Upload trained model from Colab
Browse files- config.json +40 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- trainer_state.json +314 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HypencoderDualEncoder"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"loss_kwargs": [
|
| 7 |
+
{
|
| 8 |
+
"use_in_batch_negatives": true
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"loss_type": [
|
| 12 |
+
"cross_entropy"
|
| 13 |
+
],
|
| 14 |
+
"pad_token_id": 0,
|
| 15 |
+
"passage_encoder_kwargs": {
|
| 16 |
+
"freeze_transformer": true,
|
| 17 |
+
"model_name_or_path": "cambridgeltl/SapBERT-from-PubMedBERT-fulltext",
|
| 18 |
+
"pooling_type": "cls"
|
| 19 |
+
},
|
| 20 |
+
"passage_encoder_type": "",
|
| 21 |
+
"query_encoder_kwargs": {
|
| 22 |
+
"base_encoder_output_dim": 768,
|
| 23 |
+
"converter_kwargs": {
|
| 24 |
+
"activation_type": "relu",
|
| 25 |
+
"do_residual_on_last": false,
|
| 26 |
+
"vector_dimensions": [
|
| 27 |
+
768,
|
| 28 |
+
768,
|
| 29 |
+
768,
|
| 30 |
+
1
|
| 31 |
+
]
|
| 32 |
+
},
|
| 33 |
+
"embedding_representation": null,
|
| 34 |
+
"freeze_transformer": true,
|
| 35 |
+
"model_name_or_path": "cambridgeltl/SapBERT-from-PubMedBERT-fulltext"
|
| 36 |
+
},
|
| 37 |
+
"query_encoder_type": "",
|
| 38 |
+
"shared_encoder": true,
|
| 39 |
+
"transformers_version": "4.57.3"
|
| 40 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8b63aad8b69d71cca736d771d153ee0ffa47074003be4560688b032e031a51d
|
| 3 |
+
size 89817355
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18d38a9b98bb8ba18ec992dfe3bf94af462bd6cca6083031b7a288f08eee4ce0
|
| 3 |
+
size 482938527
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:835af8befd20a54142ef2464c5620705edb181d4ba49998782d667c2992ab7b1
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2a13aedfb10730f658c90eb03b45908f32db49971da0e67d91a64b15a963525
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 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": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 400,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.25,
|
| 14 |
+
"grad_norm": 108.46660614013672,
|
| 15 |
+
"learning_rate": 4.5e-06,
|
| 16 |
+
"loss": 6.8268,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5,
|
| 21 |
+
"grad_norm": 87.85498046875,
|
| 22 |
+
"learning_rate": 9.5e-06,
|
| 23 |
+
"loss": 6.2692,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.75,
|
| 28 |
+
"grad_norm": 77.33071899414062,
|
| 29 |
+
"learning_rate": 1.45e-05,
|
| 30 |
+
"loss": 5.4279,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"grad_norm": 84.33023071289062,
|
| 36 |
+
"learning_rate": 1.95e-05,
|
| 37 |
+
"loss": 4.4944,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.25,
|
| 42 |
+
"grad_norm": 73.86274719238281,
|
| 43 |
+
"learning_rate": 1.95e-05,
|
| 44 |
+
"loss": 3.2618,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.5,
|
| 49 |
+
"grad_norm": 59.88399124145508,
|
| 50 |
+
"learning_rate": 1.8944444444444447e-05,
|
| 51 |
+
"loss": 2.4952,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.75,
|
| 56 |
+
"grad_norm": 68.54973602294922,
|
| 57 |
+
"learning_rate": 1.838888888888889e-05,
|
| 58 |
+
"loss": 1.9448,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"grad_norm": 64.97733306884766,
|
| 64 |
+
"learning_rate": 1.7833333333333334e-05,
|
| 65 |
+
