Model import
Browse files- config.json +38 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +443 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 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 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"LABEL_0": 0,
|
| 22 |
+
"LABEL_1": 1,
|
| 23 |
+
"LABEL_2": 2,
|
| 24 |
+
"LABEL_3": 3,
|
| 25 |
+
"LABEL_4": 4
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-12,
|
| 28 |
+
"max_position_embeddings": 512,
|
| 29 |
+
"model_type": "bert",
|
| 30 |
+
"num_attention_heads": 12,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"pad_token_id": 0,
|
| 33 |
+
"position_embedding_type": "absolute",
|
| 34 |
+
"transformers_version": "4.3.3",
|
| 35 |
+
"type_vocab_size": 2,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 30522
|
| 38 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:050a6d8bf62ec382c7c9e023ea81e540578c11d7acf62c55defcc974ac20cbc6
|
| 3 |
+
size 438028461
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fab52ad55aaf3a66286c9a6ba364a27f2cfec8e169224640fa91ef123c9a275e
|
| 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, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.96593837535014,
|
| 3 |
+
"best_model_checkpoint": "../output/bert-base-uncased-yelp_bin/checkpoint-3500",
|
| 4 |
+
"epoch": 0.20019447463250015,
|
| 5 |
+
"global_step": 3500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"eval_accuracy": 0.9071428571428571,
|
| 13 |
+
"eval_f1": 0.907100199071002,
|
| 14 |
+
"eval_loss": 0.2581118941307068,
|
| 15 |
+
"eval_precision": 0.9072309595785661,
|
| 16 |
+
"eval_recall": 0.9081054824813692,
|
| 17 |
+
"eval_runtime": 2.7939,
|
| 18 |
+
"eval_samples_per_second": 200.435,
|
| 19 |
+
"step": 100
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.01,
|
| 23 |
+
"eval_accuracy": 0.8892857142857142,
|
| 24 |
+
"eval_f1": 0.8868598391532736,
|
| 25 |
+
"eval_loss": 0.3021739721298218,
|
| 26 |
+
"eval_precision": 0.908363774630291,
|
| 27 |
+
"eval_recall": 0.8843936546893175,
|
| 28 |
+
"eval_runtime": 2.8003,
|
| 29 |
+
"eval_samples_per_second": 199.98,
|
| 30 |
+
"step": 200
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02,
|
| 34 |
+
"eval_accuracy": 0.9160714285714285,
|
| 35 |
+
"eval_f1": 0.9160647373036754,
|
| 36 |
+
"eval_loss": 0.2224453091621399,
|
| 37 |
+
"eval_precision": 0.9192965828167426,
|
| 38 |
+
"eval_recall": 0.9184658255678695,
|
| 39 |
+
"eval_runtime": 2.8002,
|
| 40 |
+
"eval_samples_per_second": 199.989,
|
| 41 |
+
"step": 300
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.02,
|
| 45 |
+
"eval_accuracy": 0.9232142857142858,
|
| 46 |
+
"eval_f1": 0.922669569769197,
|
| 47 |
+
"eval_loss": 0.1851794272661209,
|
| 48 |
+
"eval_precision": 0.9266868624100254,
|
| 49 |
+
"eval_recall": 0.9213035753090207,
|
| 50 |
+
"eval_runtime": 2.8015,
|
| 51 |
+
"eval_samples_per_second": 199.89,
|
| 52 |
+
"step": 400
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03,
|
| 56 |
+
"learning_rate": 1.942801578676429e-05,
|
| 57 |
+
"loss": 0.2853,
|
| 58 |
+
"step": 500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03,
|
| 62 |
+
"eval_accuracy": 0.9232142857142858,
|
| 63 |
+
"eval_f1": 0.9232081639161285,
|
| 64 |
+
"eval_loss": 0.17731928825378418,
|
| 65 |
+
"eval_precision": 0.9242238562091503,
|
| 66 |
+
