Upload 10 files
Browse files- all_results.json +8 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- train_results.json +8 -0
- trainer_state.json +376 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.5101455471208018,
|
| 4 |
+
"train_runtime": 502.263,
|
| 5 |
+
"train_samples": 987,
|
| 6 |
+
"train_samples_per_second": 9.826,
|
| 7 |
+
"train_steps_per_second": 1.234
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3"
|
| 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 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"model_type": "bert",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.28.1",
|
| 36 |
+
"type_vocab_size": 2,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 30522
|
| 39 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a606824e3321634b007049f9a6fe04b166bbc89031860779d253d880d7b33f8e
|
| 3 |
+
size 438014514
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "BertTokenizer",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.5101455471208018,
|
| 4 |
+
"train_runtime": 502.263,
|
| 5 |
+
"train_samples": 987,
|
| 6 |
+
"train_samples_per_second": 9.826,
|
| 7 |
+
"train_steps_per_second": 1.234
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9333333333333333,
|
| 3 |
+
"best_model_checkpoint": "checkpoint-llm-dist-llm-label/checkpoint-620",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 620,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 9.806451612903226e-05,
|
| 13 |
+
"loss": 1.4271,
|
| 14 |
+
"step": 12
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.19,
|
| 18 |
+
"learning_rate": 9.612903225806452e-05,
|
| 19 |
+
"loss": 1.4115,
|
| 20 |
+
"step": 24
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.29,
|
| 24 |
+
"learning_rate": 9.419354838709677e-05,
|
| 25 |
+
"loss": 1.3136,
|
| 26 |
+
"step": 36
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.39,
|
| 30 |
+
"learning_rate": 9.225806451612904e-05,
|
| 31 |
+
"loss": 1.0853,
|
| 32 |
+
"step": 48
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.48,
|
| 36 |
+
"learning_rate": 9.032258064516129e-05,
|
| 37 |
+
"loss": 1.0351,
|
| 38 |
+
"step": 60
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.58,
|
| 42 |
+
"learning_rate": 8.838709677419355e-05,
|
| 43 |
+
"loss": 1.0471,
|
| 44 |
+
"step": 72
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.68,
|
| 48 |
+
"learning_rate": 8.645161290322581e-05,
|
| 49 |
+
"loss": 0.7519,
|
| 50 |
+
"step": 84
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.77,
|
| 54 |
+
"learning_rate": 8.451612903225808e-05,
|
| 55 |
+
"loss": 0.6824,
|
| 56 |
+
"step": 96
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.87,
|
| 60 |
+
"learning_rate": 8.258064516129033e-05,
|
| 61 |
+
"loss": 0.4936,
|
| 62 |
+
"step": 108
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.97,
|
| 66 |
+
"learning_rate": 8.064516129032258e-05,
|
| 67 |
+
"loss": 0.5984,
|
| 68 |
+
"step": 120
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.0,
|
| 72 |
+
"eval_accuracy": 0.8769230769230769,
|
| 73 |
+
"eval_loss": 0.5207357406616211,
|
| 74 |
+
"eval_runtime": 5.3806,
|
| 75 |
+
"eval_samples_per_second": 36.241,
|
| 76 |
+
"eval_steps_per_second": 4.646,
|
| 77 |
+
"step": 124
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.06,
|
| 81 |
+
"learning_rate": 7.870967741935484e-05,
|
| 82 |
+
"loss": 0.7002,
|
| 83 |
+
"step": 132
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.16,
|
| 87 |
+
"learning_rate": 7.67741935483871e-05,
|
| 88 |
+
"loss": 0.5281,
|
| 89 |
+
"step": 144
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.26,
|
| 93 |
+
"learning_rate": 7.483870967741936e-05,
|
| 94 |
+
"loss": 0.4103,
|
| 95 |
+
"step": 156
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.35,
|
| 99 |
+
"learning_rate": 7.290322580645161e-05,
|
| 100 |
+
"loss": 0.2259,
|
| 101 |
+
"step": 168
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.45,
|
| 105 |