"loss": 1.6445,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.25,
|
| 70 |
+
"grad_norm": 58.61252212524414,
|
| 71 |
+
"learning_rate": 1.727777777777778e-05,
|
| 72 |
+
"loss": 1.1984,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.5,
|
| 77 |
+
"grad_norm": 39.56243133544922,
|
| 78 |
+
"learning_rate": 1.6722222222222225e-05,
|
| 79 |
+
"loss": 1.1865,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.75,
|
| 84 |
+
"grad_norm": 48.185123443603516,
|
| 85 |
+
"learning_rate": 1.616666666666667e-05,
|
| 86 |
+
"loss": 1.0324,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.0,
|
| 91 |
+
"grad_norm": 49.13726043701172,
|
| 92 |
+
"learning_rate": 1.5611111111111113e-05,
|
| 93 |
+
"loss": 0.8747,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 3.25,
|
| 98 |
+
"grad_norm": 31.3487606048584,
|
| 99 |
+
"learning_rate": 1.5055555555555556e-05,
|
| 100 |
+
"loss": 0.7836,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.5,
|
| 105 |
+
"grad_norm": 43.31613540649414,
|
| 106 |
+
"learning_rate": 1.45e-05,
|
| 107 |
+
"loss": 0.729,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.75,
|
| 112 |
+
"grad_norm": 45.93892288208008,
|
| 113 |
+
"learning_rate": 1.3944444444444446e-05,
|
| 114 |
+
"loss": 0.7182,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 4.0,
|
| 119 |
+
"grad_norm": 65.34429931640625,
|
| 120 |
+
"learning_rate": 1.338888888888889e-05,
|
| 121 |
+
"loss": 0.6853,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.25,
|
| 126 |
+
"grad_norm": 40.68680191040039,
|
| 127 |
+
"learning_rate": 1.2833333333333335e-05,
|
| 128 |
+
"loss": 0.6082,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.5,
|
| 133 |
+
"grad_norm": 23.430301666259766,
|
| 134 |
+
"learning_rate": 1.227777777777778e-05,
|
| 135 |
+
"loss": 0.6027,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.75,
|
| 140 |
+
"grad_norm": 31.279895782470703,
|
| 141 |
+
"learning_rate": 1.1722222222222224e-05,
|
| 142 |
+
"loss": 0.5536,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 5.0,
|
| 147 |
+
"grad_norm": 40.851078033447266,
|
| 148 |
+
"learning_rate": 1.1166666666666668e-05,
|
| 149 |
+
"loss": 0.5974,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 5.25,
|
| 154 |
+
"grad_norm": 41.20182800292969,
|
| 155 |
+
"learning_rate": 1.0611111111111111e-05,
|
| 156 |
+
"loss": 0.4913,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 5.5,
|
| 161 |
+
"grad_norm": 44.764102935791016,
|
| 162 |
+
"learning_rate": 1.0055555555555557e-05,
|
| 163 |
+
"loss": 0.5283,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 5.75,
|
| 168 |
+
"grad_norm": 76.29002380371094,
|
| 169 |
+
"learning_rate": 9.5e-06,
|
| 170 |
+
"loss": 0.5435,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.0,
|
| 175 |
+
"grad_norm": 42.7576904296875,
|
| 176 |
+
"learning_rate": 8.944444444444446e-06,
|
| 177 |
+
"loss": 0.5126,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 6.25,
|
| 182 |
+
"grad_norm": 31.921890258789062,
|
| 183 |
+
"learning_rate": 8.38888888888889e-06,
|
| 184 |
+
"loss": 0.4732,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 6.5,
|
| 189 |
+
"grad_norm": 344.25213623046875,
|
| 190 |
+
"learning_rate": 7.833333333333333e-06,
|
| 191 |
+
"loss": 0.507,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 6.75,
|
| 196 |
+
"grad_norm": 39.58772659301758,
|
