Ubuntu
commited on
Commit
•
3560942
1
Parent(s):
c9a916a
initial update
Browse files- all_results.json +15 -0
- config.json +26 -0
- eval_results.json +11 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +7 -0
- trainer_state.json +432 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9108830076675736,
|
| 4 |
+
"eval_combined_score": 0.8954854350082802,
|
| 5 |
+
"eval_f1": 0.8800878623489866,
|
| 6 |
+
"eval_loss": 0.28048861026763916,
|
| 7 |
+
"eval_runtime": 286.7534,
|
| 8 |
+
"eval_samples": 40430,
|
| 9 |
+
"eval_samples_per_second": 140.992,
|
| 10 |
+
"eval_steps_per_second": 17.625,
|
| 11 |
+
"train_runtime": 17616.6269,
|
| 12 |
+
"train_samples": 363846,
|
| 13 |
+
"train_samples_per_second": 61.961,
|
| 14 |
+
"train_steps_per_second": 1.936
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"finetuning_task": "qqp",
|
| 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 |
+
"transformers_version": "4.7.0.dev0",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 30522
|
| 26 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9108830076675736,
|
| 4 |
+
"eval_combined_score": 0.8954854350082802,
|
| 5 |
+
"eval_f1": 0.8800878623489866,
|
| 6 |
+
"eval_loss": 0.28048861026763916,
|
| 7 |
+
"eval_runtime": 286.7534,
|
| 8 |
+
"eval_samples": 40430,
|
| 9 |
+
"eval_samples_per_second": 140.992,
|
| 10 |
+
"eval_steps_per_second": 17.625
|
| 11 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b80c1ec4fc936112e40c404d68ea0494444e0fe632f16d16c2503727fa486c2f
|
| 3 |
+
size 438022424
|
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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased"}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_runtime": 17616.6269,
|
| 4 |
+
"train_samples": 363846,
|
| 5 |
+
"train_samples_per_second": 61.961,
|
| 6 |
+
"train_steps_per_second": 1.936
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,432 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 34113,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 1.9706856623574592e-05,
|
| 13 |
+
"loss": 0.436,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 1.9413713247149183e-05,
|
| 19 |
+
"loss": 0.3602,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.13,
|
| 24 |
+
"learning_rate": 1.9120569870723774e-05,
|
| 25 |
+
"loss": 0.3448,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.18,
|
| 30 |
+
"learning_rate": 1.882742649429836e-05,
|
| 31 |
+
"loss": 0.3243,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.22,
|
| 36 |
+
"learning_rate": 1.8534283117872952e-05,
|
| 37 |
+
"loss": 0.3147,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.26,
|
| 42 |
+
"learning_rate": 1.8241139741447543e-05,
|
| 43 |
+
"loss": 0.3057,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.31,
|
| 48 |
+
"learning_rate": 1.7947996365022134e-05,
|
| 49 |
+
"loss": 0.3029,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.35,
|
| 54 |
+
"learning_rate": 1.7654852988596725e-05,
|
| 55 |
+
"loss": 0.2968,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.4,
|
| 60 |
+
"learning_rate": 1.7361709612171312e-05,
|
| 61 |
+
"loss": 0.2983,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.44,
|
| 66 |
+
"learning_rate": 1.7068566235745903e-05,
|
| 67 |
+
"loss": 0.2855,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.48,
|
| 72 |
+
"learning_rate": 1.6775422859320497e-05,
|
| 73 |
+
"loss": 0.2801,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.53,
|
| 78 |
+
"learning_rate": 1.6482279482895085e-05,
|
| 79 |
+
"loss": 0.2733,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.57,
|
| 84 |
+
"learning_rate": 1.6189136106469676e-05,
|
| 85 |
+
"loss": 0.2706,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.62,
|
| 90 |
+
"learning_rate": 1.5895992730044266e-05,
|
| 91 |
+
"loss": 0.2649,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.66,
|
| 96 |
+
"learning_rate": 1.5602849353618857e-05,
|
| 97 |
+
"loss": 0.2586,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.7,
