": 6.794412220535426e-05,
|
| 1457 |
+
"loss": 0.0206,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.260869565217391,
|
| 1462 |
+
"grad_norm": 0.20214591920375824,
|
| 1463 |
+
"learning_rate": 6.763506794167208e-05,
|
| 1464 |
+
"loss": 0.0218,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.2717391304347827,
|
| 1469 |
+
"grad_norm": 0.16403691470623016,
|
| 1470 |
+
"learning_rate": 6.732524226298841e-05,
|
| 1471 |
+
"loss": 0.02,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.282608695652174,
|
| 1476 |
+
"grad_norm": 0.17673853039741516,
|
| 1477 |
+
"learning_rate": 6.701465872208216e-05,
|
| 1478 |
+
"loss": 0.0207,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.2934782608695654,
|
| 1483 |
+
"grad_norm": 0.21534697711467743,
|
| 1484 |
+
"learning_rate": 6.670333090488356e-05,
|
| 1485 |
+
"loss": 0.0189,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.3043478260869565,
|
| 1490 |
+
"grad_norm": 0.165096253156662,
|
| 1491 |
+
"learning_rate": 6.639127242987988e-05,
|
| 1492 |
+
"loss": 0.0195,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.3152173913043477,
|
| 1497 |
+
"grad_norm": 0.27260059118270874,
|
| 1498 |
+
"learning_rate": 6.607849694751977e-05,
|
| 1499 |
+
"loss": 0.0231,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.3260869565217392,
|
| 1504 |
+
"grad_norm": 0.2327706515789032,
|
| 1505 |
+
"learning_rate": 6.576501813961609e-05,
|
| 1506 |
+
"loss": 0.0226,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.3369565217391304,
|
| 1511 |
+
"grad_norm": 0.17362096905708313,
|
| 1512 |
+
"learning_rate": 6.545084971874738e-05,
|
| 1513 |
+
"loss": 0.0264,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.3478260869565215,
|
| 1518 |
+
"grad_norm": 0.24459755420684814,
|
| 1519 |
+
"learning_rate": 6.513600542765817e-05,
|
| 1520 |
+
"loss": 0.023,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.358695652173913,
|
| 1525 |
+
"grad_norm": 0.20271766185760498,
|
| 1526 |
+
"learning_rate": 6.48204990386577e-05,
|
| 1527 |
+
"loss": 0.0208,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.369565217391304,
|
| 1532 |
+
"grad_norm": 0.2861473560333252,
|
| 1533 |
+
"learning_rate": 6.450434435301751e-05,
|
| 1534 |
+
"loss": 0.0237,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.380434782608696,
|
| 1539 |
+
"grad_norm": 0.2328135222196579,
|
| 1540 |
+
"learning_rate": 6.418755520036775e-05,
|
| 1541 |
+
"loss": 0.0219,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.391304347826087,
|
| 1546 |
+
"grad_norm": 0.2409750074148178,
|
| 1547 |
+
"learning_rate": 6.387014543809223e-05,
|
| 1548 |
+
"loss": 0.0222,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.4021739130434785,
|
| 1553 |
+
"grad_norm": 0.20612117648124695,
|
| 1554 |
+
"learning_rate": 6.355212895072223e-05,
|
| 1555 |
+
"loss": 0.0217,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 2.4130434782608696,
|
| 1560 |
+
"grad_norm": 0.2607957720756531,
|
| 1561 |
+
"learning_rate": 6.323351964932908e-05,
|
| 1562 |
+
"loss": 0.0197,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.4239130434782608,
|
| 1567 |
+
"grad_norm": 0.2704881727695465,
|
| 1568 |
+
"learning_rate": 6.291433147091583e-05,
|
| 1569 |
+
"loss": 0.0213,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.4347826086956523,
|
| 1574 |
+
"grad_norm": 0.22981029748916626,
|
| 1575 |
+
"learning_rate": 6.259457837780742e-05,
|
| 1576 |
+
"loss": 0.0205,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.4456521739130435,
|
| 1581 |
+
"grad_norm": 0.19447964429855347,
|
| 1582 |
+
"learning_rate": 6.227427435703997e-05,
|
| 1583 |
+
"loss": 0.0248,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.4565217391304346,
|
| 1588 |
+
"grad_norm": 0.31986603140830994,
|
| 1589 |
+
"learning_rate": 6.195343341974899e-05,
|
| 1590 |
+
"loss": 0.0246,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.467391304347826,
|
| 1595 |
+
"grad_norm": 0.20756466686725616,
|
| 1596 |
+
"learning_rate": 6.163206960055651e-05,
|
| 1597 |
+
"loss": 0.0207,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.4782608695652173,
|
| 1602 |
+
"grad_norm": 0.22251754999160767,
|
| 1603 |
+
"learning_rate": 6.131019695695702e-05,
|
| 1604 |
+
"loss": 0.0265,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.489130434782609,
|
| 1609 |
+
"grad_norm": 0.16655093431472778,
|
| 1610 |
+
"learning_rate": 6.0987829568702656e-05,
|
| 1611 |
+
"loss": 0.0207,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 2.5,
|
| 1616 |
+
"grad_norm": 0.2425738126039505,
|
| 1617 |
+
"learning_rate": 6.066498153718735e-05,
|
| 1618 |
+
"loss": 0.0176,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 2.5108695652173916,
|
| 1623 |
+
"grad_norm": 0.23594196140766144,
|
| 1624 |
+
"learning_rate": 6.034166698482984e-05,
|
| 1625 |
+
"loss": 0.0253,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.5217391304347827,
|
| 1630 |
+
"grad_norm": 0.17139174044132233,
|
| 1631 |
+
"learning_rate": 6.001790005445607e-05,
|
| 1632 |
+
"loss": 0.0191,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 2.532608695652174,
|
| 1637 |
+
"grad_norm": 0.17908968031406403,
|
| 1638 |
+
"learning_rate": 5.969369490868042e-05,
|
| 1639 |
+
"loss": 0.0259,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.5434782608695654,
|
| 1644 |
+
"grad_norm": 0.24141980707645416,
|
| 1645 |
+
"learning_rate": 5.9369065729286245e-05,
|
| 1646 |
+
"loss": 0.0246,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.5543478260869565,
|
| 1651 |
+
"grad_norm": 0.23516008257865906,
|
| 1652 |
+
"learning_rate": 5.90440267166055e-05,
|
| 1653 |
+
"loss": 0.0256,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.5652173913043477,
|
| 1658 |
+
"grad_norm": 0.2081535905599594,
|
| 1659 |
+
"learning_rate": 5.871859208889759e-05,
|
| 1660 |
+
"loss": 0.0203,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.5760869565217392,
|
| 1665 |
+
"grad_norm": 0.2254313826560974,
|
| 1666 |
+
"learning_rate": 5.8392776081727385e-05,
|
| 1667 |
+
"loss": 0.0216,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.5869565217391304,
|
| 1672 |
+
"grad_norm": 0.22026807069778442,
|
| 1673 |
+
"learning_rate": 5.8066592947342555e-05,
|
| 1674 |
+
"loss": 0.0188,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 2.5978260869565215,
|
| 1679 |
+
"grad_norm": 0.2628653943538666,
|
| 1680 |
+
"learning_rate": 5.7740056954050084e-05,
|
| 1681 |
+
"loss": 0.0224,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 2.608695652173913,
|
| 1686 |
+
"grad_norm": 0.22398746013641357,
|
| 1687 |
+
"learning_rate": 5.74131823855921e-05,
|
| 1688 |
+
"loss": 0.0238,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.619565217391304,
|
| 1693 |
+
"grad_norm": 0.20215076208114624,
|
| 1694 |
+
"learning_rate": 5.7085983540521216e-05,
|
| 1695 |
+
"loss": 0.0197,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.630434782608696,
|
| 1700 |
+
"grad_norm": 0.19902300834655762,
|
| 1701 |
+
"learning_rate": 5.675847473157485e-05,
|
| 1702 |
+
"loss": 0.021,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.641304347826087,
|
| 1707 |
+
"grad_norm": 0.21893462538719177,
|
| 1708 |
+
"learning_rate": 5.6430670285049314e-05,
|
| 1709 |
+
"loss": 0.0202,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.6521739130434785,
|
| 1714 |
+
"grad_norm": 0.21789760887622833,
|
| 1715 |
+
"learning_rate": 5.6102584540173006e-05,
|
| 1716 |
+
"loss": 0.0227,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.6630434782608696,
|
| 1721 |
+
"grad_norm": 0.12057076394557953,
|
| 1722 |
+
"learning_rate": 5.577423184847932e-05,
|
| 1723 |
+
"loss": 0.0199,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.6739130434782608,
|
| 1728 |
+
"grad_norm": 0.2071666419506073,
|
| 1729 |
+
"learning_rate": 5.544562657317863e-05,
|
| 1730 |
+
"loss": 0.0236,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.6847826086956523,
|
| 1735 |
+
"grad_norm": 0.2847704291343689,
|
| 1736 |
+
"learning_rate": 5.511678308853026e-05,
|
| 1737 |
+
"loss": 0.0186,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.6956521739130435,
