Upload 7 files
Browse files- config.json +27 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +471 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.36.2",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de29e05d81697e6bb1e140f8cf188997b410e6b463ec6a348b0ae2cd855f06a6
|
| 3 |
+
size 437958648
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2be57d396198d362ec9b7d9e2813bafe1e32ace0cd716d3144615f2ad9f4ddc2
|
| 3 |
+
size 685336698
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f9e2089fe2e0e8a65b931477ab0cc88455960658c36ac46f76df78951e957f2
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ad0b210d28eca9af8faf38af1583a6da9c479ba4356c9dec900c40d2425d120
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,471 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9975,
|
| 3 |
+
"best_model_checkpoint": "./tr_results/checkpoint-1200",
|
| 4 |
+
"epoch": 12.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.98,
|
| 14 |
+
"eval_classification_report": {
|
| 15 |
+
"accuracy": 0.98,
|
| 16 |
+
"macro avg": {
|
| 17 |
+
"f1-score": 0.9799979997999799,
|
| 18 |
+
"precision": 0.9801920768307323,
|
| 19 |
+
"recall": 0.98,
|
| 20 |
+
"support": 800.0
|
| 21 |
+
},
|
| 22 |
+
"neural": {
|
| 23 |
+
"f1-score": 0.9797979797979798,
|
| 24 |
+
"precision": 0.9897959183673469,
|
| 25 |
+
"recall": 0.97,
|
| 26 |
+
"support": 400.0
|
| 27 |
+
},
|
| 28 |
+
"real": {
|
| 29 |
+
"f1-score": 0.9801980198019802,
|
| 30 |
+
"precision": 0.9705882352941176,
|
| 31 |
+
"recall": 0.99,
|
| 32 |
+
"support": 400.0
|
| 33 |
+
},
|
| 34 |
+
"weighted avg": {
|
| 35 |
+
"f1-score": 0.97999799979998,
|
| 36 |
+
"precision": 0.9801920768307323,
|
| 37 |
+
"recall": 0.98,
|
| 38 |
+
"support": 800.0
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"eval_loss": 0.08059845864772797,
|
| 42 |
+
"eval_runtime": 44.1793,
|
| 43 |
+
"eval_samples_per_second": 18.108,
|
| 44 |
+
"eval_steps_per_second": 1.132,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.0,
|
| 49 |
+
"eval_accuracy": 0.9925,
|
| 50 |
+
"eval_classification_report": {
|
| 51 |
+
"accuracy": 0.9925,
|
| 52 |
+
"macro avg": {
|
| 53 |
+
"f1-score": 0.9924995781012682,
|
| 54 |
+
"precision": 0.9926108374384237,
|
| 55 |
+
"recall": 0.9924999999999999,
|
| 56 |
+
"support": 800.0
|
| 57 |
+
},
|
| 58 |
+
"neural": {
|
| 59 |
+
"f1-score": 0.9925558312655086,
|
| 60 |
+
"precision": 0.9852216748768473,
|
| 61 |
+
"recall": 1.0,
|
| 62 |
+
"support": 400.0
|
| 63 |
+
},
|
| 64 |
+
"real": {
|
| 65 |
+
"f1-score": 0.9924433249370278,
|
| 66 |
+
"precision": 1.0,
|
| 67 |
+
"recall": 0.985,
|
| 68 |
+
"support": 400.0
|
| 69 |
+
},
|
| 70 |
+
"weighted avg": {
|
| 71 |
+
"f1-score": 0.9924995781012683,
|
| 72 |
+
"precision": 0.9926108374384236,
|
| 73 |
+
"recall": 0.9925,
|
| 74 |
+
"support": 800.0
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
"eval_loss": 0.03137431666254997,
|
| 78 |
+
"eval_runtime": 37.0926,
|
| 79 |
+
"eval_samples_per_second": 21.568,
|
| 80 |
+
"eval_steps_per_second": 1.348,
|
| 81 |
+
"step": 300