|
| 102 |
+
"learning_rate": 1.5309705977193448e-05,
|
| 103 |
+
"loss": 0.2766,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.75,
|
| 108 |
+
"learning_rate": 1.5016562600768037e-05,
|
| 109 |
+
"loss": 0.2589,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.79,
|
| 114 |
+
"learning_rate": 1.4723419224342628e-05,
|
| 115 |
+
"loss": 0.2594,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.84,
|
| 120 |
+
"learning_rate": 1.4430275847917217e-05,
|
| 121 |
+
"loss": 0.2527,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.88,
|
| 126 |
+
"learning_rate": 1.4137132471491808e-05,
|
| 127 |
+
"loss": 0.2492,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.92,
|
| 132 |
+
"learning_rate": 1.3843989095066399e-05,
|
| 133 |
+
"loss": 0.2489,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.97,
|
| 138 |
+
"learning_rate": 1.3550845718640988e-05,
|
| 139 |
+
"loss": 0.2477,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.01,
|
| 144 |
+
"learning_rate": 1.3257702342215579e-05,
|
| 145 |
+
"loss": 0.2279,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.06,
|
| 150 |
+
"learning_rate": 1.2964558965790168e-05,
|
| 151 |
+
"loss": 0.1883,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.1,
|
| 156 |
+
"learning_rate": 1.2671415589364759e-05,
|
| 157 |
+
"loss": 0.1798,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.14,
|
| 162 |
+
"learning_rate": 1.2378272212939351e-05,
|
| 163 |
+
"loss": 0.1834,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.19,
|
| 168 |
+
"learning_rate": 1.208512883651394e-05,
|
| 169 |
+
"loss": 0.1849,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.23,
|
| 174 |
+
"learning_rate": 1.1791985460088531e-05,
|
| 175 |
+
"loss": 0.1887,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.28,
|
| 180 |
+
"learning_rate": 1.149884208366312e-05,
|
| 181 |
+
"loss": 0.1806,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.32,
|
| 186 |
+
"learning_rate": 1.1205698707237711e-05,
|
| 187 |
+
"loss": 0.1824,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.36,
|
| 192 |
+
"learning_rate": 1.0912555330812302e-05,
|
| 193 |
+
"loss": 0.1862,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.41,
|
| 198 |
+
"learning_rate": 1.0619411954386891e-05,
|
| 199 |
+
"loss": 0.1839,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.45,
|
| 204 |
+
"learning_rate": 1.0326268577961482e-05,
|
| 205 |
+
"loss": 0.1802,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.5,
|
| 210 |
+
"learning_rate": 1.0033125201536071e-05,
|
| 211 |
+
"loss": 0.1795,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.54,
|
| 216 |
+
"learning_rate": 9.739981825110662e-06,
|
| 217 |
+
"loss": 0.1835,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.58,
|
| 222 |
+
"learning_rate": 9.446838448685253e-06,
|
| 223 |
+
"loss": 0.1805,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.63,
|
| 228 |
+
"learning_rate": 9.153695072259843e-06,
|
| 229 |
+
"loss": 0.1811,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.67,
|
| 234 |
+
"learning_rate": 8.860551695834433e-06,
|
| 235 |
+
"loss": 0.1793,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.71,
|
| 240 |
+
"learning_rate": 8.567408319409023e-06,
|
| 241 |
+
"loss": 0.1827,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.76,
|
| 246 |
+
"learning_rate": 8.274264942983614e-06,
|
| 247 |
+
"loss": 0.1763,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.8,
|
| 252 |
+
"learning_rate": 7.981121566558205e-06,
|
| 253 |
+
"loss": 0.1801,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.85,
|
| 258 |
+
"learning_rate": 7.687978190132794e-06,
|
| 259 |
+
"loss": 0.1839,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.89,
|
| 264 |
+
"learning_rate": 7.394834813707384e-06,
|
| 265 |
+
"loss": 0.1756,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.93,
|
| 270 |
+
"learning_rate": 7.101691437281976e-06,
|
| 271 |
+