|
| 1742 |
+
"grad_norm": 0.17881885170936584,
|
| 1743 |
+
"learning_rate": 5.478771577921351e-05,
|
| 1744 |
+
"loss": 0.0191,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.7065217391304346,
|
| 1749 |
+
"grad_norm": 0.19653011858463287,
|
| 1750 |
+
"learning_rate": 5.445843903969854e-05,
|
| 1751 |
+
"loss": 0.0137,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.717391304347826,
|
| 1756 |
+
"grad_norm": 0.2046557366847992,
|
| 1757 |
+
"learning_rate": 5.4128967273616625e-05,
|
| 1758 |
+
"loss": 0.0209,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 2.7282608695652173,
|
| 1763 |
+
"grad_norm": 0.21046030521392822,
|
| 1764 |
+
"learning_rate": 5.379931489313016e-05,
|
| 1765 |
+
"loss": 0.0207,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 2.7391304347826084,
|
| 1770 |
+
"grad_norm": 0.2215111255645752,
|
| 1771 |
+
"learning_rate": 5.3469496318302204e-05,
|
| 1772 |
+
"loss": 0.019,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 2.75,
|
| 1777 |
+
"grad_norm": 0.22360099852085114,
|
| 1778 |
+
"learning_rate": 5.313952597646568e-05,
|
| 1779 |
+
"loss": 0.0158,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.7608695652173916,
|
| 1784 |
+
"grad_norm": 0.1709163635969162,
|
| 1785 |
+
"learning_rate": 5.280941830159227e-05,
|
| 1786 |
+
"loss": 0.0214,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.7717391304347827,
|
| 1791 |
+
"grad_norm": 0.211487278342247,
|
| 1792 |
+
"learning_rate": 5.247918773366112e-05,
|
| 1793 |
+
"loss": 0.0242,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.782608695652174,
|
| 1798 |
+
"grad_norm": 0.3075908422470093,
|
| 1799 |
+
"learning_rate": 5.214884871802703e-05,
|
| 1800 |
+
"loss": 0.0213,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.7934782608695654,
|
| 1805 |
+
"grad_norm": 0.22945576906204224,
|
| 1806 |
+
"learning_rate": 5.1818415704788725e-05,
|
| 1807 |
+
"loss": 0.0187,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 2.8043478260869565,
|
| 1812 |
+
"grad_norm": 0.21798940002918243,
|
| 1813 |
+
"learning_rate": 5.148790314815663e-05,
|
| 1814 |
+
"loss": 0.0202,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.8152173913043477,
|
| 1819 |
+
"grad_norm": 0.14597228169441223,
|
| 1820 |
+
"learning_rate": 5.1157325505820694e-05,
|
| 1821 |
+
"loss": 0.0221,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.8260869565217392,
|
| 1826 |
+
"grad_norm": 0.24173279106616974,
|
| 1827 |
+
"learning_rate": 5.0826697238317935e-05,
|
| 1828 |
+
"loss": 0.0177,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 2.8369565217391304,
|
| 1833 |
+
"grad_norm": 0.16206835210323334,
|
| 1834 |
+
"learning_rate": 5.0496032808399815e-05,
|
| 1835 |
+
"loss": 0.0167,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 2.8478260869565215,
|
| 1840 |
+
"grad_norm": 0.20870648324489594,
|
| 1841 |
+
"learning_rate": 5.016534668039976e-05,
|
| 1842 |
+
"loss": 0.0208,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 2.858695652173913,
|
| 1847 |
+
"grad_norm": 0.13695970177650452,
|
| 1848 |
+
"learning_rate": 4.9834653319600246e-05,
|
| 1849 |
+
"loss": 0.0155,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.869565217391304,
|
| 1854 |
+
"grad_norm": 0.16413715481758118,
|
| 1855 |
+
"learning_rate": 4.950396719160018e-05,
|
| 1856 |
+
"loss": 0.0151,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.880434782608696,
|
| 1861 |
+
"grad_norm": 0.2725026607513428,
|
| 1862 |
+
"learning_rate": 4.917330276168208e-05,
|
| 1863 |
+
"loss": 0.0228,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.891304347826087,
|
| 1868 |
+
"grad_norm": 0.19408078491687775,
|
| 1869 |
+
"learning_rate": 4.884267449417931e-05,
|
| 1870 |
+
"loss": 0.0255,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 2.9021739130434785,
|
| 1875 |
+
"grad_norm": 0.15220940113067627,
|
| 1876 |
+
"learning_rate": 4.851209685184338e-05,
|
| 1877 |
+
"loss": 0.0191,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 2.9130434782608696,
|
| 1882 |
+
"grad_norm": 0.24963606894016266,
|
| 1883 |
+
"learning_rate": 4.818158429521129e-05,
|
| 1884 |
+
"loss": 0.0228,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 2.9239130434782608,
|
| 1889 |
+
"grad_norm": 0.2193748503923416,
|
| 1890 |
+
"learning_rate": 4.785115128197298e-05,
|
| 1891 |
+
"loss": 0.0184,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 2.9347826086956523,
|
| 1896 |
+
"grad_norm": 0.28289085626602173,
|
| 1897 |
+
"learning_rate": 4.7520812266338885e-05,
|
| 1898 |
+
"loss": 0.0225,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 2.9456521739130435,
|
| 1903 |
+
"grad_norm": 0.2755283713340759,
|
| 1904 |
+
"learning_rate": 4.7190581698407725e-05,
|
| 1905 |
+
"loss": 0.0198,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 2.9565217391304346,
|
| 1910 |
+
"grad_norm": 0.2590217888355255,
|
| 1911 |
+
"learning_rate": 4.6860474023534335e-05,
|
| 1912 |
+
"loss": 0.0197,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 2.967391304347826,
|
| 1917 |
+
"grad_norm": 0.2700153887271881,
|
| 1918 |
+
"learning_rate": 4.65305036816978e-05,
|
| 1919 |
+
"loss": 0.0198,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.9782608695652173,
|
| 1924 |
+
"grad_norm": 0.21997500956058502,
|
| 1925 |
+
"learning_rate": 4.620068510686985e-05,
|
| 1926 |
+
"loss": 0.02,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 2.9891304347826084,
|
| 1931 |
+
"grad_norm": 0.23885446786880493,
|
| 1932 |
+
"learning_rate": 4.5871032726383386e-05,
|
| 1933 |
+
"loss": 0.0166,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 3.0,
|
| 1938 |
+
"grad_norm": 0.26925128698349,
|
| 1939 |
+
"learning_rate": 4.554156096030149e-05,
|
| 1940 |
+
"loss": 0.0187,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 3.010869565217391,
|
| 1945 |
+
"grad_norm": 0.20031136274337769,
|
| 1946 |
+
"learning_rate": 4.5212284220786494e-05,
|
| 1947 |
+
"loss": 0.0169,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 3.0217391304347827,
|
| 1952 |
+
"grad_norm": 0.2370258867740631,
|
| 1953 |
+
"learning_rate": 4.488321691146975e-05,
|
| 1954 |
+
"loss": 0.0194,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 3.032608695652174,
|
| 1959 |
+
"grad_norm": 0.14988850057125092,
|
| 1960 |
+
"learning_rate": 4.4554373426821374e-05,
|
| 1961 |
+
"loss": 0.0149,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 3.0434782608695654,
|
| 1966 |
+
"grad_norm": 0.1604338139295578,
|
| 1967 |
+
"learning_rate": 4.4225768151520694e-05,
|
| 1968 |
+
"loss": 0.018,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 3.0543478260869565,
|
| 1973 |
+
"grad_norm": 0.1709444671869278,
|
| 1974 |
+
"learning_rate": 4.3897415459827e-05,
|
| 1975 |
+
"loss": 0.018,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 3.0652173913043477,
|
| 1980 |
+
"grad_norm": 0.1633748561143875,
|
| 1981 |
+
"learning_rate": 4.3569329714950704e-05,
|
| 1982 |
+
"loss": 0.0139,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 3.0760869565217392,
|
| 1987 |
+
"grad_norm": 0.18419773876667023,
|
| 1988 |
+
"learning_rate": 4.324152526842517e-05,
|
| 1989 |
+
"loss": 0.018,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 3.0869565217391304,
|
| 1994 |
+
"grad_norm": 0.1465953290462494,
|
| 1995 |
+
"learning_rate": 4.291401645947879e-05,
|
| 1996 |
+
"loss": 0.0195,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 3.097826086956522,
|
| 2001 |
+
"grad_norm": 0.21373240649700165,
|
| 2002 |
+
"learning_rate": 4.2586817614407895e-05,
|
| 2003 |
+
"loss": 0.0165,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 3.108695652173913,
|
| 2008 |
+
"grad_norm": 0.13149115443229675,
|
| 2009 |
+
"learning_rate": 4.2259943045949934e-05,
|
| 2010 |
+
"loss": 0.0191,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 3.119565217391304,
|
| 2015 |
+
"grad_norm": 0.22037185728549957,
|
| 2016 |
+
"learning_rate": 4.1933407052657456e-05,
|
| 2017 |
+
"loss": 0.015,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 3.130434782608696,
|
| 2022 |
+
"grad_norm": 0.17351217567920685,