| 197 |
+
"learning_rate": 7.277777777777778e-06,
|
| 198 |
+
"loss": 0.4971,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 7.0,
|
| 203 |
+
"grad_norm": 32.24217987060547,
|
| 204 |
+
"learning_rate": 6.7222222222222235e-06,
|
| 205 |
+
"loss": 0.4867,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 7.25,
|
| 210 |
+
"grad_norm": 36.557579040527344,
|
| 211 |
+
"learning_rate": 6.166666666666667e-06,
|
| 212 |
+
"loss": 0.417,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 7.5,
|
| 217 |
+
"grad_norm": 32.9907341003418,
|
| 218 |
+
"learning_rate": 5.611111111111112e-06,
|
| 219 |
+
"loss": 0.4371,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 7.75,
|
| 224 |
+
"grad_norm": 48.47484588623047,
|
| 225 |
+
"learning_rate": 5.0555555555555555e-06,
|
| 226 |
+
"loss": 0.4747,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 8.0,
|
| 231 |
+
"grad_norm": 39.65238952636719,
|
| 232 |
+
"learning_rate": 4.5e-06,
|
| 233 |
+
"loss": 0.4309,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 8.25,
|
| 238 |
+
"grad_norm": 30.107986450195312,
|
| 239 |
+
"learning_rate": 3.944444444444445e-06,
|
| 240 |
+
"loss": 0.4543,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.5,
|
| 245 |
+
"grad_norm": 34.437103271484375,
|
| 246 |
+
"learning_rate": 3.3888888888888893e-06,
|
| 247 |
+
"loss": 0.4244,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.75,
|
| 252 |
+
"grad_norm": 43.94343566894531,
|
| 253 |
+
"learning_rate": 2.8333333333333335e-06,
|
| 254 |
+
"loss": 0.4722,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 9.0,
|
| 259 |
+
"grad_norm": 36.12664031982422,
|
| 260 |
+
"learning_rate": 2.277777777777778e-06,
|
| 261 |
+
"loss": 0.438,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 9.25,
|
| 266 |
+
"grad_norm": 43.92878341674805,
|
| 267 |
+
"learning_rate": 1.7222222222222224e-06,
|
| 268 |
+
"loss": 0.4211,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 9.5,
|
| 273 |
+
"grad_norm": 35.80113983154297,
|
| 274 |
+
"learning_rate": 1.1666666666666668e-06,
|
| 275 |
+
"loss": 0.419,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 9.75,
|
| 280 |
+
"grad_norm": 33.334144592285156,
|
| 281 |
+
"learning_rate": 6.111111111111112e-07,
|
| 282 |
+
"loss": 0.4148,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 10.0,
|
| 287 |
+
"grad_norm": 33.29014205932617,
|
| 288 |
+
"learning_rate": 5.555555555555556e-08,
|
| 289 |
+
"loss": 0.4525,
|
| 290 |
+
"step": 400
|
| 291 |
+
}
|
| 292 |
+
],
|
| 293 |
+
"logging_steps": 10,
|
| 294 |
+
"max_steps": 400,
|
| 295 |
+
"num_input_tokens_seen": 0,
|
| 296 |
+
"num_train_epochs": 10,
|
| 297 |
+
"save_steps": 2500,
|
| 298 |
+
"stateful_callbacks": {
|
| 299 |
+
"TrainerControl": {
|
| 300 |
+
"args": {
|
| 301 |
+
"should_epoch_stop": false,
|
| 302 |
+
"should_evaluate": false,
|
| 303 |
+
"should_log": false,
|
| 304 |
+
"should_save": true,
|
| 305 |
+
"should_training_stop": true
|
| 306 |
+
},
|
| 307 |
+
"attributes": {}
|
| 308 |
+
}
|
| 309 |
+
},
|
| 310 |
+
"total_flos": 0.0,
|
| 311 |
+
"train_batch_size": 64,
|
| 312 |
+
"trial_name": null,
|
| 313 |
+
"trial_params": null
|
| 314 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:400dd9ce29f949fbb1ff4072df2a57c250ffe06fd4f1f9fbd1192057b914f746
|
| 3 |
+
size 5905
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|