delete checkpoint

checkpoint/added_tokens.json

@@ -1,28 +0,0 @@
-{
-  "</think>": 151668,
-  "</tool_call>": 151658,
-  "</tool_response>": 151666,
-  "<think>": 151667,
-  "<tool_call>": 151657,
-  "<tool_response>": 151665,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
-}

checkpoint/config.json

@@ -1,30 +0,0 @@
-{
-  "architectures": [
-    "Qwen3ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 12288,
-  "max_position_embeddings": 40960,
-  "max_window_layers": 36,
-  "model_type": "qwen3",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 36,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.1",
-  "use_cache": false,
-  "use_sliding_window": false,
-  "vocab_size": 151936
-}

checkpoint/generation_config.json

@@ -1,13 +0,0 @@
-{
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "temperature": 0.6,
-  "top_k": 20,
-  "top_p": 0.95,
-  "transformers_version": "4.51.1"
-}

checkpoint/global_step/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f5f4f4b79ff32506ab32906080af95d79b9ef1967e42bf55fac6194cb1c74dd0
-size 136

checkpoint/global_step/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:734f86a747fe8100233d07aadf7aa0e2f5475d018c939c2fb35932a55399da80
-size 136

checkpoint/global_step/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d69239f0d6cbccf4515dadc6023e2c1d708e803b4f676645f239b4f401d76fae
-size 136

checkpoint/global_step/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:10be5af584d25f6ecb8ece3884cb34cee90cb7c11a2bde2d32a0119bea301d9e
-size 136

checkpoint/global_step/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:12c2be50cb7ab0c660dc53a2180d2036facdee649f7cc657e70a1f5f3b3b49af
-size 131

checkpoint/global_step/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d6406fa226ac5e40e48d8dcb70712e62c2dba1220aa100b5e9dd31301ac548b8
-size 131

checkpoint/global_step/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4747bd7a8e882aed290e815eef6be5113537e8b99284aaf61ffe24b55402a55b
-size 131

checkpoint/global_step/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e0ebc844de0e4adc15fe26d906efb231737f5460eb4467028e6e495a92a725a2
-size 131

checkpoint/latest

@@ -1 +0,0 @@
-global_step30

checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f7c902e5249e8cffa657fca39c1f1235ae0e40cfbdf54fa21b496350ac7e3e1c
-size 135

checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:73cec5175b48a2873e56ddd88addafe391d27c09f37ca000b9b1426c524c3e5e
-size 135

checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5b7f159391827175ff75e3f87597befd1cc41fb8f698e9a73396025fedb2454c
-size 135

checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:324a90d05ec6403957185cd43f83bdd8731ffab4e34c5a47799f7b22403c019e
-size 135

checkpoint/model.safetensors.index.json

@@ -1,406 +0,0 @@
-{
-  "metadata": {
-    "total_size": 16381470720
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00004-of-00004.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.norm.weight": "model-00004-of-00004.safetensors"
-  }
-}

checkpoint/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:258c1e2c3a63db2f51212e850765e60b7cb8b33f7d5e4e9159643ce8adc99656
-size 130

checkpoint/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b63ba8e1dd2b548f83977d34f8a1552a67bc66ce33488c9733fcada5b45b62aa
-size 130

checkpoint/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1a0ba59dfefd101ded99c7e9f8efbbe53ce9a0276a30cec53f6fb02c129d1e08
-size 130

checkpoint/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:449bf3efd1254534866a15b011b5f515b7ed583db62d5b542cc09e02d0c247a6
-size 130

checkpoint/special_tokens_map.json

@@ -1,31 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

checkpoint/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
-size 11422821

checkpoint/tokenizer_config.json

@@ -1,245 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "max_length": 16384,
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "left",
-  "split_special_tokens": false,
-  "stride": 0,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": null
-}