"eval_recall": 0.9247932405312472,
|
| 67 |
+
"eval_runtime": 2.805,
|
| 68 |
+
"eval_samples_per_second": 199.641,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"eval_accuracy": 0.9375,
|
| 74 |
+
"eval_f1": 0.9374119856047567,
|
| 75 |
+
"eval_loss": 0.1572866588830948,
|
| 76 |
+
"eval_precision": 0.9371936274509804,
|
| 77 |
+
"eval_recall": 0.937780419526786,
|
| 78 |
+
"eval_runtime": 2.8024,
|
| 79 |
+
"eval_samples_per_second": 199.83,
|
| 80 |
+
"step": 600
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04,
|
| 84 |
+
"eval_accuracy": 0.9375,
|
| 85 |
+
"eval_f1": 0.9370177924736262,
|
| 86 |
+
"eval_loss": 0.1771181970834732,
|
| 87 |
+
"eval_precision": 0.9418188420834197,
|
| 88 |
+
"eval_recall": 0.9354539760453018,
|
| 89 |
+
"eval_runtime": 2.8029,
|
| 90 |
+
"eval_samples_per_second": 199.79,
|
| 91 |
+
"step": 700
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.05,
|
| 95 |
+
"eval_accuracy": 0.9285714285714286,
|
| 96 |
+
"eval_f1": 0.9278499278499278,
|
| 97 |
+
"eval_loss": 0.19192437827587128,
|
| 98 |
+
"eval_precision": 0.9352719102297815,
|
| 99 |
+
"eval_recall": 0.9259245056307601,
|
| 100 |
+
"eval_runtime": 2.8042,
|
| 101 |
+
"eval_samples_per_second": 199.7,
|
| 102 |
+
"step": 800
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.05,
|
| 106 |
+
"eval_accuracy": 0.9410714285714286,
|
| 107 |
+
"eval_f1": 0.9410035148879929,
|
| 108 |
+
"eval_loss": 0.1547766625881195,
|
| 109 |
+
"eval_precision": 0.9407763769077637,
|
| 110 |
+
"eval_recall": 0.941525737878846,
|
| 111 |
+
"eval_runtime": 2.8036,
|
| 112 |
+
"eval_samples_per_second": 199.741,
|
| 113 |
+
"step": 900
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.06,
|
| 117 |
+
"learning_rate": 1.8856031573528572e-05,
|
| 118 |
+
"loss": 0.1949,
|
| 119 |
+
"step": 1000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.06,
|
| 123 |
+
"eval_accuracy": 0.9482142857142857,
|
| 124 |
+
"eval_f1": 0.9480551050892563,
|
| 125 |
+
"eval_loss": 0.14137934148311615,
|
| 126 |
+
"eval_precision": 0.9485757467083356,
|
| 127 |
+
"eval_recall": 0.9476869783078319,
|
| 128 |
+
"eval_runtime": 2.8033,
|
| 129 |
+
"eval_samples_per_second": 199.761,
|
| 130 |
+
"step": 1000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.06,
|
| 134 |
+
"eval_accuracy": 0.9428571428571428,
|
| 135 |
+
"eval_f1": 0.9428214062360404,
|
| 136 |
+
"eval_loss": 0.14555300772190094,
|
| 137 |
+
"eval_precision": 0.9427798823964592,
|
| 138 |
+
"eval_recall": 0.9437307461236595,
|
| 139 |
+
"eval_runtime": 2.8027,
|
| 140 |
+
"eval_samples_per_second": 199.809,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.07,
|
| 145 |
+
"eval_accuracy": 0.9535714285714286,
|
| 146 |
+
"eval_f1": 0.9533787591577437,
|
| 147 |
+
"eval_loss": 0.13459965586662292,
|
| 148 |
+
"eval_precision": 0.95473282736834,
|
| 149 |
+
"eval_recall": 0.9526402576983548,
|
| 150 |
+
"eval_runtime": 2.8033,
|
| 151 |
+
"eval_samples_per_second": 199.763,
|
| 152 |
+
"step": 1200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.07,
|
| 156 |
+
"eval_accuracy": 0.925,
|
| 157 |
+
"eval_f1": 0.9239435526639158,
|
| 158 |
+
"eval_loss": 0.19309227168560028,
|
| 159 |
+
"eval_precision": 0.9362357952666323,
|
| 160 |
+
"eval_recall": 0.9215144891411333,
|
| 161 |
+
"eval_runtime": 2.8036,
|
| 162 |
+
"eval_samples_per_second": 199.744,