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.0,
|
| 85 |
+
"eval_accuracy": 0.93,
|
| 86 |
+
"eval_classification_report": {
|
| 87 |
+
"accuracy": 0.93,
|
| 88 |
+
"macro avg": {
|
| 89 |
+
"f1-score": 0.9296553110240177,
|
| 90 |
+
"precision": 0.9385964912280702,
|
| 91 |
+
"recall": 0.9299999999999999,
|
| 92 |
+
"support": 800.0
|
| 93 |
+
},
|
| 94 |
+
"neural": {
|
| 95 |
+
"f1-score": 0.924731182795699,
|
| 96 |
+
"precision": 1.0,
|
| 97 |
+
"recall": 0.86,
|
| 98 |
+
"support": 400.0
|
| 99 |
+
},
|
| 100 |
+
"real": {
|
| 101 |
+
"f1-score": 0.9345794392523363,
|
| 102 |
+
"precision": 0.8771929824561403,
|
| 103 |
+
"recall": 1.0,
|
| 104 |
+
"support": 400.0
|
| 105 |
+
},
|
| 106 |
+
"weighted avg": {
|
| 107 |
+
"f1-score": 0.9296553110240177,
|
| 108 |
+
"precision": 0.9385964912280701,
|
| 109 |
+
"recall": 0.93,
|
| 110 |
+
"support": 800.0
|
| 111 |
+
}
|
| 112 |
+
},
|
| 113 |
+
"eval_loss": 0.40115270018577576,
|
| 114 |
+
"eval_runtime": 36.1218,
|
| 115 |
+
"eval_samples_per_second": 22.147,
|
| 116 |
+
"eval_steps_per_second": 1.384,
|
| 117 |
+
"step": 450
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.33,
|
| 121 |
+
"learning_rate": 5e-05,
|
| 122 |
+
"loss": 0.1716,
|
| 123 |
+
"step": 500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.0,
|
| 127 |
+
"eval_accuracy": 0.9925,
|
| 128 |
+
"eval_classification_report": {
|
| 129 |
+
"accuracy": 0.9925,
|
| 130 |
+
"macro avg": {
|
| 131 |
+
"f1-score": 0.9924995781012682,
|
| 132 |
+
"precision": 0.9926108374384237,
|
| 133 |
+
"recall": 0.9924999999999999,
|
| 134 |
+
"support": 800.0
|
| 135 |
+
},
|
| 136 |
+
"neural": {
|
| 137 |
+
"f1-score": 0.9924433249370278,
|
| 138 |
+
"precision": 1.0,
|
| 139 |
+
"recall": 0.985,
|
| 140 |
+
"support": 400.0
|
| 141 |
+
},
|
| 142 |
+
"real": {
|
| 143 |
+
"f1-score": 0.9925558312655086,
|
| 144 |
+
"precision": 0.9852216748768473,
|
| 145 |
+
"recall": 1.0,
|
| 146 |
+
"support": 400.0
|
| 147 |
+
},
|
| 148 |
+
"weighted avg": {
|
| 149 |
+
"f1-score": 0.9924995781012683,
|
| 150 |
+
"precision": 0.9926108374384236,
|
| 151 |
+
"recall": 0.9925,
|
| 152 |
+
"support": 800.0
|
| 153 |
+
}
|
| 154 |
+
},
|
| 155 |
+
"eval_loss": 0.03166389465332031,
|
| 156 |
+
"eval_runtime": 45.4896,
|
| 157 |
+
"eval_samples_per_second": 17.586,
|
| 158 |
+
"eval_steps_per_second": 1.099,
|
| 159 |
+
"step": 600
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.0,
|
| 163 |
+
"eval_accuracy": 0.9825,
|
| 164 |
+
"eval_classification_report": {
|
| 165 |
+
"accuracy": 0.9825,
|
| 166 |
+
"macro avg": {
|
| 167 |
+
"f1-score": 0.9824946389831886,
|
| 168 |
+
"precision": 0.9830917874396135,
|
| 169 |
+
"recall": 0.9824999999999999,
|
| 170 |
+
"support": 800.0
|
| 171 |
+
},
|
| 172 |
+
"neural": {
|
| 173 |
+
"f1-score": 0.9828009828009828,
|
| 174 |
+
"precision": 0.966183574879227,
|
| 175 |
+
"recall": 1.0,
|
| 176 |
+
"support": 400.0
|
| 177 |
+
},
|
| 178 |
+
"real": {
|
| 179 |
+
"f1-score": 0.9821882951653944,
|
| 180 |
+
"precision": 1.0,
|
| 181 |
+
