upload nace2_level1_29 model
Browse files- config.json +36 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +400 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../models/roberta-large/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"finetuning_task": "nace",
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "1",
|
| 16 |
+
"1": "3"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 4096,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"1": 0,
|
| 22 |
+
"3": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-05,
|
| 25 |
+
"max_position_embeddings": 514,
|
| 26 |
+
"model_type": "roberta",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"pad_token_id": 1,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "multi_label_classification",
|
| 32 |
+
"transformers_version": "4.6.1",
|
| 33 |
+
"type_vocab_size": 1,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 50265
|
| 36 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0291d671a6babc8601c0a7b7735bb48dd4f079974d63b2b03f534535f9fcf6ac
|
| 3 |
+
size 1421611309
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d6b20e1839b311222562167e53e6b0519bcca13d4294f399a22ad4b04d9de2b
|
| 3 |
+
size 15523
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "../models/roberta-large/"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9863948830227645,
|
| 3 |
+
"best_model_checkpoint": "./output//29_roberta-large_nace_5__5e-6_0.01_0.06_07-21-22_10-40/checkpoint-46000",
|
| 4 |
+
"epoch": 1.6596362630523478,
|
| 5 |
+
"global_step": 48000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 1.1524720525527257e-06,
|
| 13 |
+
"loss": 0.1493,
|
| 14 |
+
"step": 2000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"eval_accuracy": 0.9610440126806309,
|
| 19 |
+
"eval_f1": 0.9764342504146886,
|
| 20 |
+
"eval_loss": 0.05725020170211792,
|
| 21 |
+
"eval_roc_auc": 0.9759211072420441,
|
| 22 |
+
"eval_runtime": 1536.6369,
|
| 23 |
+
"eval_samples_per_second": 33.461,
|
| 24 |
+
"step": 2000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.14,
|
| 28 |
+
"learning_rate": 2.3049441051054513e-06,
|
| 29 |
+
"loss": 0.0528,
|
| 30 |
+
"step": 4000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.14,
|
| 34 |
+
"eval_accuracy": 0.9728883443219168,
|
| 35 |
+
"eval_f1": 0.9829246052694726,
|
| 36 |
+
"eval_loss": 0.05182106792926788,
|
| 37 |
+
"eval_roc_auc": 0.9827894561625595,
|
| 38 |
+
"eval_runtime": 1536.9258,
|
| 39 |
+
"eval_samples_per_second": 33.454,
|
| 40 |
+
"step": 4000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.21,
|
| 44 |
+
"learning_rate": 3.457416157658177e-06,
|
| 45 |
+
"loss": 0.0497,
|
| 46 |
+
"step": 6000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.21,
|
| 50 |
+
"eval_accuracy": 0.9731606278079235,
|
| 51 |
+
"eval_f1": 0.9840875186474392,
|
| 52 |
+
"eval_loss": 0.048033468425273895,
|
| 53 |
+
"eval_roc_auc": 0.9838391681932317,
|
| 54 |
+
"eval_runtime": 1538.305,
|
| 55 |
+
"eval_samples_per_second": 33.424,
|
| 56 |
+
"step": 6000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.28,
|
| 60 |
+
"learning_rate": 4.609888210210903e-06,
|
| 61 |
+
"loss": 0.0462,
|
| 62 |
+
"step": 8000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.28,
|
| 66 |
+
"eval_accuracy": 0.9722465332477586,
|
| 67 |
+
"eval_f1": 0.9834792174869661,
|
| 68 |
+
"eval_loss": 0.054564349353313446,
|
| 69 |
+
"eval_roc_auc": 0.9832329187393456,
|
| 70 |
+
"eval_runtime": 1538.1819,
|
| 71 |
+
"eval_samples_per_second": 33.427,
|
| 72 |
+
"step": 8000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.35,