|
| 163 |
+
"step": 1300
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.08,
|
| 167 |
+
"eval_accuracy": 0.95,
|
| 168 |
+
"eval_f1": 0.9497687053908944,
|
| 169 |
+
"eval_loss": 0.14192207157611847,
|
| 170 |
+
"eval_precision": 0.9515268402442945,
|
| 171 |
+
"eval_recall": 0.948894939346295,
|
| 172 |
+
"eval_runtime": 2.8032,
|
| 173 |
+
"eval_samples_per_second": 199.768,
|
| 174 |
+
"step": 1400
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.09,
|
| 178 |
+
"learning_rate": 1.828404736029286e-05,
|
| 179 |
+
"loss": 0.1747,
|
| 180 |
+
"step": 1500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.09,
|
| 184 |
+
"eval_accuracy": 0.95,
|
| 185 |
+
"eval_f1": 0.9497435897435897,
|
| 186 |
+
"eval_loss": 0.13348396122455597,
|
| 187 |
+
"eval_precision": 0.9519640535077443,
|
| 188 |
+
"eval_recall": 0.9487287648119032,
|
| 189 |
+
"eval_runtime": 2.8033,
|
| 190 |
+
"eval_samples_per_second": 199.761,
|
| 191 |
+
"step": 1500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.09,
|
| 195 |
+
"eval_accuracy": 0.9535714285714286,
|
| 196 |
+
"eval_f1": 0.9533787591577437,
|
| 197 |
+
"eval_loss": 0.15492305159568787,
|
| 198 |
+
"eval_precision": 0.95473282736834,
|
| 199 |
+
"eval_recall": 0.9526402576983548,
|
| 200 |
+
"eval_runtime": 2.8024,
|
| 201 |
+
"eval_samples_per_second": 199.83,
|
| 202 |
+
"step": 1600
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.1,
|
| 206 |
+
"eval_accuracy": 0.9517857142857142,
|
| 207 |
+
"eval_f1": 0.9515966386554622,
|
| 208 |
+
"eval_loss": 0.12274421751499176,
|
| 209 |
+
"eval_precision": 0.9527568150315725,
|
| 210 |
+
"eval_recall": 0.9509337730567167,
|
| 211 |
+
"eval_runtime": 2.8039,
|
| 212 |
+
"eval_samples_per_second": 199.723,
|
| 213 |
+
"step": 1700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1,
|
| 217 |
+
"eval_accuracy": 0.95,
|
| 218 |
+
"eval_f1": 0.9496603356833737,
|
| 219 |
+
"eval_loss": 0.15004612505435944,
|
| 220 |
+
"eval_precision": 0.9535641758611323,
|
| 221 |
+
"eval_recall": 0.948230241208728,
|
| 222 |
+
"eval_runtime": 2.8029,
|
| 223 |
+
"eval_samples_per_second": 199.79,
|
| 224 |
+
"step": 1800
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.11,
|
| 228 |
+
"eval_accuracy": 0.9482142857142857,
|
| 229 |
+
"eval_f1": 0.9481413595010841,
|
| 230 |
+
"eval_loss": 0.14852674305438995,
|
| 231 |
+
"eval_precision": 0.9479166666666667,
|
| 232 |
+
"eval_recall": 0.9485178509797907,
|
| 233 |
+
"eval_runtime": 2.803,
|
| 234 |
+
"eval_samples_per_second": 199.789,
|
| 235 |
+
"step": 1900
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.11,
|
| 239 |
+
"learning_rate": 1.7712063147057142e-05,
|
| 240 |
+
"loss": 0.1688,
|
| 241 |
+
"step": 2000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.11,
|
| 245 |
+
"eval_accuracy": 0.9303571428571429,
|
| 246 |
+
"eval_f1": 0.9303515905285817,
|
| 247 |
+
"eval_loss": 0.15722833573818207,
|
| 248 |
+
"eval_precision": 0.9313725490196079,
|
| 249 |
+
"eval_recall": 0.9319515281665836,
|
| 250 |
+
"eval_runtime": 2.8087,
|
| 251 |
+
"eval_samples_per_second": 199.379,
|
| 252 |
+
"step": 2000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.12,
|
| 256 |
+
"eval_accuracy": 0.9571428571428572,
|
| 257 |
+
"eval_f1": 0.9569230769230769,
|
| 258 |
+
"eval_loss": 0.12534742057323456,
|
| 259 |
+
