Cameron Clarke
commited on
Commit
•
e023dd2
1
Parent(s):
ac53f45
add model files
Browse files- config.json +42 -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 +542 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 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 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"LABEL_0": 0,
|
| 24 |
+
"LABEL_1": 1,
|
| 25 |
+
"LABEL_2": 2,
|
| 26 |
+
"LABEL_3": 3,
|
| 27 |
+
"LABEL_4": 4,
|
| 28 |
+
"LABEL_5": 5,
|
| 29 |
+
"LABEL_6": 6
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"max_position_embeddings": 512,
|
| 33 |
+
"model_type": "bert",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_layers": 12,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"transformers_version": "4.5.0",
|
| 39 |
+
"type_vocab_size": 2,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 28996
|
| 42 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97b03455103534777c0cb03e83721015125e0108a96e6dd0f259f3d5a78ae6b5
|
| 3 |
+
size 866651345
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00b4e62246c4f8235a4dc00608b6a6d2ccac6242d0fe2d17d6af9152e43a58ad
|
| 3 |
+
size 433351945
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5330e0d5a0bc33ac5bd737fbb55975e3ec1698dd0f1a945a6906c8f3140c1229
|
| 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": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,542 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.857947587558168,
|
| 3 |
+
"best_model_checkpoint": "/scratch/ccc779/sbic_targetcategory_model/checkpoint-21247",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 42494,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 1.2038209038485956e-05,
|
| 13 |
+
"loss": 1.2666,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 1.1894876550053253e-05,
|
| 19 |
+
"loss": 1.0291,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 1.1751544061620547e-05,
|
| 25 |
+
"loss": 0.9169,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.09,
|
| 30 |
+
"learning_rate": 1.1608211573187843e-05,
|
| 31 |
+
"loss": 0.8776,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 1.1464879084755138e-05,
|
| 37 |
+
"loss": 0.8662,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.14,
|
| 42 |
+
"learning_rate": 1.1321546596322436e-05,
|
| 43 |
+
"loss": 0.9252,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.16,
|
| 48 |
+
"learning_rate": 1.1178214107889731e-05,
|
| 49 |
+
"loss": 0.7458,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19,
|
| 54 |
+
"learning_rate": 1.1034881619457027e-05,
|
| 55 |
+
"loss": 0.8532,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.21,
|
| 60 |
+
"learning_rate": 1.0891549131024323e-05,
|
| 61 |
+
"loss": 0.8326,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.24,
|
| 66 |
+
"learning_rate": 1.0748216642591619e-05,
|
| 67 |
+
"loss": 0.7976,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.26,
|
| 72 |
+
"learning_rate": 1.0604884154158914e-05,
|
| 73 |
+
"loss": 0.7793,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.28,
|
| 78 |
+
"learning_rate": 1.046155166572621e-05,
|
| 79 |
+
"loss": 0.7752,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.31,
|
| 84 |
+
"learning_rate": 1.0318219177293506e-05,
|
| 85 |
+
"loss": 0.7105,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.33,
|
| 90 |
+
"learning_rate": 1.0174886688860803e-05,
|
| 91 |
+
"loss": 0.8289,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.35,
|
| 96 |
+
"learning_rate": 1.0031554200428099e-05,
|
| 97 |
+
"loss": 0.8342,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.38,
|
| 102 |
+
"learning_rate": 9.888221711995394e-06,
|
| 103 |
+
"loss": 0.8159,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.4,
|
| 108 |
+
"learning_rate": 9.744889223562688e-06,
|
| 109 |
+
"loss": 0.7468,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.42,
