Upload 10 files
Browse files- config.json +25 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +44 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- trainer_state.json +349 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 2,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 3,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 128,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 512,
|
| 15 |
+
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"model_type": "bert",
|
| 18 |
+
"num_attention_heads": 2,
|
| 19 |
+
"num_hidden_layers": 2,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"transformers_version": "5.0.0.dev0",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": false,
|
| 24 |
+
"vocab_size": 48000
|
| 25 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7a4ab5c612128a7524818797f72377a297776cb3302443c45bafca858308748
|
| 3 |
+
size 26690208
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a049740d0cb30c75d9d73ae2de00b6e1fa19db334a474f51970d11d6a0d1f210
|
| 3 |
+
size 53406202
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:192e4f48de44df0334782c2702af7748584e1fdfd2f007d10dfc04de90259bd7
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4d0153825bdf3e3e06de8250593f5678b61d96f9a6ce0b46efd9f2d8a5d1363
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"mask_token": {
|
| 17 |
+
"content": "<mask>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "<pad>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"sep_token": {
|
| 31 |
+
"content": "</s>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"unk_token": {
|
| 38 |
+
"content": "<unk>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
}
|
| 44 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "</s>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"eos_token": "</s>",
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"max_length": null,
|
| 50 |
+
"model_input_names": [
|
| 51 |
+
"input_ids",
|
| 52 |
+
"attention_mask"
|
| 53 |
+
],
|
| 54 |
+
"model_max_length": 512,
|
| 55 |
+
"pad_to_multiple_of": null,
|
| 56 |
+
"pad_token": "<pad>",
|
| 57 |
+
"pad_token_type_id": 0,
|
| 58 |
+
"padding_side": "right",
|
| 59 |
+
"sep_token": "</s>",
|
| 60 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 61 |
+
"truncation_side": "right",
|
| 62 |
+
"unk_token": "<unk>"
|
| 63 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,349 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8294930875576036,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 22500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.018433179723502304,
|
| 14 |
+
"grad_norm": 2.7722034454345703,
|
| 15 |
+
"learning_rate": 4.969339477726575e-05,
|
| 16 |
+
"loss": 5.2387,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03686635944700461,
|
| 21 |
+
"grad_norm": 3.414055347442627,
|
| 22 |
+
"learning_rate": 4.938617511520738e-05,
|
| 23 |
+
"loss": 4.3585,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.055299539170506916,
|
| 28 |
+
"grad_norm": 2.91390061378479,
|
| 29 |
+
"learning_rate": 4.9078955453149006e-05,
|
| 30 |
+
"loss": 4.1208,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07373271889400922,
|
| 35 |
+
"grad_norm": 2.3701863288879395,
|
| 36 |
+
"learning_rate": 4.877173579109063e-05,
|
| 37 |
+
"loss": 3.9869,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09216589861751152,
|
| 42 |
+
"grad_norm": 2.441763162612915,
|
| 43 |
+
"learning_rate": 4.846451612903226e-05,
|
| 44 |
+
"loss": 3.8932,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11059907834101383,
|
| 49 |
+
"grad_norm": 2.8250324726104736,
|
| 50 |
+
"learning_rate": 4.815729646697389e-05,
|
| 51 |
+
"loss": 3.8175,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12903225806451613,
|
| 56 |
+
"grad_norm": 2.9016897678375244,
|
| 57 |
+
"learning_rate": 4.7850076804915513e-05,
|
| 58 |
+
"loss": 3.7022,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14746543778801843,
|
| 63 |
+
"grad_norm": 2.2199313640594482,
|
| 64 |
+
"learning_rate": 4.7542857142857146e-05,
|
