Commit ·
481e40c
1
Parent(s): c46bfce
first model version
Browse files- config.json +34 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +604 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "allenai/scibert_scivocab_uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"NerModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0,
|
| 21 |
+
"LABEL_1": 1,
|
| 22 |
+
"LABEL_2": 2,
|
| 23 |
+
"LABEL_3": 3
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-12,
|
| 26 |
+
"max_position_embeddings": 512,
|
| 27 |
+
"model_type": "bert",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"vocab_size": 31090
|
| 34 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b22e3a45b62776f88520839a79d412c03a9af2987feb9650fa7782d5cd414c43
|
| 3 |
+
size 935931429
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7720ce8051f3bb4818371c54d508126437cf9429be51f64b69e85af47d6b647b
|
| 3 |
+
size 467991679
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9f8d239deb3d530c21e4c2a74107a7685526048d9288f2a3552f0015175a80f
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "allenai/scibert_scivocab_uncased", "do_basic_tokenize": true, "never_split": null}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,604 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8643187872085794,
|
| 3 |
+
"best_model_checkpoint": "../out/bio/ner-scibert-qa4-querytype4-char-pattern3-subtext-dim50-new/checkpoints/checkpoint-29601",
|
| 4 |
+
"epoch": 39.0,
|
| 5 |
+
"global_step": 29601,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.6587615283267457,
|
| 12 |
+
"learning_rate": 9.97804128238911e-06,
|
| 13 |
+
"loss": 0.037110485076904294,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 0.011046583764255047,
|
| 19 |
+
"eval_micro_f1": 0.7884588313085232,
|
| 20 |
+
"step": 759
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.3175230566534915,
|
| 24 |
+
"learning_rate": 9.956082564778218e-06,
|
| 25 |
+
"loss": 0.01054325771331787,
|
| 26 |
+
"step": 1000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.9762845849802373,
|
| 30 |
+
"learning_rate": 9.934123847167326e-06,
|
| 31 |
+
"loss": 0.007474568367004395,
|
| 32 |
+
"step": 1500
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_loss": 0.010235792025923729,
|
| 37 |
+
"eval_micro_f1": 0.8130828840406419,
|
| 38 |
+
"step": 1518
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.635046113306983,
|
| 42 |
+
"learning_rate": 9.912165129556434e-06,
|
| 43 |
+
"loss": 0.004817815780639648,
|
| 44 |
+
"step": 2000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_loss": 0.010428558103740215,
|
| 49 |
+
"eval_micro_f1": 0.8344238970819677,
|
| 50 |
+
"step": 2277
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.2938076416337285,
|
| 54 |
+
"learning_rate": 9.890206411945543e-06,
|
| 55 |
+
"loss": 0.004297223091125488,
|
| 56 |
+
"step": 2500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.9525691699604746,
|
| 60 |
+
"learning_rate": 9.868247694334652e-06,
|
| 61 |
+
"loss": 0.00321596097946167,
|
| 62 |
+
"step": 3000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_loss": 0.011789126321673393,
|
| 67 |
+
"eval_micro_f1": 0.8403736228094328,
|
| 68 |
+
"step": 3036
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.61133069828722,
|
| 72 |
+
"learning_rate": 9.84628897672376e-06,
|
| 73 |
+
"loss": 0.00230128288269043,
|
| 74 |
+
"step": 3500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 5.0,
|
| 78 |
+
"eval_loss": 0.012464746832847595,
|
| 79 |
+
"eval_micro_f1": 0.837059846869405,
|
| 80 |
+
"step": 3795
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.270092226613966,
|
| 84 |
+
"learning_rate": 9.824330259112868e-06,
|
| 85 |
+
"loss": 0.0020059123039245608,
|
| 86 |
+
"step": 4000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.928853754940711,
|
| 90 |
+
"learning_rate": 9.802371541501977e-06,
|
| 91 |
+
"loss": 0.0016852006912231445,
|
| 92 |
+
"step": 4500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 6.0,
|
| 96 |
+
"eval_loss": 0.013810090720653534,