checkpoint/trainer_state.json

@@ -1,664 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.1568627450980392,
-  "eval_steps": 500,
-  "global_step": 30,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "accuracy_delta": -0.03125,
-      "baseline_accuracy": 0.5625,
-      "completion_length": 1660.1953125,
-      "degradation_rate": 0.1875,
-      "epoch": 0.00522875816993464,
-      "grad_norm": 1.8285036167620026,
-      "improvement_rate": 0.15625,
-      "kl": 0.0,
-      "learning_rate": 2e-06,
-      "loss": 0.0,
-      "reward": 0.24004681408405304,
-      "reward_std": 0.25635848194360733,
-      "rewards/AdaptiveTeachingReward": 0.24004681408405304,
-      "step": 1,
-      "student_accuracy": 0.53125,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 1349.5,
-      "teaching_length_std": 1533.2601122433693,
-      "token_efficiency": 0.01778511088825826
-    },
-    {
-      "accuracy_delta": -0.21875,
-      "baseline_accuracy": 1.0,
-      "completion_length": 2174.171875,
-      "degradation_rate": 0.21875,
-      "epoch": 0.01045751633986928,
-      "grad_norm": 1.2225533588422857,
-      "improvement_rate": 0.0,
-      "kl": 0.002572178840637207,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.2656950503587723,
-      "reward_std": 0.17467603832483292,
-      "rewards/AdaptiveTeachingReward": 0.2656950503587723,
-      "step": 2,
-      "student_accuracy": 0.78125,
-      "student_approach_length": 489.875,
-      "teaching_length_mean": 1645.90625,
-      "teaching_length_std": 1777.2254866782437,
-      "token_efficiency": 0.016061369340544678
-    },
-    {
-      "accuracy_delta": -0.0625,
-      "baseline_accuracy": 0.0625,
-      "completion_length": 2889.65625,
-      "degradation_rate": 0.0625,
-      "epoch": 0.01568627450980392,
-      "grad_norm": 0.4912196165940296,
-      "improvement_rate": 0.0,
-      "kl": 0.0021309852600097656,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.1566198617219925,
-      "reward_std": 0.17452973127365112,
-      "rewards/AdaptiveTeachingReward": 0.1566198617219925,
-      "step": 3,
-      "student_accuracy": 0.0,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 3435.71875,
-      "teaching_length_std": 874.6175996443687,
-      "token_efficiency": 0.005029539554335019
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.0,
-      "completion_length": 1765.4765625,
-      "degradation_rate": 0.0,
-      "epoch": 0.02091503267973856,
-      "grad_norm": 0.014919439029800962,
-      "improvement_rate": 0.0,
-      "kl": 0.0024797916412353516,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.0,
-      "reward_std": 0.0,
-      "rewards/AdaptiveTeachingReward": 0.0,
-      "step": 4,
-      "student_accuracy": 0.0,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 1644.53125,
-      "teaching_length_std": 1544.9233390329066,
-      "token_efficiency": 0.0
-    },
-    {
-      "accuracy_delta": 0.1875,
-      "baseline_accuracy": 0.375,
-      "completion_length": 2330.296875,
-      "degradation_rate": 0.09375,
-      "epoch": 0.026143790849673203,
-      "grad_norm": 1.6480657403271404,
-      "improvement_rate": 0.28125,
-      "kl": 0.002542257308959961,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.293629452586174,
-      "reward_std": 0.31043318659067154,
-      "rewards/AdaptiveTeachingReward": 0.293629452586174,
-      "step": 5,
-      "student_accuracy": 0.5625,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2543.6875,
-      "teaching_length_std": 1157.76463240177,
-      "token_efficiency": 0.015775285003662067
-    },
-    {
-      "accuracy_delta": -0.125,
-      "baseline_accuracy": 0.375,
-      "completion_length": 2799.2265625,
-      "degradation_rate": 0.21875,
-      "epoch": 0.03137254901960784,
-      "grad_norm": 1.3626772466174568,
-      "improvement_rate": 0.09375,
-      "kl": 0.0024237632751464844,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.297846183180809,
-      "reward_std": 0.1792445182800293,
-      "rewards/AdaptiveTeachingReward": 0.297846183180809,
-      "step": 6,
-      "student_accuracy": 0.25,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 3300.46875,
-      "teaching_length_std": 1322.463354762313,
-      "token_efficiency": 0.008984860526379333
-    },
-    {
-      "accuracy_delta": 0.15625,
-      "baseline_accuracy": 0.09375,
-      "completion_length": 2839.59375,
-      "degradation_rate": 0.0,
-      "epoch": 0.036601307189542485,
-      "grad_norm": 1.0148015671601693,
-      "improvement_rate": 0.15625,
-      "kl": 0.0022563934326171875,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.22244123369455338,
-      "reward_std": 0.32708095014095306,
-      "rewards/AdaptiveTeachingReward": 0.22244123369455338,
-      "step": 7,
-      "student_accuracy": 0.25,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2663.28125,
-      "teaching_length_std": 1263.471554191286,
-      "token_efficiency": 0.009322577760442718
-    },
-    {
-      "accuracy_delta": 0.03125,
-      "baseline_accuracy": 0.34375,
-      "completion_length": 2997.0234375,
-      "degradation_rate": 0.0625,
-      "epoch": 0.04183006535947712,
-      "grad_norm": 1.0933058629769363,
-      "improvement_rate": 0.09375,