|
| 2023 |
+
"learning_rate": 4.160722391827262e-05,
|
| 2024 |
+
"loss": 0.0153,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 3.141304347826087,
|
| 2029 |
+
"grad_norm": 0.1752108484506607,
|
| 2030 |
+
"learning_rate": 4.1281407911102425e-05,
|
| 2031 |
+
"loss": 0.0162,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 3.1521739130434785,
|
| 2036 |
+
"grad_norm": 0.11886758357286453,
|
| 2037 |
+
"learning_rate": 4.095597328339452e-05,
|
| 2038 |
+
"loss": 0.0154,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 3.1630434782608696,
|
| 2043 |
+
"grad_norm": 0.22312021255493164,
|
| 2044 |
+
"learning_rate": 4.063093427071376e-05,
|
| 2045 |
+
"loss": 0.0249,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 3.1739130434782608,
|
| 2050 |
+
"grad_norm": 0.18036895990371704,
|
| 2051 |
+
"learning_rate": 4.0306305091319595e-05,
|
| 2052 |
+
"loss": 0.0152,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 3.1847826086956523,
|
| 2057 |
+
"grad_norm": 0.13070718944072723,
|
| 2058 |
+
"learning_rate": 3.9982099945543945e-05,
|
| 2059 |
+
"loss": 0.0152,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 3.1956521739130435,
|
| 2064 |
+
"grad_norm": 0.1445332020521164,
|
| 2065 |
+
"learning_rate": 3.965833301517017e-05,
|
| 2066 |
+
"loss": 0.0154,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 3.2065217391304346,
|
| 2071 |
+
"grad_norm": 0.14855942130088806,
|
| 2072 |
+
"learning_rate": 3.933501846281267e-05,
|
| 2073 |
+
"loss": 0.0146,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 3.217391304347826,
|
| 2078 |
+
"grad_norm": 0.13377995789051056,
|
| 2079 |
+
"learning_rate": 3.901217043129735e-05,
|
| 2080 |
+
"loss": 0.0213,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 3.2282608695652173,
|
| 2085 |
+
"grad_norm": 0.1453462839126587,
|
| 2086 |
+
"learning_rate": 3.8689803043043e-05,
|
| 2087 |
+
"loss": 0.0173,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 3.239130434782609,
|
| 2092 |
+
"grad_norm": 0.12768065929412842,
|
| 2093 |
+
"learning_rate": 3.836793039944349e-05,
|
| 2094 |
+
"loss": 0.0145,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 3.25,
|
| 2099 |
+
"grad_norm": 0.176410511136055,
|
| 2100 |
+
"learning_rate": 3.8046566580251e-05,
|
| 2101 |
+
"loss": 0.0129,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 3.260869565217391,
|
| 2106 |
+
"grad_norm": 0.21856428682804108,
|
| 2107 |
+
"learning_rate": 3.772572564296005e-05,
|
| 2108 |
+
"loss": 0.0169,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 3.2717391304347827,
|
| 2113 |
+
"grad_norm": 0.16268354654312134,
|
| 2114 |
+
"learning_rate": 3.74054216221926e-05,
|
| 2115 |
+
"loss": 0.0146,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.282608695652174,
|
| 2120 |
+
"grad_norm": 0.17902961373329163,
|
| 2121 |
+
"learning_rate": 3.7085668529084184e-05,
|
| 2122 |
+
"loss": 0.0189,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.2934782608695654,
|
| 2127 |
+
"grad_norm": 0.2093406766653061,
|
| 2128 |
+
"learning_rate": 3.676648035067093e-05,
|
| 2129 |
+
"loss": 0.0159,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.3043478260869565,
|
| 2134 |
+
"grad_norm": 0.18729008734226227,
|
| 2135 |
+
"learning_rate": 3.6447871049277796e-05,
|
| 2136 |
+
"loss": 0.0133,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.3152173913043477,
|
| 2141 |
+
"grad_norm": 0.21578620374202728,
|
| 2142 |
+
"learning_rate": 3.612985456190778e-05,
|
| 2143 |
+
"loss": 0.0185,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.3260869565217392,
|
| 2148 |
+
"grad_norm": 0.1456160843372345,
|
| 2149 |
+
"learning_rate": 3.581244479963225e-05,
|
| 2150 |
+
"loss": 0.0179,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.3369565217391304,
|
| 2155 |
+
"grad_norm": 0.15574467182159424,
|
| 2156 |
+
"learning_rate": 3.5495655646982505e-05,
|
| 2157 |
+
"loss": 0.0191,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 3.3478260869565215,
|
| 2162 |
+
"grad_norm": 0.21840086579322815,
|
| 2163 |
+
"learning_rate": 3.517950096134232e-05,
|
| 2164 |
+
"loss": 0.0167,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 3.358695652173913,
|
| 2169 |
+
"grad_norm": 0.1252320110797882,
|
| 2170 |
+
"learning_rate": 3.4863994572341843e-05,
|
| 2171 |
+
"loss": 0.0156,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 3.369565217391304,
|
| 2176 |
+
"grad_norm": 0.1790045201778412,
|
| 2177 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 2178 |
+
"loss": 0.0153,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 3.380434782608696,
|
| 2183 |
+
"grad_norm": 0.21787020564079285,
|
| 2184 |
+
"learning_rate": 3.423498186038393e-05,
|
| 2185 |
+
"loss": 0.0203,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 3.391304347826087,
|
| 2190 |
+
"grad_norm": 0.17932236194610596,
|
| 2191 |
+
"learning_rate": 3.392150305248024e-05,
|
| 2192 |
+
"loss": 0.0145,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 3.4021739130434785,
|
| 2197 |
+
"grad_norm": 0.1460498571395874,
|
| 2198 |
+
"learning_rate": 3.360872757012011e-05,
|
| 2199 |
+
"loss": 0.0168,
|
| 2200 |
+
"step": 3130
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 3.4130434782608696,
|
| 2204 |
+
"grad_norm": 0.20171473920345306,
|
| 2205 |
+
"learning_rate": 3.329666909511645e-05,
|
| 2206 |
+
"loss": 0.0188,
|
| 2207 |
+
"step": 3140
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 3.4239130434782608,
|
| 2211 |
+
"grad_norm": 0.1880096197128296,
|
| 2212 |
+
"learning_rate": 3.298534127791785e-05,
|
| 2213 |
+
"loss": 0.0162,
|
| 2214 |
+
"step": 3150
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 3.4347826086956523,
|
| 2218 |
+
"grad_norm": 0.21033500134944916,
|
| 2219 |
+
"learning_rate": 3.267475773701161e-05,
|
| 2220 |
+
"loss": 0.0152,
|
| 2221 |
+
"step": 3160
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 3.4456521739130435,
|
| 2225 |
+
"grad_norm": 0.18287412822246552,
|
| 2226 |
+
"learning_rate": 3.236493205832795e-05,
|
| 2227 |
+
"loss": 0.0183,
|
| 2228 |
+
"step": 3170
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 3.4565217391304346,
|
| 2232 |
+
"grad_norm": 0.1669587939977646,
|
| 2233 |
+
"learning_rate": 3.205587779464576e-05,
|
| 2234 |
+
"loss": 0.0145,
|
| 2235 |
+
"step": 3180
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 3.467391304347826,
|
| 2239 |
+
"grad_norm": 0.2002091407775879,
|
| 2240 |
+
"learning_rate": 3.1747608464999725e-05,
|
| 2241 |
+
"loss": 0.0152,
|
| 2242 |
+
"step": 3190
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 3.4782608695652173,
|
| 2246 |
+
"grad_norm": 0.20512893795967102,
|
| 2247 |
+
"learning_rate": 3.144013755408895e-05,
|
| 2248 |
+
"loss": 0.0209,
|
| 2249 |
+
"step": 3200
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 3.489130434782609,
|
| 2253 |
+
"grad_norm": 0.164790078997612,
|
| 2254 |
+
"learning_rate": 3.113347851168721e-05,
|
| 2255 |
+
"loss": 0.0179,
|
| 2256 |
+
"step": 3210
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 3.5,
|
| 2260 |
+
"grad_norm": 0.1478477120399475,
|
| 2261 |
+
"learning_rate": 3.082764475205442e-05,
|
| 2262 |
+
"loss": 0.0143,
|
| 2263 |
+
"step": 3220
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 3.5108695652173916,
|
| 2267 |
+
"grad_norm": 0.1484198421239853,
|
| 2268 |
+
"learning_rate": 3.052264965335e-05,
|
| 2269 |
+
"loss": 0.0151,
|
| 2270 |
+
"step": 3230
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 3.5217391304347827,
|
| 2274 |
+
"grad_norm": 0.1396767646074295,
|
| 2275 |
+
"learning_rate": 3.0218506557047598e-05,
|
| 2276 |
+
"loss": 0.012,
|
| 2277 |
+
"step": 3240
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 3.532608695652174,
|
| 2281 |
+
"grad_norm": 0.12337210774421692,
|
| 2282 |
+
"learning_rate": 2.991522876735154e-05,
|
| 2283 |
+
"loss": 0.0118,
|
| 2284 |
+
"step": 3250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 3.5434782608695654,
|
| 2288 |
+
"grad_norm": 0.15380887687206268,
|
| 2289 |
+
"learning_rate": 2.9612829550614836e-05,
|
| 2290 |
+
"loss": 0.0217,
|
| 2291 |
+