| 65 |
+
"loss": 3.6935,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.16589861751152074,
|
| 70 |
+
"grad_norm": 2.4812119007110596,
|
| 71 |
+
"learning_rate": 4.723563748079877e-05,
|
| 72 |
+
"loss": 3.6745,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.18433179723502305,
|
| 77 |
+
"grad_norm": 2.6783430576324463,
|
| 78 |
+
"learning_rate": 4.69284178187404e-05,
|
| 79 |
+
"loss": 3.5583,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.20276497695852536,
|
| 84 |
+
"grad_norm": 2.524801254272461,
|
| 85 |
+
"learning_rate": 4.662119815668203e-05,
|
| 86 |
+
"loss": 3.5784,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22119815668202766,
|
| 91 |
+
"grad_norm": 2.821859836578369,
|
| 92 |
+
"learning_rate": 4.6313978494623653e-05,
|
| 93 |
+
"loss": 3.5481,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.23963133640552994,
|
| 98 |
+
"grad_norm": 2.7526915073394775,
|
| 99 |
+
"learning_rate": 4.6006758832565286e-05,
|
| 100 |
+
"loss": 3.5201,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.25806451612903225,
|
| 105 |
+
"grad_norm": 3.1275274753570557,
|
| 106 |
+
"learning_rate": 4.569953917050692e-05,
|
| 107 |
+
"loss": 3.4428,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2764976958525346,
|
| 112 |
+
"grad_norm": 2.565107583999634,
|
| 113 |
+
"learning_rate": 4.539231950844854e-05,
|
| 114 |
+
"loss": 3.4385,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.29493087557603687,
|
| 119 |
+
"grad_norm": 2.554239511489868,
|
| 120 |
+
"learning_rate": 4.5085099846390175e-05,
|
| 121 |
+
"loss": 3.4189,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.31336405529953915,
|
| 126 |
+
"grad_norm": 2.702221155166626,
|
| 127 |
+
"learning_rate": 4.47778801843318e-05,
|
| 128 |
+
"loss": 3.413,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3317972350230415,
|
| 133 |
+
"grad_norm": 2.413268804550171,
|
| 134 |
+
"learning_rate": 4.4470660522273425e-05,
|
| 135 |
+
"loss": 3.3684,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.35023041474654376,
|
| 140 |
+
"grad_norm": 2.424586296081543,
|
| 141 |
+
"learning_rate": 4.416344086021506e-05,
|
| 142 |
+
"loss": 3.3702,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3686635944700461,
|
| 147 |
+
"grad_norm": 2.7243025302886963,
|
| 148 |
+
"learning_rate": 4.385622119815668e-05,
|
| 149 |
+
"loss": 3.2839,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3870967741935484,
|
| 154 |
+
"grad_norm": 2.2430036067962646,
|
| 155 |
+
"learning_rate": 4.354900153609831e-05,
|
| 156 |
+
"loss": 3.3245,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4055299539170507,
|
| 161 |
+
"grad_norm": 2.5448081493377686,
|
| 162 |
+
"learning_rate": 4.324178187403994e-05,
|
| 163 |
+
"loss": 3.2824,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.423963133640553,
|
| 168 |
+
"grad_norm": 2.6062798500061035,
|
| 169 |
+
"learning_rate": 4.293456221198157e-05,
|
| 170 |
+
"loss": 3.2928,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.4423963133640553,
|
| 175 |
+
"grad_norm": 2.51362681388855,
|
| 176 |
+
"learning_rate": 4.26273425499232e-05,
|
| 177 |
+
"loss": 3.2731,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.4608294930875576,
|
| 182 |
+
"grad_norm": 2.2453083992004395,
|
| 183 |
+
"learning_rate": 4.232012288786483e-05,
|
| 184 |
+
"loss": 3.2556,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.4792626728110599,
|
| 189 |
+
"grad_norm": 2.3285653591156006,
|
| 190 |
+
"learning_rate": 4.2012903225806455e-05,
|
| 191 |
+
"loss": 3.2397,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4976958525345622,
|
| 196 |
+
"grad_norm": 2.4322783946990967,
|
| 197 |
+
"learning_rate": 4.170568356374808e-05,
|
| 198 |
+
"loss": 3.2348,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5161290322580645,
|
| 203 |
+
"grad_norm": 2.180086374282837,
|
| 204 |
+
"learning_rate": 4.139846390168971e-05,
|
| 205 |
+
"loss": 3.2059,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5345622119815668,
|
| 210 |
+
"grad_norm": 2.293834686279297,
|
| 211 |
+