-      "kl": 0.00222015380859375,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.4145798534154892,
-      "reward_std": 0.348370686173439,
-      "rewards/AdaptiveTeachingReward": 0.4145798534154892,
-      "step": 8,
-      "student_accuracy": 0.375,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2859.9375,
-      "teaching_length_std": 1548.3925018635746,
-      "token_efficiency": 0.014895284304358753
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.0,
-      "completion_length": 2069.3515625,
-      "degradation_rate": 0.0,
-      "epoch": 0.047058823529411764,
-      "grad_norm": 0.6907373861546955,
-      "improvement_rate": 0.0,
-      "kl": 0.0022356510162353516,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.13787749409675598,
-      "reward_std": 0.08163860440254211,
-      "rewards/AdaptiveTeachingReward": 0.13787749409675598,
-      "step": 9,
-      "student_accuracy": 0.0,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 1586.78125,
-      "teaching_length_std": 1393.5538468081056,
-      "token_efficiency": 0.009196431155361413
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.0,
-      "completion_length": 2533.3203125,
-      "degradation_rate": 0.0,
-      "epoch": 0.05228758169934641,
-      "grad_norm": 0.9569337200656036,
-      "improvement_rate": 0.0,
-      "kl": 0.002455472946166992,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.2650887817144394,
-      "reward_std": 0.1834174394607544,
-      "rewards/AdaptiveTeachingReward": 0.2650887817144394,
-      "step": 10,
-      "student_accuracy": 0.0,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2718.53125,
-      "teaching_length_std": 1545.6357044636015,
-      "token_efficiency": 0.00983657689669804
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.0,
-      "completion_length": 2366.4609375,
-      "degradation_rate": 0.0,
-      "epoch": 0.05751633986928104,
-      "grad_norm": 0.1992844149700769,
-      "improvement_rate": 0.0,
-      "kl": 0.0023772716522216797,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.00799931213259697,
-      "reward_std": 0.045250944793224335,
-      "rewards/AdaptiveTeachingReward": 0.00799931213259697,
-      "step": 11,
-      "student_accuracy": 0.0,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2560.28125,
-      "teaching_length_std": 1264.0513369895032,
-      "token_efficiency": 0.000244351732796639
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.0,
-      "completion_length": 2429.25,
-      "degradation_rate": 0.0,
-      "epoch": 0.06274509803921569,
-      "grad_norm": 0.02438642631727396,
-      "improvement_rate": 0.0,
-      "kl": 0.0028073787689208984,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.0,
-      "reward_std": 0.0,
-      "rewards/AdaptiveTeachingReward": 0.0,
-      "step": 12,
-      "student_accuracy": 0.0,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2684.0,
-      "teaching_length_std": 1537.9383137400418,
-      "token_efficiency": 0.0
-    },
-    {
-      "accuracy_delta": 0.03125,
-      "baseline_accuracy": 0.03125,
-      "completion_length": 2985.0234375,
-      "degradation_rate": 0.03125,
-      "epoch": 0.06797385620915032,
-      "grad_norm": 1.9377263264415499,
-      "improvement_rate": 0.0625,
-      "kl": 0.002295255661010742,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.3229658156633377,
-      "reward_std": 0.2836003005504608,
-      "rewards/AdaptiveTeachingReward": 0.3229658156633377,
-      "step": 13,
-      "student_accuracy": 0.0625,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2764.78125,
-      "teaching_length_std": 1359.6938149421062,
-      "token_efficiency": 0.011864912871618307
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.40625,
-      "completion_length": 2860.7890625,
-      "degradation_rate": 0.03125,
-      "epoch": 0.07320261437908497,
-      "grad_norm": 0.7397348398480618,
-      "improvement_rate": 0.03125,
-      "kl": 0.0022339820861816406,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.3183840811252594,
-      "reward_std": 0.2730633243918419,
-      "rewards/AdaptiveTeachingReward": 0.3183840811252594,
-      "step": 14,
-      "student_accuracy": 0.40625,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 3300.75,
-      "teaching_length_std": 1258.5522551939885,
-      "token_efficiency": 0.009677591351820222
-    },
-    {
-      "accuracy_delta": -0.25,
-      "baseline_accuracy": 0.59375,
-      "completion_length": 2667.375,
-      "degradation_rate": 0.375,
-      "epoch": 0.0784313725490196,
-      "grad_norm": 0.591091766464445,
-      "improvement_rate": 0.125,
-      "kl": 0.0020873546600341797,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.14508739858865738,
-      "reward_std": 0.1915995106101036,
-      "rewards/AdaptiveTeachingReward": 0.14508739858865738,
-      "step": 15,
-      "student_accuracy": 0.34375,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2580.1875,
-      "teaching_length_std": 1411.9177183341415,
-      "token_efficiency": 0.006345218750950054
-    },
-    {
-      "accuracy_delta": -0.125,
-      "baseline_accuracy": 0.78125,
-      "completion_length": 2397.8046875,
-      "degradation_rate": 0.28125,
-      "epoch": 0.08366013071895424,