"step": 3260
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 3.5543478260869565,
|
| 2295 |
+
"grad_norm": 0.13729456067085266,
|
| 2296 |
+
"learning_rate": 2.931132213475884e-05,
|
| 2297 |
+
"loss": 0.0151,
|
| 2298 |
+
"step": 3270
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 3.5652173913043477,
|
| 2302 |
+
"grad_norm": 0.12622790038585663,
|
| 2303 |
+
"learning_rate": 2.9010719708694722e-05,
|
| 2304 |
+
"loss": 0.0127,
|
| 2305 |
+
"step": 3280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 3.5760869565217392,
|
| 2309 |
+
"grad_norm": 0.17325228452682495,
|
| 2310 |
+
"learning_rate": 2.8711035421746367e-05,
|
| 2311 |
+
"loss": 0.0158,
|
| 2312 |
+
"step": 3290
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 3.5869565217391304,
|
| 2316 |
+
"grad_norm": 0.13225744664669037,
|
| 2317 |
+
"learning_rate": 2.8412282383075363e-05,
|
| 2318 |
+
"loss": 0.0125,
|
| 2319 |
+
"step": 3300
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 3.5978260869565215,
|
| 2323 |
+
"grad_norm": 0.17985399067401886,
|
| 2324 |
+
"learning_rate": 2.811447366110741e-05,
|
| 2325 |
+
"loss": 0.0137,
|
| 2326 |
+
"step": 3310
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 3.608695652173913,
|
| 2330 |
+
"grad_norm": 0.09231913089752197,
|
| 2331 |
+
"learning_rate": 2.7817622282960815e-05,
|
| 2332 |
+
"loss": 0.0127,
|
| 2333 |
+
"step": 3320
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 3.619565217391304,
|
| 2337 |
+
"grad_norm": 0.17219118773937225,
|
| 2338 |
+
"learning_rate": 2.7521741233876496e-05,
|
| 2339 |
+
"loss": 0.014,
|
| 2340 |
+
"step": 3330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 3.630434782608696,
|
| 2344 |
+
"grad_norm": 0.2218349128961563,
|
| 2345 |
+
"learning_rate": 2.7226843456650037e-05,
|
| 2346 |
+
"loss": 0.0141,
|
| 2347 |
+
"step": 3340
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 3.641304347826087,
|
| 2351 |
+
"grad_norm": 0.2514891028404236,
|
| 2352 |
+
"learning_rate": 2.693294185106562e-05,
|
| 2353 |
+
"loss": 0.0181,
|
| 2354 |
+
"step": 3350
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 3.6521739130434785,
|
| 2358 |
+
"grad_norm": 0.1861620843410492,
|
| 2359 |
+
"learning_rate": 2.6640049273331515e-05,
|
| 2360 |
+
"loss": 0.0135,
|
| 2361 |
+
"step": 3360
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 3.6630434782608696,
|
| 2365 |
+
"grad_norm": 0.11425938457250595,
|
| 2366 |
+
"learning_rate": 2.6348178535517966e-05,
|
| 2367 |
+
"loss": 0.0193,
|
| 2368 |
+
"step": 3370
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 3.6739130434782608,
|
| 2372 |
+
"grad_norm": 0.18965540826320648,
|
| 2373 |
+
"learning_rate": 2.6057342404996522e-05,
|
| 2374 |
+
"loss": 0.0187,
|
| 2375 |
+
"step": 3380
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 3.6847826086956523,
|
| 2379 |
+
"grad_norm": 0.19534063339233398,
|
| 2380 |
+
"learning_rate": 2.5767553603881767e-05,
|
| 2381 |
+
"loss": 0.0158,
|
| 2382 |
+
"step": 3390
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 3.6956521739130435,
|
| 2386 |
+
"grad_norm": 0.17224030196666718,
|
| 2387 |
+
"learning_rate": 2.547882480847461e-05,
|
| 2388 |
+
"loss": 0.0182,
|
| 2389 |
+
"step": 3400
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 3.7065217391304346,
|
| 2393 |
+
"grad_norm": 0.13765761256217957,
|
| 2394 |
+
"learning_rate": 2.5191168648707887e-05,
|
| 2395 |
+
"loss": 0.0144,
|
| 2396 |
+
"step": 3410
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 3.717391304347826,
|
| 2400 |
+
"grad_norm": 0.20135529339313507,
|
| 2401 |
+
"learning_rate": 2.490459770759398e-05,
|
| 2402 |
+
"loss": 0.0161,
|
| 2403 |
+
"step": 3420
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 3.7282608695652173,
|
| 2407 |
+
"grad_norm": 0.14608322083950043,
|
| 2408 |
+
"learning_rate": 2.4619124520674146e-05,
|
| 2409 |
+
"loss": 0.0143,
|
| 2410 |
+
"step": 3430
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 3.7391304347826084,
|
| 2414 |
+
"grad_norm": 0.2197912484407425,
|
| 2415 |
+
"learning_rate": 2.433476157547044e-05,
|
| 2416 |
+
"loss": 0.0155,
|
| 2417 |
+
"step": 3440
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 3.75,
|
| 2421 |
+
"grad_norm": 0.1401628851890564,
|
| 2422 |
+
"learning_rate": 2.405152131093926e-05,
|
| 2423 |
+
"loss": 0.014,
|
| 2424 |
+
"step": 3450
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 3.7608695652173916,
|
| 2428 |
+
"grad_norm": 0.14256739616394043,
|
| 2429 |
+
"learning_rate": 2.3769416116927335e-05,
|
| 2430 |
+
"loss": 0.0178,
|
| 2431 |
+
"step": 3460
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 3.7717391304347827,
|
| 2435 |
+
"grad_norm": 0.15367449820041656,
|
| 2436 |
+
"learning_rate": 2.3488458333629777e-05,
|
| 2437 |
+
"loss": 0.0131,
|
| 2438 |
+
"step": 3470
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 3.782608695652174,
|
| 2442 |
+
"grad_norm": 0.15327581763267517,
|
| 2443 |
+
"learning_rate": 2.3208660251050158e-05,
|
| 2444 |
+
"loss": 0.015,
|
| 2445 |
+
"step": 3480
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 3.7934782608695654,
|
| 2449 |
+
"grad_norm": 0.11331693828105927,
|
| 2450 |
+
"learning_rate": 2.29300341084631e-05,
|
| 2451 |
+
"loss": 0.0139,
|
| 2452 |
+
"step": 3490
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 3.8043478260869565,
|
| 2456 |
+
"grad_norm": 0.15740583837032318,
|
| 2457 |
+
"learning_rate": 2.2652592093878666e-05,
|
| 2458 |
+
"loss": 0.0201,
|
| 2459 |
+
"step": 3500
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 3.8152173913043477,
|
| 2463 |
+
"grad_norm": 0.1463966816663742,
|
| 2464 |
+
"learning_rate": 2.237634634350934e-05,
|
| 2465 |
+
"loss": 0.0154,
|
| 2466 |
+
"step": 3510
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 3.8260869565217392,
|
| 2470 |
+
"grad_norm": 0.12818191945552826,
|
| 2471 |
+
"learning_rate": 2.2101308941239203e-05,
|
| 2472 |
+
"loss": 0.0127,
|
| 2473 |
+
"step": 3520
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 3.8369565217391304,
|
| 2477 |
+
"grad_norm": 0.15985611081123352,
|
| 2478 |
+
"learning_rate": 2.182749191809518e-05,
|
| 2479 |
+
"loss": 0.0134,
|
| 2480 |
+
"step": 3530
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 3.8478260869565215,
|
| 2484 |
+
"grad_norm": 0.2131720781326294,
|
| 2485 |
+
"learning_rate": 2.1554907251720945e-05,
|
| 2486 |
+
"loss": 0.0171,
|
| 2487 |
+
"step": 3540
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 3.858695652173913,
|
| 2491 |
+
"grad_norm": 0.10271260142326355,
|
| 2492 |
+
"learning_rate": 2.128356686585282e-05,
|
| 2493 |
+
"loss": 0.0143,
|
| 2494 |
+
"step": 3550
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 3.869565217391304,
|
| 2498 |
+
"grad_norm": 0.12285394221544266,
|
| 2499 |
+
"learning_rate": 2.1013482629798333e-05,
|
| 2500 |
+
"loss": 0.0135,
|
| 2501 |
+
"step": 3560
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 3.880434782608696,
|
| 2505 |
+
"grad_norm": 0.18301796913146973,
|
| 2506 |
+
"learning_rate": 2.0744666357916925e-05,
|
| 2507 |
+
"loss": 0.017,
|
| 2508 |
+
"step": 3570
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 3.891304347826087,
|
| 2512 |
+
"grad_norm": 0.20998628437519073,
|
| 2513 |
+
"learning_rate": 2.0477129809103147e-05,
|
| 2514 |
+
"loss": 0.0171,
|
| 2515 |
+
"step": 3580
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 3.9021739130434785,
|
| 2519 |
+
"grad_norm": 0.15842413902282715,
|
| 2520 |
+
"learning_rate": 2.0210884686272368e-05,
|
| 2521 |
+
"loss": 0.0134,
|
| 2522 |
+
"step": 3590
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 3.9130434782608696,
|
| 2526 |
+
"grad_norm": 0.12548497319221497,
|
| 2527 |
+
"learning_rate": 1.9945942635848748e-05,
|
| 2528 |
+
"loss": 0.0149,
|
| 2529 |
+
"step": 3600
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 3.9239130434782608,
|
| 2533 |
+
"grad_norm": 0.1245172843337059,
|
| 2534 |
+
"learning_rate": 1.9682315247255894e-05,
|
| 2535 |
+
"loss": 0.012,
|
| 2536 |
+
"step": 3610
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 3.9347826086956523,