|
| 114 |
+
"learning_rate": 9.601556735129986e-06,
|
| 115 |
+
"loss": 0.7368,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.45,
|
| 120 |
+
"learning_rate": 9.458224246697281e-06,
|
| 121 |
+
"loss": 0.7052,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.47,
|
| 126 |
+
"learning_rate": 9.314891758264577e-06,
|
| 127 |
+
"loss": 0.737,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.49,
|
| 132 |
+
"learning_rate": 9.171559269831873e-06,
|
| 133 |
+
"loss": 0.7199,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.52,
|
| 138 |
+
"learning_rate": 9.02822678139917e-06,
|
| 139 |
+
"loss": 0.7493,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.54,
|
| 144 |
+
"learning_rate": 8.884894292966464e-06,
|
| 145 |
+
"loss": 0.6692,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.56,
|
| 150 |
+
"learning_rate": 8.74156180453376e-06,
|
| 151 |
+
"loss": 0.7689,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.59,
|
| 156 |
+
"learning_rate": 8.598229316101055e-06,
|
| 157 |
+
"loss": 0.6516,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.61,
|
| 162 |
+
"learning_rate": 8.454896827668353e-06,
|
| 163 |
+
"loss": 0.6827,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.64,
|
| 168 |
+
"learning_rate": 8.311564339235648e-06,
|
| 169 |
+
"loss": 0.746,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.66,
|
| 174 |
+
"learning_rate": 8.168231850802944e-06,
|
| 175 |
+
"loss": 0.5904,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.68,
|
| 180 |
+
"learning_rate": 8.02489936237024e-06,
|
| 181 |
+
"loss": 0.8199,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.71,
|
| 186 |
+
"learning_rate": 7.881566873937536e-06,
|
| 187 |
+
"loss": 0.6873,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.73,
|
| 192 |
+
"learning_rate": 7.738234385504831e-06,
|
| 193 |
+
"loss": 0.6247,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.75,
|
| 198 |
+
"learning_rate": 7.594901897072127e-06,
|
| 199 |
+
"loss": 0.7357,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.78,
|
| 204 |
+
"learning_rate": 7.4515694086394226e-06,
|
| 205 |
+
"loss": 0.6922,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.8,
|
| 210 |
+
"learning_rate": 7.30823692020672e-06,
|
| 211 |
+
"loss": 0.7077,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.82,
|
| 216 |
+
"learning_rate": 7.164904431774015e-06,
|
| 217 |
+
"loss": 0.6723,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.85,
|
| 222 |
+
"learning_rate": 7.0215719433413105e-06,
|
| 223 |
+
"loss": 0.7335,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.87,
|
| 228 |
+
"learning_rate": 6.878239454908606e-06,
|
| 229 |
+
"loss": 0.6565,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.89,
|
| 234 |
+
"learning_rate": 6.734906966475903e-06,
|
| 235 |
+
"loss": 0.7308,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.92,
|
| 240 |
+
"learning_rate": 6.591574478043198e-06,
|
| 241 |
+
"loss": 0.5847,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.94,
|
| 246 |
+
"learning_rate": 6.448241989610494e-06,
|
| 247 |
+
"loss": 0.6708,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.96,
|
| 252 |
+
"learning_rate": 6.30490950117779e-06,
|
| 253 |
+
"loss": 0.6919,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.99,
|
| 258 |
+
"learning_rate": 6.161577012745086e-06,
|
| 259 |
+
"loss": 0.6529,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.0,
|
| 264 |
+
"eval_accuracy": 0.857947587558168,
|
| 265 |
+
"eval_f1": 0.857947587558168,
|
| 266 |
+
"eval_loss": 0.7013186812400818,
|
| 267 |
+
"eval_precision": 0.857947587558168,
|
| 268 |
+
"eval_recall": 0.857947587558168,
|
| 269 |
+
"eval_runtime": 34.2359,
|
| 270 |
+
"eval_samples_per_second": 238.522,
|
| 271 |
+
"step": 21247
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.01,