-      "grad_norm": 1.0467841728187868,
-      "improvement_rate": 0.15625,
-      "kl": 0.0020101070404052734,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.29722827672958374,
-      "reward_std": 0.29581306129693985,
-      "rewards/AdaptiveTeachingReward": 0.29722827672958374,
-      "step": 16,
-      "student_accuracy": 0.65625,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 1867.65625,
-      "teaching_length_std": 1645.2406135166107,
-      "token_efficiency": 0.016315762169946447
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.4375,
-      "completion_length": 2681.4296875,
-      "degradation_rate": 0.0625,
-      "epoch": 0.08888888888888889,
-      "grad_norm": 1.0178368263353954,
-      "improvement_rate": 0.0625,
-      "kl": 0.0022170543670654297,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.27442795038223267,
-      "reward_std": 0.24267160892486572,
-      "rewards/AdaptiveTeachingReward": 0.27442795038223267,
-      "step": 17,
-      "student_accuracy": 0.4375,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 1946.4375,
-      "teaching_length_std": 1595.4173133278073,
-      "token_efficiency": 0.01725690617086827
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.0,
-      "completion_length": 2260.1484375,
-      "degradation_rate": 0.0,
-      "epoch": 0.09411764705882353,
-      "grad_norm": 0.39094525161531923,
-      "improvement_rate": 0.0,
-      "kl": 0.0026335716247558594,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.15987491607666016,
-      "reward_std": 0.12795361876487732,
-      "rewards/AdaptiveTeachingReward": 0.15987491607666016,
-      "step": 18,
-      "student_accuracy": 0.0,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2452.8125,
-      "teaching_length_std": 1687.6677585883976,
-      "token_efficiency": 0.00733118954839666
-    },
-    {
-      "accuracy_delta": 0.09375,
-      "baseline_accuracy": 0.34375,
-      "completion_length": 2509.359375,
-      "degradation_rate": 0.0,
-      "epoch": 0.09934640522875816,
-      "grad_norm": 1.112027848483532,
-      "improvement_rate": 0.09375,
-      "kl": 0.0021845102310180664,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.32069824635982513,
-      "reward_std": 0.1779022440314293,
-      "rewards/AdaptiveTeachingReward": 0.32069824635982513,
-      "step": 19,
-      "student_accuracy": 0.4375,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 1688.25,
-      "teaching_length_std": 1591.1127810270257,
-      "token_efficiency": 0.02000900419695598
-    },
-    {
-      "accuracy_delta": 0.15625,
-      "baseline_accuracy": 0.25,
-      "completion_length": 2566.109375,
-      "degradation_rate": 0.125,
-      "epoch": 0.10457516339869281,
-      "grad_norm": 0.635668741879516,
-      "improvement_rate": 0.28125,
-      "kl": 0.0020592212677001953,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.3237999305129051,
-      "reward_std": 0.29250405728816986,
-      "rewards/AdaptiveTeachingReward": 0.3237999305129051,
-      "step": 20,
-      "student_accuracy": 0.40625,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 3000.8125,
-      "teaching_length_std": 1146.9664495361749,
-      "token_efficiency": 0.009248973352977438
-    },
-    {
-      "accuracy_delta": -0.15625,
-      "baseline_accuracy": 0.5,
-      "completion_length": 2821.34375,
-      "degradation_rate": 0.15625,
-      "epoch": 0.10980392156862745,
-      "grad_norm": 1.038632983891241,
-      "improvement_rate": 0.0,
-      "kl": 0.0022677183151245117,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.26167380064725876,
-      "reward_std": 0.20054005086421967,
-      "rewards/AdaptiveTeachingReward": 0.26167380064725876,
-      "step": 21,
-      "student_accuracy": 0.34375,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2324.625,
-      "teaching_length_std": 1783.1465396131703,
-      "token_efficiency": 0.011391752427342916
-    },
-    {
-      "accuracy_delta": -0.0625,
-      "baseline_accuracy": 0.6875,
-      "completion_length": 1981.4453125,
-      "degradation_rate": 0.21875,
-      "epoch": 0.11503267973856209,
-      "grad_norm": 1.0591629807323937,
-      "improvement_rate": 0.15625,
-      "kl": 0.0025501251220703125,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.3476671576499939,
-      "reward_std": 0.32001765072345734,
-      "rewards/AdaptiveTeachingReward": 0.3476671576499939,
-      "step": 22,
-      "student_accuracy": 0.625,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 1747.6875,
-      "teaching_length_std": 1544.1982674617702,
-      "token_efficiency": 0.019930595836054183
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.6875,
-      "completion_length": 2491.2109375,
-      "degradation_rate": 0.15625,
-      "epoch": 0.12026143790849673,
-      "grad_norm": 0.8736384977021919,
-      "improvement_rate": 0.15625,
-      "kl": 0.002077817916870117,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.3966591954231262,
-      "reward_std": 0.35394637286663055,
-      "rewards/AdaptiveTeachingReward": 0.3966591954231262,
-      "step": 23,
-      "student_accuracy": 0.6875,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2244.40625,
-      "teaching_length_std": 1464.1512714006012,