|
| 2540 |
+
"grad_norm": 0.14383450150489807,
|
| 2541 |
+
"learning_rate": 1.942001405240979e-05,
|
| 2542 |
+
"loss": 0.0146,
|
| 2543 |
+
"step": 3620
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 3.9456521739130435,
|
| 2547 |
+
"grad_norm": 0.11160749197006226,
|
| 2548 |
+
"learning_rate": 1.9159050525214452e-05,
|
| 2549 |
+
"loss": 0.0143,
|
| 2550 |
+
"step": 3630
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 3.9565217391304346,
|
| 2554 |
+
"grad_norm": 0.12985584139823914,
|
| 2555 |
+
"learning_rate": 1.8899436081059975e-05,
|
| 2556 |
+
"loss": 0.0144,
|
| 2557 |
+
"step": 3640
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 3.967391304347826,
|
| 2561 |
+
"grad_norm": 0.2041911780834198,
|
| 2562 |
+
"learning_rate": 1.8641182076323148e-05,
|
| 2563 |
+
"loss": 0.0163,
|
| 2564 |
+
"step": 3650
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 3.9782608695652173,
|
| 2568 |
+
"grad_norm": 0.11336560547351837,
|
| 2569 |
+
"learning_rate": 1.838429980787081e-05,
|
| 2570 |
+
"loss": 0.011,
|
| 2571 |
+
"step": 3660
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 3.9891304347826084,
|
| 2575 |
+
"grad_norm": 0.13748924434185028,
|
| 2576 |
+
"learning_rate": 1.8128800512565513e-05,
|
| 2577 |
+
"loss": 0.0144,
|
| 2578 |
+
"step": 3670
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 4.0,
|
| 2582 |
+
"grad_norm": 0.24345290660858154,
|
| 2583 |
+
"learning_rate": 1.787469536677419e-05,
|
| 2584 |
+
"loss": 0.0155,
|
| 2585 |
+
"step": 3680
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 4.010869565217392,
|
| 2589 |
+
"grad_norm": 0.21563570201396942,
|
| 2590 |
+
"learning_rate": 1.7621995485879062e-05,
|
| 2591 |
+
"loss": 0.0155,
|
| 2592 |
+
"step": 3690
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 4.021739130434782,
|
| 2596 |
+
"grad_norm": 0.21253818273544312,
|
| 2597 |
+
"learning_rate": 1.7370711923791567e-05,
|
| 2598 |
+
"loss": 0.0116,
|
| 2599 |
+
"step": 3700
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 4.032608695652174,
|
| 2603 |
+
"grad_norm": 0.1393989771604538,
|
| 2604 |
+
"learning_rate": 1.712085567246878e-05,
|
| 2605 |
+
"loss": 0.0183,
|
| 2606 |
+
"step": 3710
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 4.043478260869565,
|
| 2610 |
+
"grad_norm": 0.11780686676502228,
|
| 2611 |
+
"learning_rate": 1.6872437661432517e-05,
|
| 2612 |
+
"loss": 0.0136,
|
| 2613 |
+
"step": 3720
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 4.054347826086956,
|
| 2617 |
+
"grad_norm": 0.12765192985534668,
|
| 2618 |
+
"learning_rate": 1.662546875729138e-05,
|
| 2619 |
+
"loss": 0.0118,
|
| 2620 |
+
"step": 3730
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 4.065217391304348,
|
| 2624 |
+
"grad_norm": 0.1177617758512497,
|
| 2625 |
+
"learning_rate": 1.637995976326527e-05,
|
| 2626 |
+
"loss": 0.0153,
|
| 2627 |
+
"step": 3740
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 4.076086956521739,
|
| 2631 |
+
"grad_norm": 0.16909116506576538,
|
| 2632 |
+
"learning_rate": 1.6135921418712956e-05,
|
| 2633 |
+
"loss": 0.0143,
|
| 2634 |
+
"step": 3750
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 4.086956521739131,
|
| 2638 |
+
"grad_norm": 0.21315212547779083,
|
| 2639 |
+
"learning_rate": 1.5893364398662176e-05,
|
| 2640 |
+
"loss": 0.0135,
|
| 2641 |
+
"step": 3760
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 4.0978260869565215,
|
| 2645 |
+
"grad_norm": 0.190399169921875,
|
| 2646 |
+
"learning_rate": 1.5652299313342773e-05,
|
| 2647 |
+
"loss": 0.0172,
|
| 2648 |
+
"step": 3770
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 4.108695652173913,
|
| 2652 |
+
"grad_norm": 0.12744581699371338,
|
| 2653 |
+
"learning_rate": 1.5412736707722537e-05,
|
| 2654 |
+
"loss": 0.0126,
|
| 2655 |
+
"step": 3780
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 4.119565217391305,
|
| 2659 |
+
"grad_norm": 0.09308245778083801,
|
| 2660 |
+
"learning_rate": 1.517468706104589e-05,
|
| 2661 |
+
"loss": 0.01,
|
| 2662 |
+
"step": 3790
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 4.130434782608695,
|
| 2666 |
+
"grad_norm": 0.15305502712726593,
|
| 2667 |
+
"learning_rate": 1.4938160786375572e-05,
|
| 2668 |
+
"loss": 0.0147,
|
| 2669 |
+
"step": 3800
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 4.141304347826087,
|
| 2673 |
+
"grad_norm": 0.10666476935148239,
|
| 2674 |
+
"learning_rate": 1.470316823013707e-05,
|
| 2675 |
+
"loss": 0.0117,
|
| 2676 |
+
"step": 3810
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 4.1521739130434785,
|
| 2680 |
+
"grad_norm": 0.1367276906967163,
|
| 2681 |
+
"learning_rate": 1.4469719671666043e-05,
|
| 2682 |
+
"loss": 0.0172,
|
| 2683 |
+
"step": 3820
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 4.163043478260869,
|
| 2687 |
+
"grad_norm": 0.08581943809986115,
|
| 2688 |
+
"learning_rate": 1.4237825322758736e-05,
|
| 2689 |
+
"loss": 0.0152,
|
| 2690 |
+
"step": 3830
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 4.173913043478261,
|
| 2694 |
+
"grad_norm": 0.15358705818653107,
|
| 2695 |
+
"learning_rate": 1.4007495327225162e-05,
|
| 2696 |
+
"loss": 0.0122,
|
| 2697 |
+
"step": 3840
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 4.184782608695652,
|
| 2701 |
+
"grad_norm": 0.126980260014534,
|
| 2702 |
+
"learning_rate": 1.3778739760445552e-05,
|
| 2703 |
+
"loss": 0.0124,
|
| 2704 |
+
"step": 3850
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 4.195652173913044,
|
| 2708 |
+
"grad_norm": 0.1939040869474411,
|
| 2709 |
+
"learning_rate": 1.3551568628929434e-05,
|
| 2710 |
+
"loss": 0.0153,
|
| 2711 |
+
"step": 3860
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 4.206521739130435,
|
| 2715 |
+
"grad_norm": 0.18035009503364563,
|
| 2716 |
+
"learning_rate": 1.3325991869878013e-05,
|
| 2717 |
+
"loss": 0.013,
|
| 2718 |
+
"step": 3870
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 4.217391304347826,
|
| 2722 |
+
"grad_norm": 0.07998842000961304,
|
| 2723 |
+
"learning_rate": 1.3102019350749528e-05,
|
| 2724 |
+
"loss": 0.0139,
|
| 2725 |
+
"step": 3880
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 4.228260869565218,
|
| 2729 |
+
"grad_norm": 0.18314486742019653,
|
| 2730 |
+
"learning_rate": 1.2879660868827508e-05,
|
| 2731 |
+
"loss": 0.0114,
|
| 2732 |
+
"step": 3890
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 4.239130434782608,
|
| 2736 |
+
"grad_norm": 0.09441019594669342,
|
| 2737 |
+
"learning_rate": 1.2658926150792322e-05,
|
| 2738 |
+
"loss": 0.0132,
|
| 2739 |
+
"step": 3900
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 4.25,
|
| 2743 |
+
"grad_norm": 0.12457236647605896,
|
| 2744 |
+
"learning_rate": 1.243982485229559e-05,
|
| 2745 |
+
"loss": 0.0122,
|
| 2746 |
+
"step": 3910
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 4.260869565217392,
|
| 2750 |
+
"grad_norm": 0.1543866991996765,
|
| 2751 |
+
"learning_rate": 1.2222366557537911e-05,
|
| 2752 |
+
"loss": 0.0121,
|
| 2753 |
+
"step": 3920
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 4.271739130434782,
|
| 2757 |
+
"grad_norm": 0.11423374712467194,
|
| 2758 |
+
"learning_rate": 1.2006560778849578e-05,
|
| 2759 |
+
"loss": 0.013,
|
| 2760 |
+
"step": 3930
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 4.282608695652174,
|
| 2764 |
+
"grad_norm": 0.10043908655643463,
|
| 2765 |
+
"learning_rate": 1.1792416956274444e-05,
|
| 2766 |
+
"loss": 0.0141,
|
| 2767 |
+
"step": 3940
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 4.293478260869565,
|
| 2771 |
+
"grad_norm": 0.20762887597084045,
|
| 2772 |
+
"learning_rate": 1.157994445715706e-05,
|
| 2773 |
+
"loss": 0.0164,
|
| 2774 |
+
"step": 3950
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 4.304347826086957,
|
| 2778 |
+
"grad_norm": 0.1447887122631073,
|
| 2779 |
+
"learning_rate": 1.1369152575732822e-05,
|
| 2780 |
+
"loss": 0.0116,
|
| 2781 |
+
"step": 3960
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 4.315217391304348,
|
| 2785 |
+
"grad_norm": 0.20277662575244904,
|
| 2786 |
+
"learning_rate": 1.1160050532721528e-05,
