Upload folder using huggingface_hub
Browse files- config.json +38 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +359 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": 0.1,
|
| 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 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.44.2",
|
| 35 |
+
"type_vocab_size": 2,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 30522
|
| 38 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1374c19b29f3e0de103d588cad6f6c81008e427a0e98c2a7797e40d703b26a26
|
| 3 |
+
size 876050682
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55796294cf10705d29bccee8c3a3ae65a43cde0e4cb587deaf6611de2ad9836d
|
| 3 |
+
size 438010094
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27e506dbf77918e0ecac909bdd0cbba872cf8bd1d06bc8b9e837827ba08cc6db
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ece7331cb48e5331eee355297800419b05685e932542c8f92a527839d617fcf
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,359 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.992,
|
| 5 |
+
"eval_steps": 60,
|
| 6 |
+
"global_step": 682,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.32,
|
| 13 |
+
"grad_norm": 2.045376777648926,
|
| 14 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 15 |
+
"loss": 1.0526,
|
| 16 |
+
"step": 20
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.64,
|
| 20 |
+
"grad_norm": 3.106898784637451,
|
| 21 |
+
"learning_rate": 5.333333333333333e-05,
|
| 22 |
+
"loss": 0.725,
|
| 23 |
+
"step": 40
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.96,
|
| 27 |
+
"grad_norm": 0.8986996412277222,
|
| 28 |
+
"learning_rate": 8e-05,
|
| 29 |
+
"loss": 0.6844,
|
| 30 |
+
"step": 60
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.96,
|
| 34 |
+
"eval_loss": 0.6844361424446106,
|
| 35 |
+
"eval_runtime": 49.0643,
|
| 36 |
+
"eval_samples_per_second": 35.036,
|
| 37 |
+
"eval_steps_per_second": 1.101,
|
| 38 |
+
"step": 60
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.28,
|
| 42 |
+
"grad_norm": 2.5714163780212402,
|
| 43 |
+
"learning_rate": 0.00010666666666666667,
|
| 44 |
+
"loss": 0.6752,
|
| 45 |
+
"step": 80
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.6,
|
| 49 |
+
"grad_norm": 0.736541211605072,
|
| 50 |
+
"learning_rate": 0.00013333333333333334,
|
| 51 |
+
"loss": 0.6895,
|
| 52 |
+
"step": 100
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.92,
|
| 56 |
+
"grad_norm": 1.6849150657653809,
|
| 57 |
+
"learning_rate": 0.00016,
|
| 58 |
+
"loss": 0.6661,
|
| 59 |
+
"step": 120
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.92,
|
| 63 |
+
"eval_loss": 0.6780075430870056,
|
| 64 |
+
"eval_runtime": 49.0527,
|
| 65 |
+
"eval_samples_per_second": 35.044,
|
| 66 |
+
"eval_steps_per_second": 1.101,
|
| 67 |
+
"step": 120
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.24,
|
| 71 |
+
"grad_norm": 1.0006439685821533,
|
| 72 |
+
"learning_rate": 0.0001866666666666667,
|
| 73 |
+
"loss": 0.6684,
|
| 74 |
+
"step": 140
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.56,
|
| 78 |
+
"grad_norm": 2.7500181198120117,
|
| 79 |
+
"learning_rate": 0.00019574468085106384,
|
| 80 |
+
"loss": 0.7304,
|
| 81 |
+
"step": 160
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.88,
|
| 85 |
+
"grad_norm": 1.4791840314865112,
|
| 86 |
+
"learning_rate": 0.0001872340425531915,
|
| 87 |
+
"loss": 0.6696,
|
| 88 |
+
"step": 180
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.88,
|
| 92 |
+
"eval_loss": 0.6752753853797913,
|
| 93 |
+
"eval_runtime": 48.8363,
|
| 94 |
+
"eval_samples_per_second": 35.199,
|
| 95 |
+
"eval_steps_per_second": 1.106,
|
| 96 |
+
"step": 180
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.2,
|
| 100 |
+
"grad_norm": 1.1989027261734009,
|
| 101 |
+
"learning_rate": 0.00017872340425531915,
|
| 102 |
+
"loss": 0.6812,
|
| 103 |
+
"step": 200
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.52,
|
| 107 |
+
"grad_norm": 1.0437731742858887,
|
| 108 |
+
"learning_rate": 0.00017021276595744682,
|
| 109 |
+
"loss": 0.6886,
|
| 110 |
+
"step": 220
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.84,
|
| 114 |
+
"grad_norm": 0.7693199515342712,
|
| 115 |
+
"learning_rate": 0.00016170212765957446,
|
| 116 |
+
"loss": 0.6783,
|
| 117 |
+
"step": 240
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.84,
|
| 121 |
+
"eval_loss": 0.6913231611251831,
|
| 122 |
+
"eval_runtime": 48.9814,
|
| 123 |
+
"eval_samples_per_second": 35.095,
|
| 124 |
+
"eval_steps_per_second": 1.102,
|
| 125 |
+
"step": 240
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.16,
|
| 129 |
+
"grad_norm": 0.9999447464942932,
|
| 130 |
+
"learning_rate": 0.00015319148936170213,
|
| 131 |
+
"loss": 0.6733,
|
| 132 |
+
"step": 260
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.48,
|
| 136 |
+
"grad_norm": 3.2817800045013428,
|
| 137 |
+
"learning_rate": 0.0001446808510638298,
|
| 138 |
+
"loss": 0.6894,
|
| 139 |
+
"step": 280