|
| 97 |
+
"eval_micro_f1": 0.8396595969605289,
|
| 98 |
+
"step": 4554
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.587615283267457,
|
| 102 |
+
"learning_rate": 9.780412823891085e-06,
|
| 103 |
+
"loss": 0.001301923632621765,
|
| 104 |
+
"step": 5000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"eval_loss": 0.01601485349237919,
|
| 109 |
+
"eval_micro_f1": 0.8524957931061408,
|
| 110 |
+
"step": 5313
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.246376811594203,
|
| 114 |
+
"learning_rate": 9.758454106280194e-06,
|
| 115 |
+
"loss": 0.0010347318649291991,
|
| 116 |
+
"step": 5500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.905138339920948,
|
| 120 |
+
"learning_rate": 9.736495388669303e-06,
|
| 121 |
+
"loss": 0.0009287782907485962,
|
| 122 |
+
"step": 6000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 8.0,
|
| 126 |
+
"eval_loss": 0.019377898424863815,
|
| 127 |
+
"eval_micro_f1": 0.8397115912912296,
|
| 128 |
+
"step": 6072
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.563899868247695,
|
| 132 |
+
"learning_rate": 9.714536671058412e-06,
|
| 133 |
+
"loss": 0.0007228772044181824,
|
| 134 |
+
"step": 6500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 9.0,
|
| 138 |
+
"eval_loss": 0.01860038936138153,
|
| 139 |
+
"eval_micro_f1": 0.8470322848517083,
|
| 140 |
+
"step": 6831
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 9.22266139657444,
|
| 144 |
+
"learning_rate": 9.692577953447519e-06,
|
| 145 |
+
"loss": 0.0006817178130149841,
|
| 146 |
+
"step": 7000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 9.881422924901186,
|
| 150 |
+
"learning_rate": 9.670619235836628e-06,
|
| 151 |
+
"loss": 0.000784088134765625,
|
| 152 |
+
"step": 7500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"eval_loss": 0.017025897279381752,
|
| 157 |
+
"eval_micro_f1": 0.8547868618338511,
|
| 158 |
+
"step": 7590
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.540184453227932,
|
| 162 |
+
"learning_rate": 9.648660518225737e-06,
|
| 163 |
+
"loss": 0.0006126079559326172,
|
| 164 |
+
"step": 8000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 11.0,
|
| 168 |
+
"eval_loss": 0.01750860922038555,
|
| 169 |
+
"eval_micro_f1": 0.8490513387855172,
|
| 170 |
+
"step": 8349
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 11.198945981554678,
|
| 174 |
+
"learning_rate": 9.626701800614845e-06,
|
| 175 |
+
"loss": 0.0005611885190010071,
|
| 176 |
+
"step": 8500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.857707509881424,
|
| 180 |
+
"learning_rate": 9.604743083003954e-06,
|
| 181 |
+
"loss": 0.0005836631059646607,
|
| 182 |
+
"step": 9000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 12.0,
|
| 186 |
+
"eval_loss": 0.017635338008403778,
|
| 187 |
+
"eval_micro_f1": 0.8532005684902128,
|
| 188 |
+
"step": 9108
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 12.516469038208168,
|
| 192 |
+
"learning_rate": 9.582784365393061e-06,
|
| 193 |
+
"loss": 0.0004462006688117981,
|
| 194 |
+
"step": 9500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 13.0,
|
| 198 |
+
"eval_loss": 0.01813138835132122,
|
| 199 |
+
"eval_micro_f1": 0.848467809452106,
|
| 200 |
+
"step": 9867
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 13.175230566534914,
|
| 204 |
+
"learning_rate": 9.56082564778217e-06,
|
| 205 |
+
"loss": 0.0004592849016189575,
|
| 206 |
+
"step": 10000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 13.83399209486166,
|
| 210 |
+
"learning_rate": 9.538866930171279e-06,
|
| 211 |
+
"loss": 0.00033676078915596006,
|
| 212 |
+
"step": 10500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 14.0,
|
| 216 |
+
"eval_loss": 0.018653256818652153,
|
| 217 |
+
"eval_micro_f1": 0.8516164681375102,
|
| 218 |
+
"step": 10626
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 14.492753623188406,
|
| 222 |
+
"learning_rate": 9.516908212560388e-06,
|
| 223 |
+
"loss": 0.0003650049865245819,
|
| 224 |
+
"step": 11000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 15.0,