|
| 2787 |
+
"loss": 0.0133,
|
| 2788 |
+
"step": 3970
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 4.326086956521739,
|
| 2792 |
+
"grad_norm": 0.18211638927459717,
|
| 2793 |
+
"learning_rate": 1.095264747492391e-05,
|
| 2794 |
+
"loss": 0.0111,
|
| 2795 |
+
"step": 3980
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 4.336956521739131,
|
| 2799 |
+
"grad_norm": 0.13810472190380096,
|
| 2800 |
+
"learning_rate": 1.0746952474821614e-05,
|
| 2801 |
+
"loss": 0.0118,
|
| 2802 |
+
"step": 3990
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 4.3478260869565215,
|
| 2806 |
+
"grad_norm": 0.14950840175151825,
|
| 2807 |
+
"learning_rate": 1.0542974530180327e-05,
|
| 2808 |
+
"loss": 0.0123,
|
| 2809 |
+
"step": 4000
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 4.358695652173913,
|
| 2813 |
+
"grad_norm": 0.10527154058218002,
|
| 2814 |
+
"learning_rate": 1.0340722563656107e-05,
|
| 2815 |
+
"loss": 0.0114,
|
| 2816 |
+
"step": 4010
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 4.369565217391305,
|
| 2820 |
+
"grad_norm": 0.1756809651851654,
|
| 2821 |
+
"learning_rate": 1.0140205422405214e-05,
|
| 2822 |
+
"loss": 0.0116,
|
| 2823 |
+
"step": 4020
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 4.380434782608695,
|
| 2827 |
+
"grad_norm": 0.11897595226764679,
|
| 2828 |
+
"learning_rate": 9.941431877696955e-06,
|
| 2829 |
+
"loss": 0.0122,
|
| 2830 |
+
"step": 4030
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 4.391304347826087,
|
| 2834 |
+
"grad_norm": 0.13338477909564972,
|
| 2835 |
+
"learning_rate": 9.744410624530148e-06,
|
| 2836 |
+
"loss": 0.0152,
|
| 2837 |
+
"step": 4040
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 4.4021739130434785,
|
| 2841 |
+
"grad_norm": 0.16387279331684113,
|
| 2842 |
+
"learning_rate": 9.549150281252633e-06,
|
| 2843 |
+
"loss": 0.0098,
|
| 2844 |
+
"step": 4050
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 4.413043478260869,
|
| 2848 |
+
"grad_norm": 0.18097949028015137,
|
| 2849 |
+
"learning_rate": 9.355659389184396e-06,
|
| 2850 |
+
"loss": 0.0139,
|
| 2851 |
+
"step": 4060
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 4.423913043478261,
|
| 2855 |
+
"grad_norm": 0.10248986631631851,
|
| 2856 |
+
"learning_rate": 9.163946412243896e-06,
|
| 2857 |
+
"loss": 0.0137,
|
| 2858 |
+
"step": 4070
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 4.434782608695652,
|
| 2862 |
+
"grad_norm": 0.09879454970359802,
|
| 2863 |
+
"learning_rate": 8.974019736577777e-06,
|
| 2864 |
+
"loss": 0.0108,
|
| 2865 |
+
"step": 4080
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 4.445652173913043,
|
| 2869 |
+
"grad_norm": 0.14235499501228333,
|
| 2870 |
+
"learning_rate": 8.785887670194138e-06,
|
| 2871 |
+
"loss": 0.0109,
|
| 2872 |
+
"step": 4090
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 4.456521739130435,
|
| 2876 |
+
"grad_norm": 0.12883390486240387,
|
| 2877 |
+
"learning_rate": 8.599558442598998e-06,
|
| 2878 |
+
"loss": 0.0142,
|
| 2879 |
+
"step": 4100
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 4.467391304347826,
|
| 2883 |
+
"grad_norm": 0.13557647168636322,
|
| 2884 |
+
"learning_rate": 8.415040204436426e-06,
|
| 2885 |
+
"loss": 0.0131,
|
| 2886 |
+
"step": 4110
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 4.478260869565218,
|
| 2890 |
+
"grad_norm": 0.2233034372329712,
|
| 2891 |
+
"learning_rate": 8.232341027131885e-06,
|
| 2892 |
+
"loss": 0.014,
|
| 2893 |
+
"step": 4120
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 4.489130434782608,
|
| 2897 |
+
"grad_norm": 0.11671403050422668,
|
| 2898 |
+
"learning_rate": 8.051468902539272e-06,
|
| 2899 |
+
"loss": 0.0116,
|
| 2900 |
+
"step": 4130
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 4.5,
|
| 2904 |
+
"grad_norm": 0.16856342554092407,
|
| 2905 |
+
"learning_rate": 7.872431742591268e-06,
|
| 2906 |
+
"loss": 0.0154,
|
| 2907 |
+
"step": 4140
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 4.510869565217392,
|
| 2911 |
+
"grad_norm": 0.2033834606409073,
|
| 2912 |
+
"learning_rate": 7.695237378953223e-06,
|
| 2913 |
+
"loss": 0.0131,
|
| 2914 |
+
"step": 4150
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 4.521739130434782,
|
| 2918 |
+
"grad_norm": 0.1596093475818634,
|
| 2919 |
+
"learning_rate": 7.519893562680663e-06,
|
| 2920 |
+
"loss": 0.0087,
|
| 2921 |
+
"step": 4160
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 4.532608695652174,
|
| 2925 |
+
"grad_norm": 0.0803675428032875,
|
| 2926 |
+
"learning_rate": 7.3464079638801365e-06,
|
| 2927 |
+
"loss": 0.0153,
|
| 2928 |
+
"step": 4170
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 4.543478260869565,
|
| 2932 |
+
"grad_norm": 0.17898015677928925,
|
| 2933 |
+
"learning_rate": 7.174788171373731e-06,
|
| 2934 |
+
"loss": 0.0145,
|
| 2935 |
+
"step": 4180
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 4.554347826086957,
|
| 2939 |
+
"grad_norm": 0.11737199872732162,
|
| 2940 |
+
"learning_rate": 7.005041692367154e-06,
|
| 2941 |
+
"loss": 0.0146,
|
| 2942 |
+
"step": 4190
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 4.565217391304348,
|
| 2946 |
+
"grad_norm": 0.10241485387086868,
|
| 2947 |
+
"learning_rate": 6.837175952121306e-06,
|
| 2948 |
+
"loss": 0.0113,
|
| 2949 |
+
"step": 4200
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 4.576086956521739,
|
| 2953 |
+
"grad_norm": 0.12728244066238403,
|
| 2954 |
+
"learning_rate": 6.671198293627479e-06,
|
| 2955 |
+
"loss": 0.0094,
|
| 2956 |
+
"step": 4210
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 4.586956521739131,
|
| 2960 |
+
"grad_norm": 0.10032593458890915,
|
| 2961 |
+
"learning_rate": 6.5071159772861436e-06,
|
| 2962 |
+
"loss": 0.01,
|
| 2963 |
+
"step": 4220
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 4.5978260869565215,
|
| 2967 |
+
"grad_norm": 0.12760287523269653,
|
| 2968 |
+
"learning_rate": 6.344936180589351e-06,
|
| 2969 |
+
"loss": 0.0093,
|
| 2970 |
+
"step": 4230
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 4.608695652173913,
|
| 2974 |
+
"grad_norm": 0.16303271055221558,
|
| 2975 |
+
"learning_rate": 6.184665997806832e-06,
|
| 2976 |
+
"loss": 0.0133,
|
| 2977 |
+
"step": 4240
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 4.619565217391305,
|
| 2981 |
+
"grad_norm": 0.12212922424077988,
|
| 2982 |
+
"learning_rate": 6.026312439675552e-06,
|
| 2983 |
+
"loss": 0.013,
|
| 2984 |
+
"step": 4250
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 4.630434782608695,
|
| 2988 |
+
"grad_norm": 0.128180593252182,
|
| 2989 |
+
"learning_rate": 5.869882433093155e-06,
|
| 2990 |
+
"loss": 0.0158,
|
| 2991 |
+
"step": 4260
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 4.641304347826087,
|
| 2995 |
+
"grad_norm": 0.0874294564127922,
|
| 2996 |
+
"learning_rate": 5.715382820814885e-06,
|
| 2997 |
+
"loss": 0.0107,
|
| 2998 |
+
"step": 4270
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 4.6521739130434785,
|
| 3002 |
+
"grad_norm": 0.14639824628829956,
|
| 3003 |
+
"learning_rate": 5.562820361154314e-06,
|
| 3004 |
+
"loss": 0.0113,
|
| 3005 |
+
"step": 4280
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 4.663043478260869,
|
| 3009 |
+
"grad_norm": 0.12464270740747452,
|
| 3010 |
+
"learning_rate": 5.412201727687644e-06,
|
| 3011 |
+
"loss": 0.0103,
|
| 3012 |
+
"step": 4290
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 4.673913043478261,
|
| 3016 |
+
"grad_norm": 0.1470411717891693,
|
| 3017 |
+
"learning_rate": 5.263533508961827e-06,
|
| 3018 |
+
"loss": 0.0117,
|
| 3019 |
+
"step": 4300
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 4.684782608695652,
|
| 3023 |
+
"grad_norm": 0.10918842256069183,
|
| 3024 |
+
"learning_rate": 5.116822208206396e-06,
|
| 3025 |
+
"loss": 0.0088,
|
| 3026 |
+
"step": 4310
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 4.695652173913043,
|
| 3030 |
+
"grad_norm": 0.10830997675657272,
|
| 3031 |
+
"learning_rate": 4.972074243048897e-06,
|
| 3032 |
+
"loss": 0.0118,
|
| 3033 |
+
"step": 4320
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 4.706521739130435,