|
| 275 |
+
"learning_rate": 6.018244524312382e-06,
|
| 276 |
+
"loss": 0.5928,
|
| 277 |
+
"step": 21500
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.04,
|
| 281 |
+
"learning_rate": 5.874912035879678e-06,
|
| 282 |
+
"loss": 0.5018,
|
| 283 |
+
"step": 22000
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.06,
|
| 287 |
+
"learning_rate": 5.731579547446973e-06,
|
| 288 |
+
"loss": 0.5071,
|
| 289 |
+
"step": 22500
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.08,
|
| 293 |
+
"learning_rate": 5.588247059014269e-06,
|
| 294 |
+
"loss": 0.5208,
|
| 295 |
+
"step": 23000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.11,
|
| 299 |
+
"learning_rate": 5.4449145705815655e-06,
|
| 300 |
+
"loss": 0.5747,
|
| 301 |
+
"step": 23500
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.13,
|
| 305 |
+
"learning_rate": 5.301582082148861e-06,
|
| 306 |
+
"loss": 0.4878,
|
| 307 |
+
"step": 24000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.15,
|
| 311 |
+
"learning_rate": 5.158249593716157e-06,
|
| 312 |
+
"loss": 0.5553,
|
| 313 |
+
"step": 24500
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.18,
|
| 317 |
+
"learning_rate": 5.0149171052834525e-06,
|
| 318 |
+
"loss": 0.5383,
|
| 319 |
+
"step": 25000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.2,
|
| 323 |
+
"learning_rate": 4.871584616850749e-06,
|
| 324 |
+
"loss": 0.4743,
|
| 325 |
+
"step": 25500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.22,
|
| 329 |
+
"learning_rate": 4.728252128418044e-06,
|
| 330 |
+
"loss": 0.4293,
|
| 331 |
+
"step": 26000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.25,
|
| 335 |
+
"learning_rate": 4.58491963998534e-06,
|
| 336 |
+
"loss": 0.6425,
|
| 337 |
+
"step": 26500
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.27,
|
| 341 |
+
"learning_rate": 4.441587151552636e-06,
|
| 342 |
+
"loss": 0.5248,
|
| 343 |
+
"step": 27000
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.29,
|
| 347 |
+
"learning_rate": 4.298254663119932e-06,
|
| 348 |
+
"loss": 0.5099,
|
| 349 |
+
"step": 27500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.32,
|
| 353 |
+
"learning_rate": 4.1549221746872275e-06,
|
| 354 |
+
"loss": 0.5134,
|
| 355 |
+
"step": 28000
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.34,
|
| 359 |
+
"learning_rate": 4.011589686254524e-06,
|
| 360 |
+
"loss": 0.4548,
|
| 361 |
+
"step": 28500
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.36,
|
| 365 |
+
"learning_rate": 3.86825719782182e-06,
|
| 366 |
+
"loss": 0.5803,
|
| 367 |
+
"step": 29000
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.39,
|
| 371 |
+
"learning_rate": 3.7249247093891154e-06,
|
| 372 |
+
"loss": 0.547,
|
| 373 |
+
"step": 29500
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.41,
|
| 377 |
+
"learning_rate": 3.581592220956411e-06,
|
| 378 |
+
"loss": 0.4615,
|
| 379 |
+
"step": 30000
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.44,
|
| 383 |
+
"learning_rate": 3.438259732523707e-06,
|
| 384 |
+
"loss": 0.4958,
|
| 385 |
+
"step": 30500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.46,
|
| 389 |
+
"learning_rate": 3.294927244091003e-06,
|
| 390 |
+
"loss": 0.556,
|
| 391 |
+
"step": 31000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.48,
|
| 395 |
+
"learning_rate": 3.151594755658299e-06,
|
| 396 |
+
"loss": 0.5757,
|
| 397 |
+
"step": 31500
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.51,
|
| 401 |
+
"learning_rate": 3.0082622672255946e-06,
|
| 402 |
+
"loss": 0.4861,
|
| 403 |
+
"step": 32000
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.53,
|
| 407 |
+
"learning_rate": 2.8649297787928907e-06,
|
| 408 |
+
"loss": 0.4568,
|
| 409 |
+
"step": 32500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.55,
|
| 413 |
+
"learning_rate": 2.7215972903601864e-06,