"learning_rate": 4.109124423963134e-05,
|
| 212 |
+
"loss": 3.2066,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5529953917050692,
|
| 217 |
+
"grad_norm": 2.4870762825012207,
|
| 218 |
+
"learning_rate": 4.078402457757296e-05,
|
| 219 |
+
"loss": 3.1875,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5714285714285714,
|
| 224 |
+
"grad_norm": 2.4512012004852295,
|
| 225 |
+
"learning_rate": 4.0476804915514595e-05,
|
| 226 |
+
"loss": 3.1519,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5898617511520737,
|
| 231 |
+
"grad_norm": 3.0072903633117676,
|
| 232 |
+
"learning_rate": 4.016958525345622e-05,
|
| 233 |
+
"loss": 3.194,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6082949308755761,
|
| 238 |
+
"grad_norm": 2.5981032848358154,
|
| 239 |
+
"learning_rate": 3.986236559139785e-05,
|
| 240 |
+
"loss": 3.1575,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6267281105990783,
|
| 245 |
+
"grad_norm": 2.6231231689453125,
|
| 246 |
+
"learning_rate": 3.9555145929339484e-05,
|
| 247 |
+
"loss": 3.1602,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6451612903225806,
|
| 252 |
+
"grad_norm": 2.6723060607910156,
|
| 253 |
+
"learning_rate": 3.924792626728111e-05,
|
| 254 |
+
"loss": 3.1713,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.663594470046083,
|
| 259 |
+
"grad_norm": 2.222766876220703,
|
| 260 |
+
"learning_rate": 3.8940706605222735e-05,
|
| 261 |
+
"loss": 3.1258,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6820276497695853,
|
| 266 |
+
"grad_norm": 2.3424344062805176,
|
| 267 |
+
"learning_rate": 3.863348694316437e-05,
|
| 268 |
+
"loss": 3.1091,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.7004608294930875,
|
| 273 |
+
"grad_norm": 2.849412679672241,
|
| 274 |
+
"learning_rate": 3.832626728110599e-05,
|
| 275 |
+
"loss": 3.1179,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7188940092165899,
|
| 280 |
+
"grad_norm": 2.475759267807007,
|
| 281 |
+
"learning_rate": 3.8019047619047624e-05,
|
| 282 |
+
"loss": 3.1026,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7373271889400922,
|
| 287 |
+
"grad_norm": 2.421753168106079,
|
| 288 |
+
"learning_rate": 3.771182795698925e-05,
|
| 289 |
+
"loss": 3.0828,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7557603686635944,
|
| 294 |
+
"grad_norm": 2.5588021278381348,
|
| 295 |
+
"learning_rate": 3.7404608294930875e-05,
|
| 296 |
+
"loss": 3.1001,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7741935483870968,
|
| 301 |
+
"grad_norm": 2.294607400894165,
|
| 302 |
+
"learning_rate": 3.709738863287251e-05,
|
| 303 |
+
"loss": 3.0791,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.7926267281105991,
|
| 308 |
+
"grad_norm": 2.657045841217041,
|
| 309 |
+
"learning_rate": 3.679016897081413e-05,
|
| 310 |
+
"loss": 3.0481,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8110599078341014,
|
| 315 |
+
"grad_norm": 2.426490068435669,
|
| 316 |
+
"learning_rate": 3.648294930875576e-05,
|
| 317 |
+
"loss": 3.0674,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8294930875576036,
|
| 322 |
+
"grad_norm": 2.5447800159454346,
|
| 323 |
+
"learning_rate": 3.617572964669739e-05,
|
| 324 |
+
"loss": 3.075,
|
| 325 |
+
"step": 22500
|
| 326 |
+
}
|
| 327 |
+
],
|
| 328 |
+
"logging_steps": 500,
|
| 329 |
+
"max_steps": 81375,
|
| 330 |
+
"num_input_tokens_seen": 0,
|
| 331 |
+
"num_train_epochs": 3,
|
| 332 |
+
"save_steps": 500,
|
| 333 |
+
"stateful_callbacks": {
|
| 334 |
+
"TrainerControl": {
|
| 335 |
+
"args": {
|
| 336 |
+
"should_epoch_stop": false,
|
| 337 |
+
"should_evaluate": false,
|
| 338 |
+
"should_log": false,
|
| 339 |
+
"should_save": true,
|
| 340 |
+
"should_training_stop": false
|
| 341 |
+
},
|
| 342 |
+
"attributes": {}
|
| 343 |
+
}
|
| 344 |
+
},
|
| 345 |
+
"total_flos": 1020914565120000.0,
|
| 346 |
+
"train_batch_size": 32,
|
| 347 |
+
"trial_name": null,
|
| 348 |
+
"trial_params": null
|
| 349 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d31e29813f8bde325b13382dbcc0ef127eb88f1dd6ebaa68705b96afe506de58
|
| 3 |
+
size 4728
|