"eval_precision": 0.9591739516679327,
|
| 260 |
+
"eval_recall": 0.9558870524472396,
|
| 261 |
+
"eval_runtime": 2.8059,
|
| 262 |
+
"eval_samples_per_second": 199.582,
|
| 263 |
+
"step": 2100
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.13,
|
| 267 |
+
"eval_accuracy": 0.9517857142857142,
|
| 268 |
+
"eval_f1": 0.9514723581802134,
|
| 269 |
+
"eval_loss": 0.13627249002456665,
|
| 270 |
+
"eval_precision": 0.9550765095119934,
|
| 271 |
+
"eval_recall": 0.950102900384758,
|
| 272 |
+
"eval_runtime": 2.8027,
|
| 273 |
+
"eval_samples_per_second": 199.804,
|
| 274 |
+
"step": 2200
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.13,
|
| 278 |
+
"eval_accuracy": 0.9553571428571429,
|
| 279 |
+
"eval_f1": 0.9552679926511702,
|
| 280 |
+
"eval_loss": 0.12657539546489716,
|
| 281 |
+
"eval_precision": 0.9551983234512369,
|
| 282 |
+
"eval_recall": 0.9553437895463435,
|
| 283 |
+
"eval_runtime": 2.8014,
|
| 284 |
+
"eval_samples_per_second": 199.901,
|
| 285 |
+
"step": 2300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.14,
|
| 289 |
+
"eval_accuracy": 0.9482142857142857,
|
| 290 |
+
"eval_f1": 0.9480338292092119,
|
| 291 |
+
"eval_loss": 0.12863141298294067,
|
| 292 |
+
"eval_precision": 0.9488461538461539,
|
| 293 |
+
"eval_recall": 0.9475208037734402,
|
| 294 |
+
"eval_runtime": 2.8027,
|
| 295 |
+
"eval_samples_per_second": 199.809,
|
| 296 |
+
"step": 2400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.14,
|
| 300 |
+
"learning_rate": 1.7140078933821426e-05,
|
| 301 |
+
"loss": 0.165,
|
| 302 |
+
"step": 2500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.14,
|
| 306 |
+
"eval_accuracy": 0.9357142857142857,
|
| 307 |
+
"eval_f1": 0.9357011635027557,
|
| 308 |
+
"eval_loss": 0.1396503895521164,
|
| 309 |
+
"eval_precision": 0.9362679425837321,
|
| 310 |
+
"eval_recall": 0.9370709820914982,
|
| 311 |
+
"eval_runtime": 2.8041,
|
| 312 |
+
"eval_samples_per_second": 199.709,
|
| 313 |
+
"step": 2500
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.15,
|
| 317 |
+
"eval_accuracy": 0.9571428571428572,
|
| 318 |
+
"eval_f1": 0.9570024570024569,
|
| 319 |
+
"eval_loss": 0.11459986865520477,
|
| 320 |
+
"eval_precision": 0.9576750086495214,
|
| 321 |
+
"eval_recall": 0.9565517505848065,
|
| 322 |
+
"eval_runtime": 2.8039,
|
| 323 |
+
"eval_samples_per_second": 199.72,
|
| 324 |
+
"step": 2600
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.15,
|
| 328 |
+
"eval_accuracy": 0.9589285714285715,
|
| 329 |
+
"eval_f1": 0.9588591725199715,
|
| 330 |
+
"eval_loss": 0.11520295590162277,
|
| 331 |
+
"eval_precision": 0.9586845466155811,
|
| 332 |
+
"eval_recall": 0.9590891078984034,
|
| 333 |
+
"eval_runtime": 2.8102,
|
| 334 |
+
"eval_samples_per_second": 199.272,
|
| 335 |
+
"step": 2700
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.16,
|
| 339 |
+
"eval_accuracy": 0.95,
|
| 340 |
+
"eval_f1": 0.9498919865526454,
|
| 341 |
+
"eval_loss": 0.11789484322071075,
|
| 342 |
+
"eval_precision": 0.9498919865526454,
|
| 343 |
+
"eval_recall": 0.9498919865526454,
|
| 344 |
+
"eval_runtime": 2.8046,
|
| 345 |
+
"eval_samples_per_second": 199.675,
|
| 346 |
+
"step": 2800
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.17,
|
| 350 |
+
"eval_accuracy": 0.9535714285714286,
|
| 351 |
+
"eval_f1": 0.9532277960526315,
|
| 352 |
+
"eval_loss": 0.12774023413658142,