"loss": 0.1784,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.98,
|
| 276 |
+
"learning_rate": 6.808548060856566e-06,
|
| 277 |
+
"loss": 0.169,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.02,
|
| 282 |
+
"learning_rate": 6.515404684431156e-06,
|
| 283 |
+
"loss": 0.1475,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.07,
|
| 288 |
+
"learning_rate": 6.222261308005746e-06,
|
| 289 |
+
"loss": 0.1214,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.11,
|
| 294 |
+
"learning_rate": 5.929117931580336e-06,
|
| 295 |
+
"loss": 0.1157,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.15,
|
| 300 |
+
"learning_rate": 5.6359745551549274e-06,
|
| 301 |
+
"loss": 0.1188,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.2,
|
| 306 |
+
"learning_rate": 5.3428311787295174e-06,
|
| 307 |
+
"loss": 0.1157,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.24,
|
| 312 |
+
"learning_rate": 5.049687802304107e-06,
|
| 313 |
+
"loss": 0.1207,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.29,
|
| 318 |
+
"learning_rate": 4.756544425878697e-06,
|
| 319 |
+
"loss": 0.1286,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.33,
|
| 324 |
+
"learning_rate": 4.463401049453288e-06,
|
| 325 |
+
"loss": 0.1237,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.37,
|
| 330 |
+
"learning_rate": 4.170257673027878e-06,
|
| 331 |
+
"loss": 0.1218,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.42,
|
| 336 |
+
"learning_rate": 3.877114296602469e-06,
|
| 337 |
+
"loss": 0.1259,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.46,
|
| 342 |
+
"learning_rate": 3.583970920177059e-06,
|
| 343 |
+
"loss": 0.1156,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.51,
|
| 348 |
+
"learning_rate": 3.290827543751649e-06,
|
| 349 |
+
"loss": 0.1206,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.55,
|
| 354 |
+
"learning_rate": 2.9976841673262398e-06,
|
| 355 |
+
"loss": 0.1136,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.59,
|
| 360 |
+
"learning_rate": 2.7045407909008298e-06,
|
| 361 |
+
"loss": 0.1169,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.64,
|
| 366 |
+
"learning_rate": 2.41139741447542e-06,
|
| 367 |
+
"loss": 0.1162,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.68,
|
| 372 |
+
"learning_rate": 2.1182540380500106e-06,
|
| 373 |
+
"loss": 0.1142,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.73,
|
| 378 |
+
"learning_rate": 1.825110661624601e-06,
|
| 379 |
+
"loss": 0.1092,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.77,
|
| 384 |
+
"learning_rate": 1.531967285199191e-06,
|
| 385 |
+
"loss": 0.119,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.81,
|
| 390 |
+
"learning_rate": 1.2388239087737813e-06,
|
| 391 |
+
"loss": 0.1162,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.86,
|
| 396 |
+
"learning_rate": 9.456805323483717e-07,
|
| 397 |
+
"loss": 0.1224,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.9,
|
| 402 |
+
"learning_rate": 6.525371559229619e-07,
|
| 403 |
+
"loss": 0.1157,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.95,
|
| 408 |
+
"learning_rate": 3.5939377949755233e-07,
|
| 409 |
+
"loss": 0.1188,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.99,
|
| 414 |
+
"learning_rate": 6.62504030721426e-08,
|
| 415 |
+
"loss": 0.1148,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.0,
|
| 420 |
+
"step": 34113,
|
| 421 |
+
"total_flos": 9.178038072619315e+16,
|
| 422 |
+
"train_runtime": 17616.6269,
|
| 423 |
+
"train_samples_per_second": 61.961,
|
| 424 |
+
"train_steps_per_second": 1.936
|
| 425 |
+
}
|
| 426 |
+
],
|
| 427 |
+
"max_steps": 34113,
|
| 428 |
+
"num_train_epochs": 3,
|
| 429 |
+
"total_flos": 9.178038072619315e+16,
|
| 430 |
+
"trial_name": null,
|
| 431 |
+
"trial_params": null
|
| 432 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e112ed29e1c43376f78766507aed42293413f4d8d28d051edfa4b3df873f70d8
|
| 3 |
+
size 2415
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|