|
| 76 |
+
"learning_rate": 4.951336320098873e-06,
|
| 77 |
+
"loss": 0.0433,
|
| 78 |
+
"step": 10000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.35,
|
| 82 |
+
"eval_accuracy": 0.9736079506777914,
|
| 83 |
+
"eval_f1": 0.9837862700755107,
|
| 84 |
+
"eval_loss": 0.04221172630786896,
|
| 85 |
+
"eval_roc_auc": 0.9836052885203017,
|
| 86 |
+
"eval_runtime": 1535.859,
|
| 87 |
+
"eval_samples_per_second": 33.478,
|
| 88 |
+
"step": 10000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.41,
|
| 92 |
+
"learning_rate": 4.877770666431257e-06,
|
| 93 |
+
"loss": 0.0442,
|
| 94 |
+
"step": 12000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.41,
|
| 98 |
+
"eval_accuracy": 0.9738413365229399,
|
| 99 |
+
"eval_f1": 0.9840872143062064,
|
| 100 |
+
"eval_loss": 0.047410748898983,
|
| 101 |
+
"eval_roc_auc": 0.9838395246306029,
|
| 102 |
+
"eval_runtime": 1536.4074,
|
| 103 |
+
"eval_samples_per_second": 33.466,
|
| 104 |
+
"step": 12000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.48,
|
| 108 |
+
"learning_rate": 4.804205012763641e-06,
|
| 109 |
+
"loss": 0.0433,
|
| 110 |
+
"step": 14000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.48,
|
| 114 |
+
"eval_accuracy": 0.9747748799035338,
|
| 115 |
+
"eval_f1": 0.9848328360492695,
|
| 116 |
+
"eval_loss": 0.04587765783071518,
|
| 117 |
+
"eval_roc_auc": 0.9845986397430451,
|
| 118 |
+
"eval_runtime": 1536.4412,
|
| 119 |
+
"eval_samples_per_second": 33.465,
|
| 120 |
+
"step": 14000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.55,
|
| 124 |
+
"learning_rate": 4.730639359096026e-06,
|
| 125 |
+
"loss": 0.0427,
|
| 126 |
+
"step": 16000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.55,
|
| 130 |
+
"eval_accuracy": 0.9745609428788145,
|
| 131 |
+
"eval_f1": 0.9846027155907081,
|
| 132 |
+
"eval_loss": 0.04280721768736839,
|
| 133 |
+
"eval_roc_auc": 0.9844085121898316,
|
| 134 |
+
"eval_runtime": 1536.1052,
|
| 135 |
+
"eval_samples_per_second": 33.472,
|
| 136 |
+
"step": 16000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.62,
|
| 140 |
+
"learning_rate": 4.65707370542841e-06,
|
| 141 |
+
"loss": 0.0401,
|
| 142 |
+
"step": 18000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.62,
|
| 146 |
+
"eval_accuracy": 0.9754555886185503,
|
| 147 |
+
"eval_f1": 0.9849309815950921,
|
| 148 |
+
"eval_loss": 0.0410287007689476,
|
| 149 |
+
"eval_roc_auc": 0.9847790254315509,
|
| 150 |
+
"eval_runtime": 1536.224,
|
| 151 |
+
"eval_samples_per_second": 33.47,
|
| 152 |
+
"step": 18000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.69,
|
| 156 |
+
"learning_rate": 4.583508051760795e-06,
|
| 157 |
+
"loss": 0.0409,
|
| 158 |
+
"step": 20000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.69,
|
| 162 |
+
"eval_accuracy": 0.974891572826108,
|
| 163 |
+
"eval_f1": 0.9855708668931557,
|
| 164 |
+
"eval_loss": 0.040095292031764984,
|
| 165 |
+
"eval_roc_auc": 0.9852792796060187,
|
| 166 |
+
"eval_runtime": 1536.3646,
|
| 167 |
+
"eval_samples_per_second": 33.467,
|
| 168 |
+
"step": 20000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.76,
|
| 172 |
+
"learning_rate": 4.509942398093178e-06,
|
| 173 |
+
"loss": 0.0403,
|
| 174 |
+
"step": 22000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.76,
|
| 178 |
+
"eval_accuracy": 0.9755139350798374,
|
| 179 |
+
"eval_f1": 0.9850088183421517,
|
| 180 |
+
"eval_loss": 0.040499284863471985,
|
| 181 |
+
"eval_roc_auc": 0.9848554210846383,
|
| 182 |
+
"eval_runtime": 1536.2737,
|
| 183 |
+
"eval_samples_per_second": 33.469,
|
| 184 |
+