-      "token_efficiency": 0.020170202633726
-    },
-    {
-      "accuracy_delta": -0.0625,
-      "baseline_accuracy": 0.40625,
-      "completion_length": 3183.6796875,
-      "degradation_rate": 0.09375,
-      "epoch": 0.12549019607843137,
-      "grad_norm": 0.731937384244321,
-      "improvement_rate": 0.03125,
-      "kl": 0.002083301544189453,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.24638524651527405,
-      "reward_std": 0.25337880849838257,
-      "rewards/AdaptiveTeachingReward": 0.24638524651527405,
-      "step": 24,
-      "student_accuracy": 0.34375,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2833.75,
-      "teaching_length_std": 883.8529811162587,
-      "token_efficiency": 0.0154971457828618
-    },
-    {
-      "accuracy_delta": 0.09375,
-      "baseline_accuracy": 0.09375,
-      "completion_length": 2996.8203125,
-      "degradation_rate": 0.0625,
-      "epoch": 0.13071895424836602,
-      "grad_norm": 1.0366727211421645,
-      "improvement_rate": 0.15625,
-      "kl": 0.002071857452392578,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.10002126544713974,
-      "reward_std": 0.12362907081842422,
-      "rewards/AdaptiveTeachingReward": 0.10002126544713974,
-      "step": 25,
-      "student_accuracy": 0.1875,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2241.40625,
-      "teaching_length_std": 1680.2583046873353,
-      "token_efficiency": 0.005314979233325259
-    },
-    {
-      "accuracy_delta": 0.03125,
-      "baseline_accuracy": 0.125,
-      "completion_length": 2699.5078125,
-      "degradation_rate": 0.125,
-      "epoch": 0.13594771241830064,
-      "grad_norm": 0.8849958564728577,
-      "improvement_rate": 0.15625,
-      "kl": 0.00244140625,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.21003766357898712,
-      "reward_std": 0.27024491131305695,
-      "rewards/AdaptiveTeachingReward": 0.21003766357898712,
-      "step": 26,
-      "student_accuracy": 0.15625,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2865.75,
-      "teaching_length_std": 1575.6950824020187,
-      "token_efficiency": 0.00747702067329278
-    },
-    {
-      "accuracy_delta": 0.09375,
-      "baseline_accuracy": 0.0,
-      "completion_length": 2216.78125,
-      "degradation_rate": 0.0,
-      "epoch": 0.1411764705882353,
-      "grad_norm": 0.6451950468247998,
-      "improvement_rate": 0.09375,
-      "kl": 0.0021767616271972656,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.2089657336473465,
-      "reward_std": 0.21514078974723816,
-      "rewards/AdaptiveTeachingReward": 0.2089657336473465,
-      "step": 27,
-      "student_accuracy": 0.09375,
-      "student_approach_length": 499.96875,
-      "teaching_length_mean": 2619.40625,
-      "teaching_length_std": 1265.4369118665845,
-      "token_efficiency": 0.0060904088353781515
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.0,
-      "completion_length": 2668.4140625,
-      "degradation_rate": 0.0,
-      "epoch": 0.14640522875816994,
-      "grad_norm": 0.7896767066978999,
-      "improvement_rate": 0.0,
-      "kl": 0.002083301544189453,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.14528799057006836,
-      "reward_std": 0.09566954523324966,
-      "rewards/AdaptiveTeachingReward": 0.14528799057006836,
-      "step": 28,
-      "student_accuracy": 0.0,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 3113.90625,
-      "teaching_length_std": 884.9974614855895,
-      "token_efficiency": 0.0035470700822770596
-    },
-    {
-      "accuracy_delta": 0.03125,
-      "baseline_accuracy": 0.0,
-      "completion_length": 2467.4140625,
-      "degradation_rate": 0.0,
-      "epoch": 0.15163398692810456,
-      "grad_norm": 0.22872066233966626,
-      "improvement_rate": 0.03125,
-      "kl": 0.0025146007537841797,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.007998689077794552,
-      "reward_std": 0.04524742066860199,
-      "rewards/AdaptiveTeachingReward": 0.007998689077794552,
-      "step": 29,
-      "student_accuracy": 0.03125,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2764.9375,
-      "teaching_length_std": 1560.6896673437209,
-      "token_efficiency": 0.0002591402932910396
-    },
-    {
-      "accuracy_delta": 0.0,
-      "baseline_accuracy": 0.0,
-      "completion_length": 2854.59375,
-      "degradation_rate": 0.0,
-      "epoch": 0.1568627450980392,
-      "grad_norm": 0.5744778046050318,
-      "improvement_rate": 0.0,
-      "kl": 0.0022513866424560547,
-      "learning_rate": 2e-06,
-      "loss": 0.0001,
-      "reward": 0.16005077958106995,
-      "reward_std": 0.10021104663610458,
-      "rewards/AdaptiveTeachingReward": 0.16005077958106995,
-      "step": 30,
-      "student_accuracy": 0.0,
-      "student_approach_length": 500.0,
-      "teaching_length_mean": 2139.71875,
-      "teaching_length_std": 1711.9645016733543,
-      "token_efficiency": 0.007949871083127776
-    }
-  ],
-  "logging_steps": 1,
-  "max_steps": 250,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 10,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 0.0,
-  "train_batch_size": 16,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fb102755f6a8032c8da7daf88cca9336f93aa1768d8d06988bb3559ee06587f7
-size 129