"recall": 0.965,
|
| 182 |
+
"support": 400.0
|
| 183 |
+
},
|
| 184 |
+
"weighted avg": {
|
| 185 |
+
"f1-score": 0.9824946389831887,
|
| 186 |
+
"precision": 0.9830917874396136,
|
| 187 |
+
"recall": 0.9825,
|
| 188 |
+
"support": 800.0
|
| 189 |
+
}
|
| 190 |
+
},
|
| 191 |
+
"eval_loss": 0.06639690697193146,
|
| 192 |
+
"eval_runtime": 45.9078,
|
| 193 |
+
"eval_samples_per_second": 17.426,
|
| 194 |
+
"eval_steps_per_second": 1.089,
|
| 195 |
+
"step": 750
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 6.0,
|
| 199 |
+
"eval_accuracy": 0.995,
|
| 200 |
+
"eval_classification_report": {
|
| 201 |
+
"accuracy": 0.995,
|
| 202 |
+
"macro avg": {
|
| 203 |
+
"f1-score": 0.9949998749968749,
|
| 204 |
+
"precision": 0.995049504950495,
|
| 205 |
+
"recall": 0.995,
|
| 206 |
+
"support": 800.0
|
| 207 |
+
},
|
| 208 |
+
"neural": {
|
| 209 |
+
"f1-score": 0.9949748743718593,
|
| 210 |
+
"precision": 1.0,
|
| 211 |
+
"recall": 0.99,
|
| 212 |
+
"support": 400.0
|
| 213 |
+
},
|
| 214 |
+
"real": {
|
| 215 |
+
"f1-score": 0.9950248756218906,
|
| 216 |
+
"precision": 0.9900990099009901,
|
| 217 |
+
"recall": 1.0,
|
| 218 |
+
"support": 400.0
|
| 219 |
+
},
|
| 220 |
+
"weighted avg": {
|
| 221 |
+
"f1-score": 0.9949998749968749,
|
| 222 |
+
"precision": 0.9950495049504952,
|
| 223 |
+
"recall": 0.995,
|
| 224 |
+
"support": 800.0
|
| 225 |
+
}
|
| 226 |
+
},
|
| 227 |
+
"eval_loss": 0.01404611486941576,
|
| 228 |
+
"eval_runtime": 44.8322,
|
| 229 |
+
"eval_samples_per_second": 17.844,
|
| 230 |
+
"eval_steps_per_second": 1.115,
|
| 231 |
+
"step": 900
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 6.67,
|
| 235 |
+
"learning_rate": 4.827586206896552e-05,
|
| 236 |
+
"loss": 0.0304,
|
| 237 |
+
"step": 1000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 7.0,
|
| 241 |
+
"eval_accuracy": 0.98625,
|
| 242 |
+
"eval_classification_report": {
|
| 243 |
+
"accuracy": 0.98625,
|
| 244 |
+
"macro avg": {
|
| 245 |
+
"f1-score": 0.9862473998990433,
|
| 246 |
+
"precision": 0.9866180048661801,
|
| 247 |
+
"recall": 0.9862500000000001,
|
| 248 |
+
"support": 800.0
|
| 249 |
+
},
|
| 250 |
+
"neural": {
|
| 251 |
+
"f1-score": 0.9860583016476552,
|
| 252 |
+
"precision": 1.0,
|
| 253 |
+
"recall": 0.9725,
|
| 254 |
+
"support": 400.0
|
| 255 |
+
},
|
| 256 |
+
"real": {
|
| 257 |
+
"f1-score": 0.9864364981504316,
|
| 258 |
+
"precision": 0.9732360097323601,
|
| 259 |
+
"recall": 1.0,
|
| 260 |
+
"support": 400.0
|
| 261 |
+
},
|
| 262 |
+
"weighted avg": {
|
| 263 |
+
"f1-score": 0.9862473998990434,
|
| 264 |
+
"precision": 0.98661800486618,
|
| 265 |
+
"recall": 0.98625,
|
| 266 |
+
"support": 800.0
|
| 267 |
+
}
|
| 268 |
+
},
|
| 269 |
+
"eval_loss": 0.06141611561179161,
|
| 270 |
+
"eval_runtime": 44.6418,
|
| 271 |
+
"eval_samples_per_second": 17.92,
|
| 272 |
+
"eval_steps_per_second": 1.12,
|
| 273 |
+
"step": 1050
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.0,
|
| 277 |
+
"eval_accuracy": 0.9975,
|
| 278 |
+
"eval_classification_report": {
|
| 279 |
+
"accuracy": 0.9975,
|