"step": 22000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.83,
|
| 188 |
+
"learning_rate": 4.436376744425563e-06,
|
| 189 |
+
"loss": 0.0414,
|
| 190 |
+
"step": 24000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.83,
|
| 194 |
+
"eval_accuracy": 0.975319446875547,
|
| 195 |
+
"eval_f1": 0.9852808881232654,
|
| 196 |
+
"eval_loss": 0.041136886924505234,
|
| 197 |
+
"eval_roc_auc": 0.985079469215943,
|
| 198 |
+
"eval_runtime": 1536.5795,
|
| 199 |
+
"eval_samples_per_second": 33.462,
|
| 200 |
+
"step": 24000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.9,
|
| 204 |
+
"learning_rate": 4.362811090757947e-06,
|
| 205 |
+
"loss": 0.0402,
|
| 206 |
+
"step": 26000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.9,
|
| 210 |
+
"eval_accuracy": 0.9764474784604313,
|
| 211 |
+
"eval_f1": 0.9861650624772766,
|
| 212 |
+
"eval_loss": 0.04073059558868408,
|
| 213 |
+
"eval_roc_auc": 0.9859694252223201,
|
| 214 |
+
"eval_runtime": 1536.8522,
|
| 215 |
+
"eval_samples_per_second": 33.456,
|
| 216 |
+
"step": 26000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.97,
|
| 220 |
+
"learning_rate": 4.289245437090332e-06,
|
| 221 |
+
"loss": 0.0399,
|
| 222 |
+
"step": 28000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.97,
|
| 226 |
+
"eval_accuracy": 0.9755722815411245,
|
| 227 |
+
"eval_f1": 0.9853538060958797,
|
| 228 |
+
"eval_loss": 0.040422726422548294,
|
| 229 |
+
"eval_roc_auc": 0.9851619243043377,
|
| 230 |
+
"eval_runtime": 1537.2709,
|
| 231 |
+
"eval_samples_per_second": 33.447,
|
| 232 |
+
"step": 28000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.04,
|
| 236 |
+
"learning_rate": 4.215679783422716e-06,
|
| 237 |
+
"loss": 0.04,
|
| 238 |
+
"step": 30000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.04,
|
| 242 |
+
"eval_accuracy": 0.9761946437948539,
|
| 243 |
+
"eval_f1": 0.9859556473987333,
|
| 244 |
+
"eval_loss": 0.03985821455717087,
|
| 245 |
+
"eval_roc_auc": 0.9857539906157645,
|
| 246 |
+
"eval_runtime": 1537.4136,
|
| 247 |
+
"eval_samples_per_second": 33.444,
|
| 248 |
+
"step": 30000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.11,
|
| 252 |
+
"learning_rate": 4.142114129755101e-06,
|
| 253 |
+
"loss": 0.0373,
|
| 254 |
+
"step": 32000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.11,
|
| 258 |
+
"eval_accuracy": 0.9766419666647218,
|
| 259 |
+
"eval_f1": 0.9855267070141279,
|
| 260 |
+
"eval_loss": 0.04419500008225441,
|
| 261 |
+
"eval_roc_auc": 0.9854023838792458,
|
| 262 |
+
"eval_runtime": 1536.3227,
|
| 263 |
+
"eval_samples_per_second": 33.468,
|
| 264 |
+
"step": 32000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.18,
|
| 268 |
+
"learning_rate": 4.068548476087484e-06,
|
| 269 |
+
"loss": 0.0357,
|
| 270 |
+
"step": 34000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.18,
|
| 274 |
+
"eval_accuracy": 0.9768948013302993,
|
| 275 |
+
"eval_f1": 0.9859001025621362,
|
| 276 |
+
"eval_loss": 0.04071442782878876,
|
| 277 |
+
"eval_roc_auc": 0.9857602731082165,
|
| 278 |
+
"eval_runtime": 1536.5165,
|
| 279 |
+
"eval_samples_per_second": 33.463,
|
| 280 |
+
"step": 34000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.24,
|
| 284 |
+
"learning_rate": 3.994982822419869e-06,
|
| 285 |
+
"loss": 0.0365,
|
| 286 |
+
"step": 36000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.24,
|
| 290 |
+
"eval_accuracy": 0.976252990256141,
|
| 291 |
+
"eval_f1": 0.9857402622260503,
|
| 292 |
+
"eval_loss": 0.04006611183285713,
|
| 293 |
+
"eval_roc_auc": 0.9855463976313715,
|
| 294 |
+
"eval_runtime": 1536.8448,
|
| 295 |
+