|
| 228 |
+
"eval_loss": 0.019014721736311913,
|
| 229 |
+
"eval_micro_f1": 0.8508441462836741,
|
| 230 |
+
"step": 11385
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 15.151515151515152,
|
| 234 |
+
"learning_rate": 9.494949494949497e-06,
|
| 235 |
+
"loss": 0.00036732107400894165,
|
| 236 |
+
"step": 11500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 15.810276679841897,
|
| 240 |
+
"learning_rate": 9.472990777338604e-06,
|
| 241 |
+
"loss": 0.000251627117395401,
|
| 242 |
+
"step": 12000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 16.0,
|
| 246 |
+
"eval_loss": 0.019610272720456123,
|
| 247 |
+
"eval_micro_f1": 0.8487043739773622,
|
| 248 |
+
"step": 12144
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 16.469038208168644,
|
| 252 |
+
"learning_rate": 9.451032059727712e-06,
|
| 253 |
+
"loss": 0.0005120611190795898,
|
| 254 |
+
"step": 12500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 17.0,
|
| 258 |
+
"eval_loss": 0.018985049799084663,
|
| 259 |
+
"eval_micro_f1": 0.8462077662179299,
|
| 260 |
+
"step": 12903
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 17.12779973649539,
|
| 264 |
+
"learning_rate": 9.429073342116821e-06,
|
| 265 |
+
"loss": 0.00031096377968788146,
|
| 266 |
+
"step": 13000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 17.786561264822133,
|
| 270 |
+
"learning_rate": 9.40711462450593e-06,
|
| 271 |
+
"loss": 0.00019182461500167846,
|
| 272 |
+
"step": 13500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 18.0,
|
| 276 |
+
"eval_loss": 0.01964498870074749,
|
| 277 |
+
"eval_micro_f1": 0.8557531957198969,
|
| 278 |
+
"step": 13662
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 18.44532279314888,
|
| 282 |
+
"learning_rate": 9.385155906895039e-06,
|
| 283 |
+
"loss": 0.00024452657997608187,
|
| 284 |
+
"step": 14000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 19.0,
|
| 288 |
+
"eval_loss": 0.021180404350161552,
|
| 289 |
+
"eval_micro_f1": 0.8577108770917136,
|
| 290 |
+
"step": 14421
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 19.104084321475625,
|
| 294 |
+
"learning_rate": 9.363197189284146e-06,
|
| 295 |
+
"loss": 0.0002680089771747589,
|
| 296 |
+
"step": 14500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 19.76284584980237,
|
| 300 |
+
"learning_rate": 9.341238471673255e-06,
|
| 301 |
+
"loss": 0.0002937615513801575,
|
| 302 |
+
"step": 15000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 20.0,
|
| 306 |
+
"eval_loss": 0.020903080701828003,
|
| 307 |
+
"eval_micro_f1": 0.8581900192349345,
|
| 308 |
+
"step": 15180
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 20.421607378129117,
|
| 312 |
+
"learning_rate": 9.319279754062364e-06,
|
| 313 |
+
"loss": 0.00018737909197807313,
|
| 314 |
+
"step": 15500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 21.0,
|
| 318 |
+
"eval_loss": 0.021407702937722206,
|
| 319 |
+
"eval_micro_f1": 0.8597197164416296,
|
| 320 |
+
"step": 15939
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 21.080368906455863,
|
| 324 |
+
"learning_rate": 9.297321036451472e-06,
|
| 325 |
+
"loss": 0.0001290062665939331,
|
| 326 |
+
"step": 16000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 21.73913043478261,
|
| 330 |
+
"learning_rate": 9.275362318840581e-06,
|
| 331 |
+
"loss": 0.0001307707875967026,
|
| 332 |
+
"step": 16500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 22.0,
|
| 336 |
+
"eval_loss": 0.02195800468325615,
|
| 337 |
+
"eval_micro_f1": 0.8524727572533776,
|
| 338 |
+
"step": 16698
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 22.397891963109355,
|
| 342 |
+
"learning_rate": 9.253403601229688e-06,
|
| 343 |
+
"loss": 0.00023717455565929412,
|
| 344 |
+
"step": 17000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 23.0,
|
| 348 |
+
"eval_loss": 0.022745156660676003,
|
| 349 |
+
"eval_micro_f1": 0.8558443397926969,
|
| 350 |
+
"step": 17457
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 23.0566534914361,
|
| 354 |
+
"learning_rate": 9.231444883618797e-06,