|
| 353 |
+
"eval_precision": 0.9578231292517008,
|
| 354 |
+
"eval_recall": 0.9516432104920045,
|
| 355 |
+
"eval_runtime": 2.8037,
|
| 356 |
+
"eval_samples_per_second": 199.733,
|
| 357 |
+
"step": 2900
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.17,
|
| 361 |
+
"learning_rate": 1.6568094720585712e-05,
|
| 362 |
+
"loss": 0.1585,
|
| 363 |
+
"step": 3000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.17,
|
| 367 |
+
"eval_accuracy": 0.9589285714285715,
|
| 368 |
+
"eval_f1": 0.9588181315325859,
|
| 369 |
+
"eval_loss": 0.11161162704229355,
|
| 370 |
+
"eval_precision": 0.9591011466011465,
|
| 371 |
+
"eval_recall": 0.9585905842952283,
|
| 372 |
+
"eval_runtime": 2.8029,
|
| 373 |
+
"eval_samples_per_second": 199.797,
|
| 374 |
+
"step": 3000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.18,
|
| 378 |
+
"eval_accuracy": 0.9535714285714286,
|
| 379 |
+
"eval_f1": 0.9534859946841137,
|
| 380 |
+
"eval_loss": 0.11447751522064209,
|
| 381 |
+
"eval_precision": 0.9533591384662554,
|
| 382 |
+
"eval_recall": 0.9536373049047053,
|
| 383 |
+
"eval_runtime": 2.8035,
|
| 384 |
+
"eval_samples_per_second": 199.752,
|
| 385 |
+
"step": 3100
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.18,
|
| 389 |
+
"eval_accuracy": 0.9553571428571429,
|
| 390 |
+
"eval_f1": 0.955237099491941,
|
| 391 |
+
"eval_loss": 0.10215133428573608,
|
| 392 |
+
"eval_precision": 0.9555180180180181,
|
| 393 |
+
"eval_recall": 0.95501144047756,
|
| 394 |
+
"eval_runtime": 2.7996,
|
| 395 |
+
"eval_samples_per_second": 200.03,
|
| 396 |
+
"step": 3200
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.19,
|
| 400 |
+
"eval_accuracy": 0.9571428571428572,
|
| 401 |
+
"eval_f1": 0.957063995093028,
|
| 402 |
+
"eval_loss": 0.10696452111005783,
|
| 403 |
+
"eval_precision": 0.9569360875841542,
|
| 404 |
+
"eval_recall": 0.9572164487223735,
|
| 405 |
+
"eval_runtime": 2.8029,
|
| 406 |
+
"eval_samples_per_second": 199.795,
|
| 407 |
+
"step": 3300
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.19,
|
| 411 |
+
"eval_accuracy": 0.9589285714285715,
|
| 412 |
+
"eval_f1": 0.9587854507521336,
|
| 413 |
+
"eval_loss": 0.10249486565589905,
|
| 414 |
+
"eval_precision": 0.9596153846153845,
|
| 415 |
+
"eval_recall": 0.9582582352264448,
|
| 416 |
+
"eval_runtime": 2.8023,
|
| 417 |
+
"eval_samples_per_second": 199.835,
|
| 418 |
+
"step": 3400
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.2,
|
| 422 |
+
"learning_rate": 1.599611050735e-05,
|
| 423 |
+
"loss": 0.1469,
|
| 424 |
+
"step": 3500
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.2,
|
| 428 |
+
"eval_accuracy": 0.9660714285714286,
|
| 429 |
+
"eval_f1": 0.96593837535014,
|
| 430 |
+
"eval_loss": 0.09906778484582901,
|
| 431 |
+
"eval_precision": 0.96713126957236,
|
| 432 |
+
"eval_recall": 0.9652503483273893,
|
| 433 |
+
"eval_runtime": 2.8009,
|
| 434 |
+
"eval_samples_per_second": 199.939,
|
| 435 |
+
"step": 3500
|
| 436 |
+
}
|
| 437 |
+
],
|
| 438 |
+
"max_steps": 17483,
|
| 439 |
+
"num_train_epochs": 1,
|
| 440 |
+
"total_flos": 9417555087360000,
|
| 441 |
+
"trial_name": null,
|
| 442 |
+
"trial_params": null
|
| 443 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46827ca230dfee8f8517577b8c8830bbf17f1316c8e228d01ac56855ecdf1cef
|
| 3 |
+
size 2159
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|