+
"learning_rate": 7.096774193548388e-05,
|
| 106 |
+
"loss": 0.7418,
|
| 107 |
+
"step": 180
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.55,
|
| 111 |
+
"learning_rate": 6.903225806451613e-05,
|
| 112 |
+
"loss": 0.8794,
|
| 113 |
+
"step": 192
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.65,
|
| 117 |
+
"learning_rate": 6.709677419354839e-05,
|
| 118 |
+
"loss": 0.3744,
|
| 119 |
+
"step": 204
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.74,
|
| 123 |
+
"learning_rate": 6.516129032258065e-05,
|
| 124 |
+
"loss": 0.5089,
|
| 125 |
+
"step": 216
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.84,
|
| 129 |
+
"learning_rate": 6.32258064516129e-05,
|
| 130 |
+
"loss": 0.438,
|
| 131 |
+
"step": 228
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.94,
|
| 135 |
+
"learning_rate": 6.129032258064517e-05,
|
| 136 |
+
"loss": 0.6729,
|
| 137 |
+
"step": 240
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.0,
|
| 141 |
+
"eval_accuracy": 0.9230769230769231,
|
| 142 |
+
"eval_loss": 0.3991715610027313,
|
| 143 |
+
"eval_runtime": 5.4603,
|
| 144 |
+
"eval_samples_per_second": 35.712,
|
| 145 |
+
"eval_steps_per_second": 4.578,
|
| 146 |
+
"step": 248
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.03,
|
| 150 |
+
"learning_rate": 5.935483870967742e-05,
|
| 151 |
+
"loss": 0.466,
|
| 152 |
+
"step": 252
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.13,
|
| 156 |
+
"learning_rate": 5.7419354838709685e-05,
|
| 157 |
+
"loss": 0.3185,
|
| 158 |
+
"step": 264
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.23,
|
| 162 |
+
"learning_rate": 5.5483870967741936e-05,
|
| 163 |
+
"loss": 0.6499,
|
| 164 |
+
"step": 276
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.32,
|
| 168 |
+
"learning_rate": 5.35483870967742e-05,
|
| 169 |
+
"loss": 0.2163,
|
| 170 |
+
"step": 288
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.42,
|
| 174 |
+
"learning_rate": 5.161290322580645e-05,
|
| 175 |
+
"loss": 0.4336,
|
| 176 |
+
"step": 300
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.52,
|
| 180 |
+
"learning_rate": 4.967741935483871e-05,
|
| 181 |
+
"loss": 0.3656,
|
| 182 |
+
"step": 312
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.61,
|
| 186 |
+
"learning_rate": 4.774193548387097e-05,
|
| 187 |
+
"loss": 0.5974,
|
| 188 |
+
"step": 324
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.71,
|
| 192 |
+
"learning_rate": 4.580645161290323e-05,
|
| 193 |
+
"loss": 0.3766,
|
| 194 |
+
"step": 336
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.81,
|
| 198 |
+
"learning_rate": 4.387096774193549e-05,
|
| 199 |
+
"loss": 0.4473,
|
| 200 |
+
"step": 348
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.9,
|
| 204 |
+
"learning_rate": 4.1935483870967746e-05,
|
| 205 |
+
"loss": 0.4135,
|
| 206 |
+
"step": 360
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.0,
|
| 210 |
+
"learning_rate": 4e-05,
|
| 211 |
+
"loss": 0.173,
|
| 212 |
+
"step": 372
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.0,
|
| 216 |
+
"eval_accuracy": 0.9282051282051282,
|
| 217 |
+
"eval_loss": 0.37362906336784363,
|
| 218 |
+
"eval_runtime": 5.5298,
|
| 219 |
+
"eval_samples_per_second": 35.263,
|
| 220 |
+
"eval_steps_per_second": 4.521,
|
| 221 |
+
"step": 372
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 3.1,
|
| 225 |
+
"learning_rate": 3.8064516129032254e-05,
|
| 226 |
+
"loss": 0.3401,
|
| 227 |
+
"step": 384
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.19,
|
| 231 |
+
"learning_rate": 3.612903225806452e-05,
|
| 232 |
+
"loss": 0.1776,
|
| 233 |
+
"step": 396
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.29,
|
| 237 |
+
"learning_rate": 3.4193548387096776e-05,
|
| 238 |
+
"loss": 0.2485,
|
| 239 |
+
"step": 408
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.39,
|
| 243 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 244 |
+
"loss": 0.5576,
|
| 245 |
+
"step": 420