|
| 355 |
+
"loss": 0.00017341481149196625,
|
| 356 |
+
"step": 17500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 23.715415019762847,
|
| 360 |
+
"learning_rate": 9.209486166007906e-06,
|
| 361 |
+
"loss": 0.00025756615400314333,
|
| 362 |
+
"step": 18000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 24.0,
|
| 366 |
+
"eval_loss": 0.02122940495610237,
|
| 367 |
+
"eval_micro_f1": 0.8519865691696683,
|
| 368 |
+
"step": 18216
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 24.37417654808959,
|
| 372 |
+
"learning_rate": 9.187527448397015e-06,
|
| 373 |
+
"loss": 0.0001464369297027588,
|
| 374 |
+
"step": 18500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 25.0,
|
| 378 |
+
"eval_loss": 0.02185015007853508,
|
| 379 |
+
"eval_micro_f1": 0.8496085697511283,
|
| 380 |
+
"step": 18975
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 25.032938076416336,
|
| 384 |
+
"learning_rate": 9.165568730786123e-06,
|
| 385 |
+
"loss": 0.0001510075181722641,
|
| 386 |
+
"step": 19000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 25.691699604743082,
|
| 390 |
+
"learning_rate": 9.143610013175232e-06,
|
| 391 |
+
"loss": 0.00016037344932556152,
|
| 392 |
+
"step": 19500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 26.0,
|
| 396 |
+
"eval_loss": 0.022148123010993004,
|
| 397 |
+
"eval_micro_f1": 0.8574194435600588,
|
| 398 |
+
"step": 19734
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 26.350461133069828,
|
| 402 |
+
"learning_rate": 9.12165129556434e-06,
|
| 403 |
+
"loss": 0.000233057901263237,
|
| 404 |
+
"step": 20000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 27.0,
|
| 408 |
+
"eval_loss": 0.022844456136226654,
|
| 409 |
+
"eval_micro_f1": 0.8623087616694572,
|
| 410 |
+
"step": 20493
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 27.009222661396574,
|
| 414 |
+
"learning_rate": 9.099692577953448e-06,
|
| 415 |
+
"loss": 0.00011244810372591019,
|
| 416 |
+
"step": 20500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 27.66798418972332,
|
| 420 |
+
"learning_rate": 9.077733860342557e-06,
|
| 421 |
+
"loss": 0.00013506200909614563,
|
| 422 |
+
"step": 21000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 28.0,
|
| 426 |
+
"eval_loss": 0.022953923791646957,
|
| 427 |
+
"eval_micro_f1": 0.8545429086416555,
|
| 428 |
+
"step": 21252
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 28.326745718050066,
|
| 432 |
+
"learning_rate": 9.055775142731666e-06,
|
| 433 |
+
"loss": 0.00026963132619857785,
|
| 434 |
+
"step": 21500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 28.985507246376812,
|
| 438 |
+
"learning_rate": 9.033816425120775e-06,
|
| 439 |
+
"loss": 0.00014831958711147307,
|
| 440 |
+
"step": 22000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 29.0,
|
| 444 |
+
"eval_loss": 0.023488974198698997,
|
| 445 |
+
"eval_micro_f1": 0.8477237043668356,
|
| 446 |
+
"step": 22011
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 29.64426877470356,
|
| 450 |
+
"learning_rate": 9.011857707509882e-06,
|
| 451 |
+
"loss": 0.0001335151344537735,
|
| 452 |
+
"step": 22500
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 30.0,
|
| 456 |
+
"eval_loss": 0.019763289019465446,
|
| 457 |
+
"eval_micro_f1": 0.8529330757872978,
|
| 458 |
+
"step": 22770
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 30.303030303030305,
|
| 462 |
+
"learning_rate": 8.98989898989899e-06,
|
| 463 |
+
"loss": 0.00023964977264404297,
|
| 464 |
+
"step": 23000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 30.961791831357047,
|
| 468 |
+
"learning_rate": 8.9679402722881e-06,
|
| 469 |
+
"loss": 0.00018574166297912598,
|
| 470 |
+
"step": 23500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 31.0,
|
| 474 |
+
"eval_loss": 0.02139969728887081,
|
| 475 |
+
"eval_micro_f1": 0.8617217410970216,
|
| 476 |
+
"step": 23529
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 31.620553359683793,
|
| 480 |
+
"learning_rate": 8.945981554677208e-06,
|
| 481 |
+
"loss": 7.593867182731629e-05,