|
| 3037 |
+
"grad_norm": 0.06698288768529892,
|
| 3038 |
+
"learning_rate": 4.829295945234258e-06,
|
| 3039 |
+
"loss": 0.0105,
|
| 3040 |
+
"step": 4330
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 4.717391304347826,
|
| 3044 |
+
"grad_norm": 0.15622438490390778,
|
| 3045 |
+
"learning_rate": 4.688493560347773e-06,
|
| 3046 |
+
"loss": 0.0105,
|
| 3047 |
+
"step": 4340
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 4.728260869565218,
|
| 3051 |
+
"grad_norm": 0.13942964375019073,
|
| 3052 |
+
"learning_rate": 4.549673247541875e-06,
|
| 3053 |
+
"loss": 0.0105,
|
| 3054 |
+
"step": 4350
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 4.739130434782608,
|
| 3058 |
+
"grad_norm": 0.11007948219776154,
|
| 3059 |
+
"learning_rate": 4.412841079266777e-06,
|
| 3060 |
+
"loss": 0.0093,
|
| 3061 |
+
"step": 4360
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 4.75,
|
| 3065 |
+
"grad_norm": 0.1278226226568222,
|
| 3066 |
+
"learning_rate": 4.27800304100478e-06,
|
| 3067 |
+
"loss": 0.0105,
|
| 3068 |
+
"step": 4370
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 4.760869565217392,
|
| 3072 |
+
"grad_norm": 0.1259925812482834,
|
| 3073 |
+
"learning_rate": 4.145165031008508e-06,
|
| 3074 |
+
"loss": 0.0102,
|
| 3075 |
+
"step": 4380
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 4.771739130434782,
|
| 3079 |
+
"grad_norm": 0.11253256350755692,
|
| 3080 |
+
"learning_rate": 4.01433286004283e-06,
|
| 3081 |
+
"loss": 0.0138,
|
| 3082 |
+
"step": 4390
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 4.782608695652174,
|
| 3086 |
+
"grad_norm": 0.1246488019824028,
|
| 3087 |
+
"learning_rate": 3.885512251130763e-06,
|
| 3088 |
+
"loss": 0.0144,
|
| 3089 |
+
"step": 4400
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 4.793478260869565,
|
| 3093 |
+
"grad_norm": 0.1902555227279663,
|
| 3094 |
+
"learning_rate": 3.75870883930306e-06,
|
| 3095 |
+
"loss": 0.0148,
|
| 3096 |
+
"step": 4410
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 4.804347826086957,
|
| 3100 |
+
"grad_norm": 0.0815320685505867,
|
| 3101 |
+
"learning_rate": 3.6339281713517303e-06,
|
| 3102 |
+
"loss": 0.0139,
|
| 3103 |
+
"step": 4420
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 4.815217391304348,
|
| 3107 |
+
"grad_norm": 0.20405898988246918,
|
| 3108 |
+
"learning_rate": 3.511175705587433e-06,
|
| 3109 |
+
"loss": 0.0144,
|
| 3110 |
+
"step": 4430
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 4.826086956521739,
|
| 3114 |
+
"grad_norm": 0.17824992537498474,
|
| 3115 |
+
"learning_rate": 3.390456811600673e-06,
|
| 3116 |
+
"loss": 0.0156,
|
| 3117 |
+
"step": 4440
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 4.836956521739131,
|
| 3121 |
+
"grad_norm": 0.12627997994422913,
|
| 3122 |
+
"learning_rate": 3.271776770026963e-06,
|
| 3123 |
+
"loss": 0.0119,
|
| 3124 |
+
"step": 4450
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 4.8478260869565215,
|
| 3128 |
+
"grad_norm": 0.16256245970726013,
|
| 3129 |
+
"learning_rate": 3.155140772315773e-06,
|
| 3130 |
+
"loss": 0.0116,
|
| 3131 |
+
"step": 4460
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 4.858695652173913,
|
| 3135 |
+
"grad_norm": 0.14503680169582367,
|
| 3136 |
+
"learning_rate": 3.040553920503503e-06,
|
| 3137 |
+
"loss": 0.0103,
|
| 3138 |
+
"step": 4470
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 4.869565217391305,
|
| 3142 |
+
"grad_norm": 0.16697053611278534,
|
| 3143 |
+
"learning_rate": 2.928021226990263e-06,
|
| 3144 |
+
"loss": 0.0115,
|
| 3145 |
+
"step": 4480
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 4.880434782608695,
|
| 3149 |
+
"grad_norm": 0.12260522693395615,
|
| 3150 |
+
"learning_rate": 2.817547614320615e-06,
|
| 3151 |
+
"loss": 0.0127,
|
| 3152 |
+
"step": 4490
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 4.891304347826087,
|
| 3156 |
+
"grad_norm": 0.11083414405584335,
|
| 3157 |
+
"learning_rate": 2.7091379149682685e-06,
|
| 3158 |
+
"loss": 0.0122,
|
| 3159 |
+
"step": 4500
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 4.9021739130434785,
|
| 3163 |
+
"grad_norm": 0.08423303812742233,
|
| 3164 |
+
"learning_rate": 2.602796871124663e-06,
|
| 3165 |
+
"loss": 0.0139,
|
| 3166 |
+
"step": 4510
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 4.913043478260869,
|
| 3170 |
+
"grad_norm": 0.11884451657533646,
|
| 3171 |
+
"learning_rate": 2.4985291344915674e-06,
|
| 3172 |
+
"loss": 0.011,
|
| 3173 |
+
"step": 4520
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 4.923913043478261,
|
| 3177 |
+
"grad_norm": 0.12083287537097931,
|
| 3178 |
+
"learning_rate": 2.3963392660775575e-06,
|
| 3179 |
+
"loss": 0.0118,
|
| 3180 |
+
"step": 4530
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 4.934782608695652,
|
| 3184 |
+
"grad_norm": 0.10024096816778183,
|
| 3185 |
+
"learning_rate": 2.296231735998511e-06,
|
| 3186 |
+
"loss": 0.0105,
|
| 3187 |
+
"step": 4540
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 4.945652173913043,
|
| 3191 |
+
"grad_norm": 0.09267722815275192,
|
| 3192 |
+
"learning_rate": 2.1982109232821178e-06,
|
| 3193 |
+
"loss": 0.0109,
|
| 3194 |
+
"step": 4550
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 4.956521739130435,
|
| 3198 |
+
"grad_norm": 0.10499723255634308,
|
| 3199 |
+
"learning_rate": 2.102281115676258e-06,
|
| 3200 |
+
"loss": 0.0091,
|
| 3201 |
+
"step": 4560
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 4.967391304347826,
|
| 3205 |
+
"grad_norm": 0.08696238696575165,
|
| 3206 |
+
"learning_rate": 2.008446509461498e-06,
|
| 3207 |
+
"loss": 0.0116,
|
| 3208 |
+
"step": 4570
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 4.978260869565218,
|
| 3212 |
+
"grad_norm": 0.17206984758377075,
|
| 3213 |
+
"learning_rate": 1.91671120926748e-06,
|
| 3214 |
+
"loss": 0.0113,
|
| 3215 |
+
"step": 4580
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 4.989130434782608,
|
| 3219 |
+
"grad_norm": 0.12113843113183975,
|
| 3220 |
+
"learning_rate": 1.8270792278934302e-06,
|
| 3221 |
+
"loss": 0.0104,
|
| 3222 |
+
"step": 4590
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 5.0,
|
| 3226 |
+
"grad_norm": 0.22009101510047913,
|
| 3227 |
+
"learning_rate": 1.7395544861325718e-06,
|
| 3228 |
+
"loss": 0.01,
|
| 3229 |
+
"step": 4600
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 5.010869565217392,
|
| 3233 |
+
"grad_norm": 0.16371949017047882,
|
| 3234 |
+
"learning_rate": 1.6541408126006463e-06,
|
| 3235 |
+
"loss": 0.0135,
|
| 3236 |
+
"step": 4610
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 5.021739130434782,
|
| 3240 |
+
"grad_norm": 0.16570837795734406,
|
| 3241 |
+
"learning_rate": 1.5708419435684462e-06,
|
| 3242 |
+
"loss": 0.013,
|
| 3243 |
+
"step": 4620
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 5.032608695652174,
|
| 3247 |
+
"grad_norm": 0.1099071279168129,
|
| 3248 |
+
"learning_rate": 1.4896615227983468e-06,
|
| 3249 |
+
"loss": 0.0107,
|
| 3250 |
+
"step": 4630
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 5.043478260869565,
|
| 3254 |
+
"grad_norm": 0.19537553191184998,
|
| 3255 |
+
"learning_rate": 1.4106031013849496e-06,
|
| 3256 |
+
"loss": 0.0122,
|
| 3257 |
+
"step": 4640
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 5.054347826086956,
|
| 3261 |
+
"grad_norm": 0.1724758744239807,
|
| 3262 |
+
"learning_rate": 1.333670137599713e-06,
|
| 3263 |
+
"loss": 0.0117,
|
| 3264 |
+
"step": 4650
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 5.065217391304348,
|
| 3268 |
+
"grad_norm": 0.12308087944984436,
|
| 3269 |
+
"learning_rate": 1.2588659967397e-06,
|
| 3270 |
+
"loss": 0.0192,
|
| 3271 |
+
"step": 4660
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 5.076086956521739,
|
| 3275 |
+
"grad_norm": 0.11377613991498947,
|
| 3276 |
+
"learning_rate": 1.1861939509803687e-06,
|
| 3277 |
+
"loss": 0.0121,
|
| 3278 |
+
"step": 4670
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 5.086956521739131,
|
| 3282 |
+
"grad_norm": 0.10649964958429337,
|
| 3283 |
+
"learning_rate": 1.1156571792324211e-06,