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.48,
|
| 249 |
+
"learning_rate": 3.032258064516129e-05,
|
| 250 |
+
"loss": 0.4437,
|
| 251 |
+
"step": 432
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.58,
|
| 255 |
+
"learning_rate": 2.838709677419355e-05,
|
| 256 |
+
"loss": 0.5132,
|
| 257 |
+
"step": 444
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.68,
|
| 261 |
+
"learning_rate": 2.645161290322581e-05,
|
| 262 |
+
"loss": 0.2877,
|
| 263 |
+
"step": 456
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.77,
|
| 267 |
+
"learning_rate": 2.4516129032258064e-05,
|
| 268 |
+
"loss": 0.4377,
|
| 269 |
+
"step": 468
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.87,
|
| 273 |
+
"learning_rate": 2.258064516129032e-05,
|
| 274 |
+
"loss": 0.1697,
|
| 275 |
+
"step": 480
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.97,
|
| 279 |
+
"learning_rate": 2.0645161290322582e-05,
|
| 280 |
+
"loss": 0.2741,
|
| 281 |
+
"step": 492
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 4.0,
|
| 285 |
+
"eval_accuracy": 0.9282051282051282,
|
| 286 |
+
"eval_loss": 0.377105176448822,
|
| 287 |
+
"eval_runtime": 5.5428,
|
| 288 |
+
"eval_samples_per_second": 35.181,
|
| 289 |
+
"eval_steps_per_second": 4.51,
|
| 290 |
+
"step": 496
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.06,
|
| 294 |
+
"learning_rate": 1.870967741935484e-05,
|
| 295 |
+
"loss": 0.379,
|
| 296 |
+
"step": 504
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.16,
|
| 300 |
+
"learning_rate": 1.6774193548387098e-05,
|
| 301 |
+
"loss": 0.1826,
|
| 302 |
+
"step": 516
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.26,
|
| 306 |
+
"learning_rate": 1.4838709677419355e-05,
|
| 307 |
+
"loss": 0.3932,
|
| 308 |
+
"step": 528
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.35,
|
| 312 |
+
"learning_rate": 1.2903225806451613e-05,
|
| 313 |
+
"loss": 0.3326,
|
| 314 |
+
"step": 540
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.45,
|
| 318 |
+
"learning_rate": 1.0967741935483872e-05,
|
| 319 |
+
"loss": 0.1451,
|
| 320 |
+
"step": 552
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.55,
|
| 324 |
+
"learning_rate": 9.03225806451613e-06,
|
| 325 |
+
"loss": 0.3364,
|
| 326 |
+
"step": 564
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.65,
|
| 330 |
+
"learning_rate": 7.096774193548387e-06,
|
| 331 |
+
"loss": 0.2966,
|
| 332 |
+
"step": 576
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.74,
|
| 336 |
+
"learning_rate": 5.161290322580646e-06,
|
| 337 |
+
"loss": 0.3227,
|
| 338 |
+
"step": 588
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.84,
|
| 342 |
+
"learning_rate": 3.225806451612903e-06,
|
| 343 |
+
"loss": 0.3128,
|
| 344 |
+
"step": 600
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.94,
|
| 348 |
+
"learning_rate": 1.2903225806451614e-06,
|
| 349 |
+
"loss": 0.3511,
|
| 350 |
+
"step": 612
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 5.0,
|
| 354 |
+
"eval_accuracy": 0.9333333333333333,
|
| 355 |
+
"eval_loss": 0.33735406398773193,
|
| 356 |
+
"eval_runtime": 5.5434,
|
| 357 |
+
"eval_samples_per_second": 35.177,
|
| 358 |
+
"eval_steps_per_second": 4.51,
|
| 359 |
+
"step": 620
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 5.0,
|
| 363 |
+
"step": 620,
|
| 364 |
+
"total_flos": 1298476374773760.0,
|
| 365 |
+
"train_loss": 0.5101455471208018,
|
| 366 |
+
"train_runtime": 502.263,
|
| 367 |
+
"train_samples_per_second": 9.826,
|
| 368 |
+
"train_steps_per_second": 1.234
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"max_steps": 620,
|
| 372 |
+
"num_train_epochs": 5,
|
| 373 |
+
"total_flos": 1298476374773760.0,
|
| 374 |
+
"trial_name": null,
|
| 375 |
+
"trial_params": null
|
| 376 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d98da5501fd0befae3b2de99751e25e6c81730a87d17c770dc824a71f9fbca21
|
| 3 |
+
size 4536
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|