|
| 482 |
+
"step": 24000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 32.0,
|
| 486 |
+
"eval_loss": 0.027622610330581665,
|
| 487 |
+
"eval_micro_f1": 0.8440183166154224,
|
| 488 |
+
"step": 24288
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 32.27931488801054,
|
| 492 |
+
"learning_rate": 8.924022837066317e-06,
|
| 493 |
+
"loss": 6.25964105129242e-05,
|
| 494 |
+
"step": 24500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 32.93807641633729,
|
| 498 |
+
"learning_rate": 8.902064119455424e-06,
|
| 499 |
+
"loss": 9.8123200237751e-05,
|
| 500 |
+
"step": 25000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 33.0,
|
| 504 |
+
"eval_loss": 0.025167174637317657,
|
| 505 |
+
"eval_micro_f1": 0.8521543222259202,
|
| 506 |
+
"step": 25047
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 33.59683794466403,
|
| 510 |
+
"learning_rate": 8.880105401844533e-06,
|
| 511 |
+
"loss": 0.00018300886452198028,
|
| 512 |
+
"step": 25500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 34.0,
|
| 516 |
+
"eval_loss": 0.023568451404571533,
|
| 517 |
+
"eval_micro_f1": 0.851057944458968,
|
| 518 |
+
"step": 25806
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 34.25559947299078,
|
| 522 |
+
"learning_rate": 8.858146684233642e-06,
|
| 523 |
+
"loss": 0.00012137698382139205,
|
| 524 |
+
"step": 26000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 34.91436100131752,
|
| 528 |
+
"learning_rate": 8.83618796662275e-06,
|
| 529 |
+
"loss": 0.00019975709915161132,
|
| 530 |
+
"step": 26500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 35.0,
|
| 534 |
+
"eval_loss": 0.022091668099164963,
|
| 535 |
+
"eval_micro_f1": 0.8548590655495029,
|
| 536 |
+
"step": 26565
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 35.573122529644266,
|
| 540 |
+
"learning_rate": 8.81422924901186e-06,
|
| 541 |
+
"loss": 0.00012561745941638947,
|
| 542 |
+
"step": 27000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 36.0,
|
| 546 |
+
"eval_loss": 0.02340899035334587,
|
| 547 |
+
"eval_micro_f1": 0.8555708385644274,
|
| 548 |
+
"step": 27324
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 36.231884057971016,
|
| 552 |
+
"learning_rate": 8.792270531400966e-06,
|
| 553 |
+
"loss": 0.000144828662276268,
|
| 554 |
+
"step": 27500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 36.89064558629776,
|
| 558 |
+
"learning_rate": 8.770311813790075e-06,
|
| 559 |
+
"loss": 7.70660936832428e-05,
|
| 560 |
+
"step": 28000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 37.0,
|
| 564 |
+
"eval_loss": 0.022807367146015167,
|
| 565 |
+
"eval_micro_f1": 0.8562674089705398,
|
| 566 |
+
"step": 28083
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 37.54940711462451,
|
| 570 |
+
"learning_rate": 8.748353096179184e-06,
|
| 571 |
+
"loss": 8.054495602846145e-05,
|
| 572 |
+
"step": 28500
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 38.0,
|
| 576 |
+
"eval_loss": 0.021150145679712296,
|
| 577 |
+
"eval_micro_f1": 0.8554654733605974,
|
| 578 |
+
"step": 28842
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 38.20816864295125,
|
| 582 |
+
"learning_rate": 8.726394378568293e-06,
|
| 583 |
+
"loss": 0.00011904157698154449,
|
| 584 |
+
"step": 29000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 38.866930171278,
|
| 588 |
+
"learning_rate": 8.704435660957402e-06,
|
| 589 |
+
"loss": 0.00016540713608264923,
|
| 590 |
+
"step": 29500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 39.0,
|
| 594 |
+
"eval_loss": 0.021935490891337395,
|
| 595 |
+
"eval_micro_f1": 0.8643187872085794,
|
| 596 |
+
"step": 29601
|
| 597 |
+
}
|
| 598 |
+
],
|
| 599 |
+
"max_steps": 227700,
|
| 600 |
+
"num_train_epochs": 300,
|
| 601 |
+
"total_flos": 125343142215754368,
|
| 602 |
+
"trial_name": null,
|
| 603 |
+
"trial_params": null
|
| 604 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dccc28ee3c7a41bbda57a8c3e419ebf09c5290923d201e40953a5f443069c5a0
|
| 3 |
+
size 2031
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|