checkpoint/zero_to_fp32.py

@@ -1,674 +0,0 @@
-#!/usr/bin/env python
-
-# Copyright (c) Microsoft Corporation.
-# SPDX-License-Identifier: Apache-2.0
-
-# DeepSpeed Team
-
-# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
-# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
-# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
-# application.
-#
-# example:
-#   python zero_to_fp32.py . output_dir/
-#   or
-#   python zero_to_fp32.py . output_dir/ --safe_serialization
-
-import argparse
-import torch
-import glob
-import math
-import os
-import re
-import json
-from tqdm import tqdm
-from collections import OrderedDict
-from dataclasses import dataclass
-
-# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
-# DeepSpeed data structures it has to be available in the current python environment.
-from deepspeed.utils import logger
-from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
-                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
-                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
-
-
-@dataclass
-class zero_model_state:
-    buffers: dict()
-    param_shapes: dict()
-    shared_params: list
-    ds_version: int
-    frozen_param_shapes: dict()
-    frozen_param_fragments: dict()
-
-
-debug = 0
-
-# load to cpu
-device = torch.device('cpu')
-
-
-def atoi(text):
-    return int(text) if text.isdigit() else text
-
-
-def natural_keys(text):
-    '''
-    alist.sort(key=natural_keys) sorts in human order
-    http://nedbatchelder.com/blog/200712/human_sorting.html
-    (See Toothy's implementation in the comments)
-    '''
-    return [atoi(c) for c in re.split(r'(\d+)', text)]
-
-
-def get_model_state_file(checkpoint_dir, zero_stage):
-    if not os.path.isdir(checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
-
-    # there should be only one file
-    if zero_stage <= 2:
-        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
-    elif zero_stage == 3:
-        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
-
-    if not os.path.exists(file):
-        raise FileNotFoundError(f"can't find model states file at '{file}'")
-
-    return file
-
-
-def get_checkpoint_files(checkpoint_dir, glob_pattern):
-    # XXX: need to test that this simple glob rule works for multi-node setup too
-    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
-
-    if len(ckpt_files) == 0:
-        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
-
-    return ckpt_files
-
-
-def get_optim_files(checkpoint_dir):
-    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
-
-
-def get_model_state_files(checkpoint_dir):
-    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
-
-
-def parse_model_states(files):
-    zero_model_states = []
-    for file in files:
-        state_dict = torch.load(file, map_location=device)
-
-        if BUFFER_NAMES not in state_dict:
-            raise ValueError(f"{file} is not a model state checkpoint")
-        buffer_names = state_dict[BUFFER_NAMES]
-        if debug:
-            print("Found buffers:", buffer_names)
-
-        # recover just the buffers while restoring them to fp32 if they were saved in fp16
-        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
-        param_shapes = state_dict[PARAM_SHAPES]
-
-        # collect parameters that are included in param_shapes
-        param_names = []
-        for s in param_shapes:
-            for name in s.keys():
-                param_names.append(name)
-
-        # update with frozen parameters
-        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
-        if frozen_param_shapes is not None:
-            if debug:
-                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
-            param_names += list(frozen_param_shapes.keys())
-
-        # handle shared params
-        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
-
-        ds_version = state_dict.get(DS_VERSION, None)
-
-        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
-
-        z_model_state = zero_model_state(buffers=buffers,
-                                         param_shapes=param_shapes,
-                                         shared_params=shared_params,
-                                         ds_version=ds_version,
-                                         frozen_param_shapes=frozen_param_shapes,
-                                         frozen_param_fragments=frozen_param_fragments)
-        zero_model_states.append(z_model_state)
-
-    return zero_model_states
-
-
-def parse_optim_states(files, ds_checkpoint_dir):
-    total_files = len(files)
-    state_dicts = []
-    for f in files:
-        state_dict = torch.load(f, map_location=device)
-        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
-        # and also handle the case where it was already removed by another helper script
-        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
-        state_dicts.append(state_dict)
-
-    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
-        raise ValueError(f"{files[0]} is not a zero checkpoint")
-    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
-    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
-
-    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
-    # parameters can be different from data parallelism for non-expert parameters. So we can just
-    # use the max of the partition_count to get the dp world_size.
-
-    if type(world_size) is list:
-        world_size = max(world_size)
-
-    if world_size != total_files:
-        raise ValueError(
-            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
-            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
-        )
-
-    # the groups are named differently in each stage
-    if zero_stage <= 2:
-        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
-    elif zero_stage == 3:
-        fp32_groups_key = FP32_FLAT_GROUPS
-    else:
-        raise ValueError(f"unknown zero stage {zero_stage}")
-
-    if zero_stage <= 2:
-        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
-    elif zero_stage == 3:
-        # if there is more than one param group, there will be multiple flattened tensors - one
-        # flattened tensor per group - for simplicity merge them into a single tensor
-        #
-        # XXX: could make the script more memory efficient for when there are multiple groups - it
-        # will require matching the sub-lists of param_shapes for each param group flattened tensor
-
-        fp32_flat_groups = [
-            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
-        ]
-
-    return zero_stage, world_size, fp32_flat_groups
-
-
-def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
-    """
-    Returns fp32 state_dict reconstructed from ds checkpoint
-
-    Args:
-        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
-
-    """
-    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
-
-    optim_files = get_optim_files(ds_checkpoint_dir)
-    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
-    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
-
-    model_files = get_model_state_files(ds_checkpoint_dir)
-
-    zero_model_states = parse_model_states(model_files)
-    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
-
-    if zero_stage <= 2:
-        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                                          exclude_frozen_parameters)
-    elif zero_stage == 3:
-        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                                          exclude_frozen_parameters)