"eval_samples_per_second": 33.456,
|
| 296 |
+
"step": 36000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.31,
|
| 300 |
+
"learning_rate": 3.921417168752253e-06,
|
| 301 |
+
"loss": 0.0362,
|
| 302 |
+
"step": 38000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.31,
|
| 306 |
+
"eval_accuracy": 0.9752805492346889,
|
| 307 |
+
"eval_f1": 0.9857657021203471,
|
| 308 |
+
"eval_loss": 0.03810262680053711,
|
| 309 |
+
"eval_roc_auc": 0.9854908677538746,
|
| 310 |
+
"eval_runtime": 1536.4894,
|
| 311 |
+
"eval_samples_per_second": 33.464,
|
| 312 |
+
"step": 38000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.38,
|
| 316 |
+
"learning_rate": 3.847851515084638e-06,
|
| 317 |
+
"loss": 0.0367,
|
| 318 |
+
"step": 40000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.38,
|
| 322 |
+
"eval_accuracy": 0.9741719664702336,
|
| 323 |
+
"eval_f1": 0.9848820340536,
|
| 324 |
+
"eval_loss": 0.03949220851063728,
|
| 325 |
+
"eval_roc_auc": 0.984581025607102,
|
| 326 |
+
"eval_runtime": 1536.5636,
|
| 327 |
+
"eval_samples_per_second": 33.462,
|
| 328 |
+
"step": 40000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.45,
|
| 332 |
+
"learning_rate": 3.7742858614170217e-06,
|
| 333 |
+
"loss": 0.0366,
|
| 334 |
+
"step": 42000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.45,
|
| 338 |
+
"eval_accuracy": 0.9754166909776922,
|
| 339 |
+
"eval_f1": 0.9858603603173542,
|
| 340 |
+
"eval_loss": 0.03979261964559555,
|
| 341 |
+
"eval_roc_auc": 0.9855892138192017,
|
| 342 |
+
"eval_runtime": 1537.1787,
|
| 343 |
+
"eval_samples_per_second": 33.449,
|
| 344 |
+
"step": 42000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.52,
|
| 348 |
+
"learning_rate": 3.7007202077494066e-06,
|
| 349 |
+
"loss": 0.0354,
|
| 350 |
+
"step": 44000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.52,
|
| 354 |
+
"eval_accuracy": 0.9768559036894412,
|
| 355 |
+
"eval_f1": 0.9861624145916668,
|
| 356 |
+
"eval_loss": 0.039536893367767334,
|
| 357 |
+
"eval_roc_auc": 0.9859729895960303,
|
| 358 |
+
"eval_runtime": 1536.4855,
|
| 359 |
+
"eval_samples_per_second": 33.464,
|
| 360 |
+
"step": 44000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.59,
|
| 364 |
+
"learning_rate": 3.6271545540817902e-06,
|
| 365 |
+
"loss": 0.0365,
|
| 366 |
+
"step": 46000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.59,
|
| 370 |
+
"eval_accuracy": 0.9768364548690122,
|
| 371 |
+
"eval_f1": 0.9863948830227645,
|
| 372 |
+
"eval_loss": 0.04265940561890602,
|
| 373 |
+
"eval_roc_auc": 0.9861797953532997,
|
| 374 |
+
"eval_runtime": 1536.6035,
|
| 375 |
+
"eval_samples_per_second": 33.461,
|
| 376 |
+
"step": 46000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.66,
|
| 380 |
+
"learning_rate": 3.553588900414175e-06,
|
| 381 |
+
"loss": 0.0358,
|
| 382 |
+
"step": 48000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.66,
|
| 386 |
+
"eval_accuracy": 0.9745609428788145,
|
| 387 |
+
"eval_f1": 0.9850252764160049,
|
| 388 |
+
"eval_loss": 0.039769496768713,
|
| 389 |
+
"eval_roc_auc": 0.9847700991727389,
|
| 390 |
+
"eval_runtime": 1536.7946,
|
| 391 |
+
"eval_samples_per_second": 33.457,
|
| 392 |
+
"step": 48000
|
| 393 |
+
}
|
| 394 |
+
],
|
| 395 |
+
"max_steps": 144610,
|
| 396 |
+
"num_train_epochs": 5,
|
| 397 |
+
"total_flos": 6.9866971594752e+16,
|
| 398 |
+
"trial_name": null,
|
| 399 |
+
"trial_params": null
|
| 400 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ec687911cb81e5994a95ebae35370b2054083e9e06bf60529648a5323d55401
|
| 3 |
+
size 2479
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|