|
| 3284 |
+
"loss": 0.0088,
|
| 3285 |
+
"step": 4680
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 5.0978260869565215,
|
| 3289 |
+
"grad_norm": 0.11878595501184464,
|
| 3290 |
+
"learning_rate": 1.0472587670027678e-06,
|
| 3291 |
+
"loss": 0.0127,
|
| 3292 |
+
"step": 4690
|
| 3293 |
+
},
|
| 3294 |
+
{
|
| 3295 |
+
"epoch": 5.108695652173913,
|
| 3296 |
+
"grad_norm": 0.07565627247095108,
|
| 3297 |
+
"learning_rate": 9.810017062595322e-07,
|
| 3298 |
+
"loss": 0.0164,
|
| 3299 |
+
"step": 4700
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 5.119565217391305,
|
| 3303 |
+
"grad_norm": 0.1543477326631546,
|
| 3304 |
+
"learning_rate": 9.168888953011989e-07,
|
| 3305 |
+
"loss": 0.0108,
|
| 3306 |
+
"step": 4710
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 5.130434782608695,
|
| 3310 |
+
"grad_norm": 0.170787513256073,
|
| 3311 |
+
"learning_rate": 8.549231386298151e-07,
|
| 3312 |
+
"loss": 0.0132,
|
| 3313 |
+
"step": 4720
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 5.141304347826087,
|
| 3317 |
+
"grad_norm": 0.09899775683879852,
|
| 3318 |
+
"learning_rate": 7.951071468283167e-07,
|
| 3319 |
+
"loss": 0.0112,
|
| 3320 |
+
"step": 4730
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 5.1521739130434785,
|
| 3324 |
+
"grad_norm": 0.11870214343070984,
|
| 3325 |
+
"learning_rate": 7.374435364419674e-07,
|
| 3326 |
+
"loss": 0.0095,
|
| 3327 |
+
"step": 4740
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 5.163043478260869,
|
| 3331 |
+
"grad_norm": 0.11212939023971558,
|
| 3332 |
+
"learning_rate": 6.819348298638839e-07,
|
| 3333 |
+
"loss": 0.0089,
|
| 3334 |
+
"step": 4750
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 5.173913043478261,
|
| 3338 |
+
"grad_norm": 0.20279225707054138,
|
| 3339 |
+
"learning_rate": 6.285834552247128e-07,
|
| 3340 |
+
"loss": 0.0129,
|
| 3341 |
+
"step": 4760
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 5.184782608695652,
|
| 3345 |
+
"grad_norm": 0.09186626970767975,
|
| 3346 |
+
"learning_rate": 5.773917462864264e-07,
|
| 3347 |
+
"loss": 0.011,
|
| 3348 |
+
"step": 4770
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 5.195652173913044,
|
| 3352 |
+
"grad_norm": 0.11231357604265213,
|
| 3353 |
+
"learning_rate": 5.283619423401998e-07,
|
| 3354 |
+
"loss": 0.0125,
|
| 3355 |
+
"step": 4780
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 5.206521739130435,
|
| 3359 |
+
"grad_norm": 0.16140662133693695,
|
| 3360 |
+
"learning_rate": 4.814961881085045e-07,
|
| 3361 |
+
"loss": 0.0097,
|
| 3362 |
+
"step": 4790
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 5.217391304347826,
|
| 3366 |
+
"grad_norm": 0.10995183140039444,
|
| 3367 |
+
"learning_rate": 4.367965336512403e-07,
|
| 3368 |
+
"loss": 0.013,
|
| 3369 |
+
"step": 4800
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 5.228260869565218,
|
| 3373 |
+
"grad_norm": 0.13332118093967438,
|
| 3374 |
+
"learning_rate": 3.9426493427611177e-07,
|
| 3375 |
+
"loss": 0.0097,
|
| 3376 |
+
"step": 4810
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 5.239130434782608,
|
| 3380 |
+
"grad_norm": 0.1429547816514969,
|
| 3381 |
+
"learning_rate": 3.5390325045304706e-07,
|
| 3382 |
+
"loss": 0.0082,
|
| 3383 |
+
"step": 4820
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 5.25,
|
| 3387 |
+
"grad_norm": 0.17897242307662964,
|
| 3388 |
+
"learning_rate": 3.157132477328628e-07,
|
| 3389 |
+
"loss": 0.012,
|
| 3390 |
+
"step": 4830
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"epoch": 5.260869565217392,
|
| 3394 |
+
"grad_norm": 0.08187426626682281,
|
| 3395 |
+
"learning_rate": 2.796965966699927e-07,
|
| 3396 |
+
"loss": 0.0204,
|
| 3397 |
+
"step": 4840
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 5.271739130434782,
|
| 3401 |
+
"grad_norm": 0.10710621625185013,
|
| 3402 |
+
"learning_rate": 2.458548727494292e-07,
|
| 3403 |
+
"loss": 0.0119,
|
| 3404 |
+
"step": 4850
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 5.282608695652174,
|
| 3408 |
+
"grad_norm": 0.08736681938171387,
|
| 3409 |
+
"learning_rate": 2.1418955631781202e-07,
|
| 3410 |
+
"loss": 0.0116,
|
| 3411 |
+
"step": 4860
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 5.293478260869565,
|
| 3415 |
+
"grad_norm": 0.09124402701854706,
|
| 3416 |
+
"learning_rate": 1.847020325186577e-07,
|
| 3417 |
+
"loss": 0.0111,
|
| 3418 |
+
"step": 4870
|
| 3419 |
+
},
|
| 3420 |
+
{
|
| 3421 |
+
"epoch": 5.304347826086957,
|
| 3422 |
+
"grad_norm": 0.12248014658689499,
|
| 3423 |
+
"learning_rate": 1.5739359123178587e-07,
|
| 3424 |
+
"loss": 0.0137,
|
| 3425 |
+
"step": 4880
|
| 3426 |
+
},
|
| 3427 |
+
{
|
| 3428 |
+
"epoch": 5.315217391304348,
|
| 3429 |
+
"grad_norm": 0.1349477767944336,
|
| 3430 |
+
"learning_rate": 1.3226542701689215e-07,
|
| 3431 |
+
"loss": 0.0103,
|
| 3432 |
+
"step": 4890
|
| 3433 |
+
},
|
| 3434 |
+
{
|
| 3435 |
+
"epoch": 5.326086956521739,
|
| 3436 |
+
"grad_norm": 0.19862999022006989,
|
| 3437 |
+
"learning_rate": 1.0931863906127327e-07,
|
| 3438 |
+
"loss": 0.0121,
|
| 3439 |
+
"step": 4900
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 5.336956521739131,
|
| 3443 |
+
"grad_norm": 0.11860275268554688,
|
| 3444 |
+
"learning_rate": 8.855423113177664e-08,
|
| 3445 |
+
"loss": 0.0104,
|
| 3446 |
+
"step": 4910
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 5.3478260869565215,
|
| 3450 |
+
"grad_norm": 0.1107594221830368,
|
| 3451 |
+
"learning_rate": 6.997311153086883e-08,
|
| 3452 |
+
"loss": 0.0096,
|
| 3453 |
+
"step": 4920
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 5.358695652173913,
|
| 3457 |
+
"grad_norm": 0.08218859881162643,
|
| 3458 |
+
"learning_rate": 5.3576093056922906e-08,
|
| 3459 |
+
"loss": 0.0115,
|
| 3460 |
+
"step": 4930
|
| 3461 |
+
},
|
| 3462 |
+
{
|
| 3463 |
+
"epoch": 5.369565217391305,
|
| 3464 |
+
"grad_norm": 0.16671264171600342,
|
| 3465 |
+
"learning_rate": 3.936389296864129e-08,
|
| 3466 |
+
"loss": 0.0101,
|
| 3467 |
+
"step": 4940
|
| 3468 |
+
},
|
| 3469 |
+
{
|
| 3470 |
+
"epoch": 5.380434782608695,
|
| 3471 |
+
"grad_norm": 0.1079106330871582,
|
| 3472 |
+
"learning_rate": 2.7337132953697554e-08,
|
| 3473 |
+
"loss": 0.012,
|
| 3474 |
+
"step": 4950
|
| 3475 |
+
},
|
| 3476 |
+
{
|
| 3477 |
+
"epoch": 5.391304347826087,
|
| 3478 |
+
"grad_norm": 0.0908968448638916,
|
| 3479 |
+
"learning_rate": 1.749633910153592e-08,
|
| 3480 |
+
"loss": 0.0086,
|
| 3481 |
+
"step": 4960
|
| 3482 |
+
},
|
| 3483 |
+
{
|
| 3484 |
+
"epoch": 5.4021739130434785,
|
| 3485 |
+
"grad_norm": 0.14503175020217896,
|
| 3486 |
+
"learning_rate": 9.841941880361916e-09,
|
| 3487 |
+
"loss": 0.0148,
|
| 3488 |
+
"step": 4970
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 5.413043478260869,
|
| 3492 |
+
"grad_norm": 0.12894049286842346,
|
| 3493 |
+
"learning_rate": 4.3742761183018784e-09,
|
| 3494 |
+
"loss": 0.0149,
|
| 3495 |
+
"step": 4980
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 5.423913043478261,
|
| 3499 |
+
"grad_norm": 0.11368037760257721,
|
| 3500 |
+
"learning_rate": 1.0935809887702154e-09,
|
| 3501 |
+
"loss": 0.011,
|
| 3502 |
+
"step": 4990
|
| 3503 |
+
},
|
| 3504 |
+
{
|
| 3505 |
+
"epoch": 5.434782608695652,
|
| 3506 |
+
"grad_norm": 0.10479787737131119,
|
| 3507 |
+
"learning_rate": 0.0,
|
| 3508 |
+
"loss": 0.0124,
|
| 3509 |
+
"step": 5000
|
| 3510 |
+
}
|
| 3511 |
+
],
|
| 3512 |
+
"logging_steps": 10,
|
| 3513 |
+
"max_steps": 5000,
|
| 3514 |
+
"num_input_tokens_seen": 0,
|
| 3515 |
+
"num_train_epochs": 6,
|
| 3516 |
+
"save_steps": 500,
|
| 3517 |
+
"stateful_callbacks": {
|
| 3518 |
+
"TrainerControl": {
|
| 3519 |
+
"args": {
|
| 3520 |
+
"should_epoch_stop": false,
|
| 3521 |
+
"should_evaluate": false,
|
| 3522 |
+
"should_log": false,
|
| 3523 |
+
"should_save": true,
|
| 3524 |
+
"should_training_stop": true
|
| 3525 |
+
},
|
| 3526 |
+
"attributes": {}
|
| 3527 |
+
}
|
| 3528 |
+
},
|
| 3529 |
+
"total_flos": 4.9488596845979616e+17,
|
| 3530 |
+
"train_batch_size": 32,
|
| 3531 |
+
"trial_name": null,
|
| 3532 |
+
"trial_params": null
|
| 3533 |
+
}
|