| 280 |
+
"macro avg": {
|
| 281 |
+
"f1-score": 0.9974999843749024,
|
| 282 |
+
"precision": 0.9975124378109452,
|
| 283 |
+
"recall": 0.9975,
|
| 284 |
+
"support": 800.0
|
| 285 |
+
},
|
| 286 |
+
"neural": {
|
| 287 |
+
"f1-score": 0.9974937343358395,
|
| 288 |
+
"precision": 1.0,
|
| 289 |
+
"recall": 0.995,
|
| 290 |
+
"support": 400.0
|
| 291 |
+
},
|
| 292 |
+
"real": {
|
| 293 |
+
"f1-score": 0.9975062344139651,
|
| 294 |
+
"precision": 0.9950248756218906,
|
| 295 |
+
"recall": 1.0,
|
| 296 |
+
"support": 400.0
|
| 297 |
+
},
|
| 298 |
+
"weighted avg": {
|
| 299 |
+
"f1-score": 0.9974999843749024,
|
| 300 |
+
"precision": 0.9975124378109453,
|
| 301 |
+
"recall": 0.9975,
|
| 302 |
+
"support": 800.0
|
| 303 |
+
}
|
| 304 |
+
},
|
| 305 |
+
"eval_loss": 0.010667502880096436,
|
| 306 |
+
"eval_runtime": 35.7885,
|
| 307 |
+
"eval_samples_per_second": 22.354,
|
| 308 |
+
"eval_steps_per_second": 1.397,
|
| 309 |
+
"step": 1200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 9.0,
|
| 313 |
+
"eval_accuracy": 0.9975,
|
| 314 |
+
"eval_classification_report": {
|
| 315 |
+
"accuracy": 0.9975,
|
| 316 |
+
"macro avg": {
|
| 317 |
+
"f1-score": 0.9974999843749024,
|
| 318 |
+
"precision": 0.9975124378109452,
|
| 319 |
+
"recall": 0.9975,
|
| 320 |
+
"support": 800.0
|
| 321 |
+
},
|
| 322 |
+
"neural": {
|
| 323 |
+
"f1-score": 0.9974937343358395,
|
| 324 |
+
"precision": 1.0,
|
| 325 |
+
"recall": 0.995,
|
| 326 |
+
"support": 400.0
|
| 327 |
+
},
|
| 328 |
+
"real": {
|
| 329 |
+
"f1-score": 0.9975062344139651,
|
| 330 |
+
"precision": 0.9950248756218906,
|
| 331 |
+
"recall": 1.0,
|
| 332 |
+
"support": 400.0
|
| 333 |
+
},
|
| 334 |
+
"weighted avg": {
|
| 335 |
+
"f1-score": 0.9974999843749024,
|
| 336 |
+
"precision": 0.9975124378109453,
|
| 337 |
+
"recall": 0.9975,
|
| 338 |
+
"support": 800.0
|
| 339 |
+
}
|
| 340 |
+
},
|
| 341 |
+
"eval_loss": 0.016876069828867912,
|
| 342 |
+
"eval_runtime": 29.7468,
|
| 343 |
+
"eval_samples_per_second": 26.894,
|
| 344 |
+
"eval_steps_per_second": 1.681,
|
| 345 |
+
"step": 1350
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 10.0,
|
| 349 |
+
"learning_rate": 4.655172413793104e-05,
|
| 350 |
+
"loss": 0.0059,
|
| 351 |
+
"step": 1500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 10.0,
|
| 355 |
+
"eval_accuracy": 0.9975,
|
| 356 |
+
"eval_classification_report": {
|
| 357 |
+
"accuracy": 0.9975,
|
| 358 |
+
"macro avg": {
|
| 359 |
+
"f1-score": 0.9974999843749024,
|
| 360 |
+
"precision": 0.9975124378109452,
|
| 361 |
+
"recall": 0.9975,
|
| 362 |
+
"support": 800.0
|
| 363 |
+
},
|
| 364 |
+
"neural": {
|
| 365 |
+
"f1-score": 0.9974937343358395,
|
| 366 |
+
"precision": 1.0,
|
| 367 |
+
"recall": 0.995,
|
| 368 |
+
"support": 400.0
|
| 369 |
+
},
|
| 370 |
+
"real": {
|
| 371 |
+
"f1-score": 0.9975062344139651,
|
| 372 |
+
"precision": 0.9950248756218906,
|
| 373 |
+
"recall": 1.0,
|
| 374 |
+
"support": 400.0
|
| 375 |
+
},
|
| 376 |
+
"weighted avg": {
|
| 377 |
+
"f1-score": 0.9974999843749024,
|
| 378 |
+