-
-
-def _zero2_merge_frozen_params(state_dict, zero_model_states):
-    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
-        return
-
-    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
-    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
-
-    if debug:
-        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
-        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
-
-        wanted_params = len(frozen_param_shapes)
-        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
-        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
-        print(f'Frozen params: Have {avail_numel} numels to process.')
-        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
-
-    total_params = 0
-    total_numel = 0
-    for name, shape in frozen_param_shapes.items():
-        total_params += 1
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-
-        state_dict[name] = frozen_param_fragments[name]
-
-        if debug:
-            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
-
-    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _has_callable(obj, fn):
-    attr = getattr(obj, fn, None)
-    return callable(attr)
-
-
-def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
-    param_shapes = zero_model_states[0].param_shapes
-
-    # Reconstruction protocol:
-    #
-    # XXX: document this
-
-    if debug:
-        for i in range(world_size):
-            for j in range(len(fp32_flat_groups[0])):
-                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
-
-    # XXX: memory usage doubles here (zero2)
-    num_param_groups = len(fp32_flat_groups[0])
-    merged_single_partition_of_fp32_groups = []
-    for i in range(num_param_groups):
-        merged_partitions = [sd[i] for sd in fp32_flat_groups]
-        full_single_fp32_vector = torch.cat(merged_partitions, 0)
-        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
-    avail_numel = sum(
-        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
-
-    if debug:
-        wanted_params = sum([len(shapes) for shapes in param_shapes])
-        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
-        # not asserting if there is a mismatch due to possible padding
-        print(f"Have {avail_numel} numels to process.")
-        print(f"Need {wanted_numel} numels in {wanted_params} params.")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    total_numel = 0
-    total_params = 0
-    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
-        offset = 0
-        avail_numel = full_single_fp32_vector.numel()
-        for name, shape in shapes.items():
-
-            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
-            total_numel += unpartitioned_numel
-            total_params += 1
-
-            if debug:
-                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
-            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
-            offset += unpartitioned_numel
-
-        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
-        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
-        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
-        # live optimizer object, so we are checking that the numbers are within the right range
-        align_to = 2 * world_size
-
-        def zero2_align(x):
-            return align_to * math.ceil(x / align_to)
-
-        if debug:
-            print(f"original offset={offset}, avail_numel={avail_numel}")
-
-        offset = zero2_align(offset)
-        avail_numel = zero2_align(avail_numel)
-
-        if debug:
-            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
-
-        # Sanity check
-        if offset != avail_numel:
-            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                               exclude_frozen_parameters):
-    state_dict = OrderedDict()
-
-    # buffers
-    buffers = zero_model_states[0].buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    if not exclude_frozen_parameters:
-        _zero2_merge_frozen_params(state_dict, zero_model_states)
-
-    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
-
-    # recover shared parameters
-    for pair in zero_model_states[0].shared_params:
-        if pair[1] in state_dict:
-            state_dict[pair[0]] = state_dict[pair[1]]
-
-    return state_dict
-
-
-def zero3_partitioned_param_info(unpartitioned_numel, world_size):
-    remainder = unpartitioned_numel % world_size
-    padding_numel = (world_size - remainder) if remainder else 0
-    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
-    return partitioned_numel, padding_numel
-
-
-def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
-    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
-        return
-
-    if debug:
-        for i in range(world_size):
-            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
-            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
-
-        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
-        wanted_params = len(frozen_param_shapes)
-        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
-        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
-        print(f'Frozen params: Have {avail_numel} numels to process.')
-        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
-
-    total_params = 0
-    total_numel = 0
-    for name, shape in zero_model_states[0].frozen_param_shapes.items():
-        total_params += 1
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-
-        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
-        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
-
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
-    param_shapes = zero_model_states[0].param_shapes
-    avail_numel = fp32_flat_groups[0].numel() * world_size
-    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
-    # param, re-consolidating each param, while dealing with padding if any
-
-    # merge list of dicts, preserving order
-    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
-
-    if debug:
-        for i in range(world_size):
-            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
-
-        wanted_params = len(param_shapes)
-        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
-        # not asserting if there is a mismatch due to possible padding
-        avail_numel = fp32_flat_groups[0].numel() * world_size
-        print(f"Trainable params: Have {avail_numel} numels to process.")
-        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    offset = 0
-    total_numel = 0
-    total_params = 0
-    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-        total_params += 1
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-        # XXX: memory usage doubles here
-        state_dict[name] = torch.cat(
-            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
-            0).narrow(0, 0, unpartitioned_numel).view(shape)
-        offset += partitioned_numel
-
-    offset *= world_size
-
-    # Sanity check
-    if offset != avail_numel:
-        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                               exclude_frozen_parameters):
-    state_dict = OrderedDict()
-
-    # buffers
-    buffers = zero_model_states[0].buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    if not exclude_frozen_parameters:
-        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
-
-    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
-
-    # recover shared parameters