|
| 414 |
+
"loss": 0.5247,
|
| 415 |
+
"step": 33000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.58,
|
| 419 |
+
"learning_rate": 2.578264801927482e-06,
|
| 420 |
+
"loss": 0.5093,
|
| 421 |
+
"step": 33500
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.6,
|
| 425 |
+
"learning_rate": 2.434932313494778e-06,
|
| 426 |
+
"loss": 0.5081,
|
| 427 |
+
"step": 34000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.62,
|
| 431 |
+
"learning_rate": 2.291599825062074e-06,
|
| 432 |
+
"loss": 0.4745,
|
| 433 |
+
"step": 34500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.65,
|
| 437 |
+
"learning_rate": 2.14826733662937e-06,
|
| 438 |
+
"loss": 0.5952,
|
| 439 |
+
"step": 35000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.67,
|
| 443 |
+
"learning_rate": 2.0049348481966656e-06,
|
| 444 |
+
"loss": 0.484,
|
| 445 |
+
"step": 35500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.69,
|
| 449 |
+
"learning_rate": 1.8616023597639615e-06,
|
| 450 |
+
"loss": 0.4612,
|
| 451 |
+
"step": 36000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.72,
|
| 455 |
+
"learning_rate": 1.7182698713312574e-06,
|
| 456 |
+
"loss": 0.4916,
|
| 457 |
+
"step": 36500
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.74,
|
| 461 |
+
"learning_rate": 1.5749373828985531e-06,
|
| 462 |
+
"loss": 0.5205,
|
| 463 |
+
"step": 37000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 1.76,
|
| 467 |
+
"learning_rate": 1.431604894465849e-06,
|
| 468 |
+
"loss": 0.5094,
|
| 469 |
+
"step": 37500
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.79,
|
| 473 |
+
"learning_rate": 1.288272406033145e-06,
|
| 474 |
+
"loss": 0.5167,
|
| 475 |
+
"step": 38000
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.81,
|
| 479 |
+
"learning_rate": 1.1449399176004408e-06,
|
| 480 |
+
"loss": 0.4265,
|
| 481 |
+
"step": 38500
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.84,
|
| 485 |
+
"learning_rate": 1.0016074291677367e-06,
|
| 486 |
+
"loss": 0.4839,
|
| 487 |
+
"step": 39000
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.86,
|
| 491 |
+
"learning_rate": 8.582749407350325e-07,
|
| 492 |
+
"loss": 0.3951,
|
| 493 |
+
"step": 39500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.88,
|
| 497 |
+
"learning_rate": 7.149424523023283e-07,
|
| 498 |
+
"loss": 0.4862,
|
| 499 |
+
"step": 40000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.91,
|
| 503 |
+
"learning_rate": 5.716099638696242e-07,
|
| 504 |
+
"loss": 0.4289,
|
| 505 |
+
"step": 40500
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.93,
|
| 509 |
+
"learning_rate": 4.2827747543692e-07,
|
| 510 |
+
"loss": 0.4957,
|
| 511 |
+
"step": 41000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.95,
|
| 515 |
+
"learning_rate": 2.8494498700421584e-07,
|
| 516 |
+
"loss": 0.489,
|
| 517 |
+
"step": 41500
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.98,
|
| 521 |
+
"learning_rate": 1.416124985715117e-07,
|
| 522 |
+
"loss": 0.545,
|
| 523 |
+
"step": 42000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.0,
|
| 527 |
+
"eval_accuracy": 0.8563556208670096,
|
| 528 |
+
"eval_f1": 0.8563556208670096,
|
| 529 |
+
"eval_loss": 0.7366806864738464,
|
| 530 |
+
"eval_precision": 0.8563556208670096,
|
| 531 |
+
"eval_recall": 0.8563556208670096,
|
| 532 |
+
"eval_runtime": 33.6504,
|
| 533 |
+
"eval_samples_per_second": 242.672,
|
| 534 |
+
"step": 42494
|
| 535 |
+
}
|
| 536 |
+
],
|
| 537 |
+
"max_steps": 42494,
|
| 538 |
+
"num_train_epochs": 2,
|
| 539 |
+
"total_flos": 2056889592480660.0,
|
| 540 |
+
"trial_name": null,
|
| 541 |
+
"trial_params": null
|
| 542 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:191e85a7212381580d5fb33b8b390af12286c444ad0ad8ac61ea7c1cf49bd6fe
|
| 3 |
+
size 2351
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|