"precision": 0.9975124378109453,
|
| 379 |
+
"recall": 0.9975,
|
| 380 |
+
"support": 800.0
|
| 381 |
+
}
|
| 382 |
+
},
|
| 383 |
+
"eval_loss": 0.015976013615727425,
|
| 384 |
+
"eval_runtime": 30.2383,
|
| 385 |
+
"eval_samples_per_second": 26.457,
|
| 386 |
+
"eval_steps_per_second": 1.654,
|
| 387 |
+
"step": 1500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 11.0,
|
| 391 |
+
"eval_accuracy": 0.9975,
|
| 392 |
+
"eval_classification_report": {
|
| 393 |
+
"accuracy": 0.9975,
|
| 394 |
+
"macro avg": {
|
| 395 |
+
"f1-score": 0.9974999843749024,
|
| 396 |
+
"precision": 0.9975124378109452,
|
| 397 |
+
"recall": 0.9975,
|
| 398 |
+
"support": 800.0
|
| 399 |
+
},
|
| 400 |
+
"neural": {
|
| 401 |
+
"f1-score": 0.9974937343358395,
|
| 402 |
+
"precision": 1.0,
|
| 403 |
+
"recall": 0.995,
|
| 404 |
+
"support": 400.0
|
| 405 |
+
},
|
| 406 |
+
"real": {
|
| 407 |
+
"f1-score": 0.9975062344139651,
|
| 408 |
+
"precision": 0.9950248756218906,
|
| 409 |
+
"recall": 1.0,
|
| 410 |
+
"support": 400.0
|
| 411 |
+
},
|
| 412 |
+
"weighted avg": {
|
| 413 |
+
"f1-score": 0.9974999843749024,
|
| 414 |
+
"precision": 0.9975124378109453,
|
| 415 |
+
"recall": 0.9975,
|
| 416 |
+
"support": 800.0
|
| 417 |
+
}
|
| 418 |
+
},
|
| 419 |
+
"eval_loss": 0.015417657792568207,
|
| 420 |
+
"eval_runtime": 26.7067,
|
| 421 |
+
"eval_samples_per_second": 29.955,
|
| 422 |
+
"eval_steps_per_second": 1.872,
|
| 423 |
+
"step": 1650
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 12.0,
|
| 427 |
+
"eval_accuracy": 0.9975,
|
| 428 |
+
"eval_classification_report": {
|
| 429 |
+
"accuracy": 0.9975,
|
| 430 |
+
"macro avg": {
|
| 431 |
+
"f1-score": 0.9974999843749024,
|
| 432 |
+
"precision": 0.9975124378109452,
|
| 433 |
+
"recall": 0.9975,
|
| 434 |
+
"support": 800.0
|
| 435 |
+
},
|
| 436 |
+
"neural": {
|
| 437 |
+
"f1-score": 0.9974937343358395,
|
| 438 |
+
"precision": 1.0,
|
| 439 |
+
"recall": 0.995,
|
| 440 |
+
"support": 400.0
|
| 441 |
+
},
|
| 442 |
+
"real": {
|
| 443 |
+
"f1-score": 0.9975062344139651,
|
| 444 |
+
"precision": 0.9950248756218906,
|
| 445 |
+
"recall": 1.0,
|
| 446 |
+
"support": 400.0
|
| 447 |
+
},
|
| 448 |
+
"weighted avg": {
|
| 449 |
+
"f1-score": 0.9974999843749024,
|
| 450 |
+
"precision": 0.9975124378109453,
|
| 451 |
+
"recall": 0.9975,
|
| 452 |
+
"support": 800.0
|
| 453 |
+
}
|
| 454 |
+
},
|
| 455 |
+
"eval_loss": 0.017138773575425148,
|
| 456 |
+
"eval_runtime": 28.9695,
|
| 457 |
+
"eval_samples_per_second": 27.615,
|
| 458 |
+
"eval_steps_per_second": 1.726,
|
| 459 |
+
"step": 1800
|
| 460 |
+
}
|
| 461 |
+
],
|
| 462 |
+
"logging_steps": 500,
|
| 463 |
+
"max_steps": 15000,
|
| 464 |
+
"num_input_tokens_seen": 0,
|
| 465 |
+
"num_train_epochs": 100,
|
| 466 |
+
"save_steps": 500,
|
| 467 |
+
"total_flos": 7577598394368000.0,
|
| 468 |
+
"train_batch_size": 16,
|
| 469 |
+
"trial_name": null,
|
| 470 |
+
"trial_params": null
|
| 471 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:294c56ae2e968f7ea9c4e93598e43193b8ba191c8967848e273e83eb01306723
|
| 3 |
+
size 4664
|