-    for pair in zero_model_states[0].shared_params:
-        if pair[1] in state_dict:
-            state_dict[pair[0]] = state_dict[pair[1]]
-
-    return state_dict
-
-
-def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
-    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
-    via a model hub.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
-        - ``exclude_frozen_parameters``: exclude frozen parameters
-
-    Returns:
-        - pytorch ``state_dict``
-
-    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
-    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
-    the checkpoint.
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
-        # do the training and checkpoint saving
-        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
-        model = model.cpu() # move to cpu
-        model.load_state_dict(state_dict)
-        # submit to model hub or save the model to share with others
-
-    In this example the ``model`` will no longer be usable in the deepspeed context of the same
-    application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
-
-    """
-    if tag is None:
-        latest_path = os.path.join(checkpoint_dir, 'latest')
-        if os.path.isfile(latest_path):
-            with open(latest_path, 'r') as fd:
-                tag = fd.read().strip()
-        else:
-            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
-
-    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
-
-    if not os.path.isdir(ds_checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
-
-    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
-
-
-def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
-                                               output_dir,
-                                               max_shard_size="5GB",
-                                               safe_serialization=False,
-                                               tag=None,
-                                               exclude_frozen_parameters=False):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
-    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``output_dir``: directory to the pytorch fp32 state_dict output files
-        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
-        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
-        - ``exclude_frozen_parameters``: exclude frozen parameters
-    """
-    # Dependency pre-check
-    if safe_serialization:
-        try:
-            from safetensors.torch import save_file
-        except ImportError:
-            print('If you want to use `safe_serialization`, please `pip install safetensors`')
-            raise
-    if max_shard_size is not None:
-        try:
-            from huggingface_hub import split_torch_state_dict_into_shards
-        except ImportError:
-            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
-            raise
-
-    # Convert zero checkpoint to state_dict
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
-
-    # Shard the model if it is too big.
-    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
-    if max_shard_size is not None:
-        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
-        state_dict_split = split_torch_state_dict_into_shards(state_dict,
-                                                              filename_pattern=filename_pattern,
-                                                              max_shard_size=max_shard_size)
-    else:
-        from collections import namedtuple
-        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
-        state_dict_split = StateDictSplit(is_sharded=False,
-                                          filename_to_tensors={weights_name: list(state_dict.keys())})
-
-    # Save the model
-    filename_to_tensors = state_dict_split.filename_to_tensors.items()
-    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
-        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
-        output_path = os.path.join(output_dir, shard_file)
-        if safe_serialization:
-            save_file(shard, output_path, metadata={"format": "pt"})
-        else:
-            torch.save(shard, output_path)
-
-    # Save index if sharded
-    if state_dict_split.is_sharded:
-        index = {
-            "metadata": state_dict_split.metadata,
-            "weight_map": state_dict_split.tensor_to_filename,
-        }
-        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
-        save_index_file = os.path.join(output_dir, save_index_file)
-        with open(save_index_file, "w", encoding="utf-8") as f:
-            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
-            f.write(content)
-
-
-def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
-    """
-    1. Put the provided model to cpu
-    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
-    3. Load it into the provided model
-
-    Args:
-        - ``model``: the model object to update
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
-
-    Returns:
-        - ``model`: modified model
-
-    Make sure you have plenty of CPU memory available before you call this function. If you don't
-    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
-    conveniently placed for you in the checkpoint folder.
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
-        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
-        # submit to model hub or save the model to share with others
-
-    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
-    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    """
-    logger.info(f"Extracting fp32 weights")
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
-
-    logger.info(f"Overwriting model with fp32 weights")
-    model = model.cpu()
-    model.load_state_dict(state_dict, strict=False)
-
-    return model
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("checkpoint_dir",
-                        type=str,
-                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
-    parser.add_argument("output_dir",
-                        type=str,
-                        help="directory to the pytorch fp32 state_dict output files"
-                        "(e.g. path/checkpoint-12-output/)")
-    parser.add_argument(
-        "--max_shard_size",
-        type=str,
-        default="5GB",
-        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
-        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
-        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
-        "without CPU OOM issues.")
-    parser.add_argument(
-        "--safe_serialization",
-        default=False,
-        action='store_true',
-        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
-    parser.add_argument("-t",
-                        "--tag",
-                        type=str,
-                        default=None,
-                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
-    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
-    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
-    args = parser.parse_args()
-
-    debug = args.debug
-
-    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
-                                               args.output_dir,
-                                               max_shard_size=args.max_shard_size,
-                                               safe_serialization=args.safe_serialization,
-                                               tag=args.tag,
-                                               exclude_frozen_parameters=args.exclude_frozen_parameters)