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.8,
|
| 143 |
+
"grad_norm": 1.485412836074829,
|
| 144 |
+
"learning_rate": 0.00013617021276595746,
|
| 145 |
+
"loss": 0.6714,
|
| 146 |
+
"step": 300
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.8,
|
| 150 |
+
"eval_loss": 0.6768029928207397,
|
| 151 |
+
"eval_runtime": 48.9645,
|
| 152 |
+
"eval_samples_per_second": 35.107,
|
| 153 |
+
"eval_steps_per_second": 1.103,
|
| 154 |
+
"step": 300
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.12,
|
| 158 |
+
"grad_norm": 0.6202168464660645,
|
| 159 |
+
"learning_rate": 0.00012765957446808513,
|
| 160 |
+
"loss": 0.6726,
|
| 161 |
+
"step": 320
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.44,
|
| 165 |
+
"grad_norm": 0.9941303133964539,
|
| 166 |
+
"learning_rate": 0.00011914893617021277,
|
| 167 |
+
"loss": 0.6547,
|
| 168 |
+
"step": 340
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.76,
|
| 172 |
+
"grad_norm": 1.1737464666366577,
|
| 173 |
+
"learning_rate": 0.00011063829787234043,
|
| 174 |
+
"loss": 0.683,
|
| 175 |
+
"step": 360
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.76,
|
| 179 |
+
"eval_loss": 0.6857156753540039,
|
| 180 |
+
"eval_runtime": 49.0746,
|
| 181 |
+
"eval_samples_per_second": 35.028,
|
| 182 |
+
"eval_steps_per_second": 1.1,
|
| 183 |
+
"step": 360
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.08,
|
| 187 |
+
"grad_norm": 2.2875583171844482,
|
| 188 |
+
"learning_rate": 0.00010212765957446809,
|
| 189 |
+
"loss": 0.6763,
|
| 190 |
+
"step": 380
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.4,
|
| 194 |
+
"grad_norm": 0.5993250608444214,
|
| 195 |
+
"learning_rate": 9.361702127659576e-05,
|
| 196 |
+
"loss": 0.659,
|
| 197 |
+
"step": 400
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 6.72,
|
| 201 |
+
"grad_norm": 1.2196799516677856,
|
| 202 |
+
"learning_rate": 8.510638297872341e-05,
|
| 203 |
+
"loss": 0.6541,
|
| 204 |
+
"step": 420
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 6.72,
|
| 208 |
+
"eval_loss": 0.6817581653594971,
|
| 209 |
+
"eval_runtime": 49.0974,
|
| 210 |
+
"eval_samples_per_second": 35.012,
|
| 211 |
+
"eval_steps_per_second": 1.1,
|
| 212 |
+
"step": 420
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.04,
|
| 216 |
+
"grad_norm": 1.3733019828796387,
|
| 217 |
+
"learning_rate": 7.659574468085106e-05,
|
| 218 |
+
"loss": 0.6489,
|
| 219 |
+
"step": 440
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.36,
|
| 223 |
+
"grad_norm": 2.523149013519287,
|
| 224 |
+
"learning_rate": 6.808510638297873e-05,
|
| 225 |
+
"loss": 0.6602,
|
| 226 |
+
"step": 460
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.68,
|
| 230 |
+
"grad_norm": 1.8784421682357788,
|
| 231 |
+
"learning_rate": 5.9574468085106384e-05,
|
| 232 |
+
"loss": 0.6429,
|
| 233 |
+
"step": 480
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.68,
|
| 237 |
+
"eval_loss": 0.668049693107605,
|
| 238 |
+
"eval_runtime": 49.0805,
|
| 239 |
+
"eval_samples_per_second": 35.024,
|
| 240 |
+
"eval_steps_per_second": 1.1,
|
| 241 |
+
"step": 480
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.0,
|
| 245 |
+
"grad_norm": 1.0589911937713623,
|
| 246 |
+
"learning_rate": 5.1063829787234044e-05,
|
| 247 |
+
"loss": 0.6452,
|
| 248 |
+
"step": 500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.384,
|
| 252 |
+
"grad_norm": 1.13771653175354,
|
| 253 |
+
"learning_rate": 4.2553191489361704e-05,
|
| 254 |
+
"loss": 0.6496,
|
| 255 |
+
"step": 520
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.704,
|
| 259 |
+
"grad_norm": 1.4135953187942505,
|
| 260 |
+
"learning_rate": 3.4042553191489365e-05,
|
| 261 |
+
"loss": 0.6299,
|
| 262 |
+
"step": 540
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 8.704,
|
| 266 |
+
"eval_loss": 0.6739547848701477,
|
| 267 |
+
"eval_runtime": 50.9783,
|
| 268 |
+
"eval_samples_per_second": 33.72,
|
| 269 |
+
"eval_steps_per_second": 1.059,
|
| 270 |
+
"step": 540
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.024,
|
| 274 |
+
"grad_norm": 0.9489519000053406,
|
| 275 |
+
"learning_rate": 2.5531914893617022e-05,
|
| 276 |
+
"loss": 0.6414,
|
| 277 |
+
"step": 560
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 9.344,
|
| 281 |
+
"grad_norm": 1.4730383157730103,
|
| 282 |
+
"learning_rate": 1.7021276595744682e-05,
|
| 283 |
+
"loss": 0.6083,
|
| 284 |
+
"step": 580
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 9.664,
|
| 288 |
+
"grad_norm": 1.221296787261963,
|
| 289 |
+
"learning_rate": 8.510638297872341e-06,
|
| 290 |
+
"loss": 0.6431,
|
| 291 |
+
"step": 600
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 9.664,
|
| 295 |
+
"eval_loss": 0.6727736592292786,
|
| 296 |
+
"eval_runtime": 50.9608,
|
| 297 |
+
"eval_samples_per_second": 33.732,
|
| 298 |
+
"eval_steps_per_second": 1.06,
|
| 299 |
+
"step": 600
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 9.984,
|
| 303 |
+
"grad_norm": 1.7475664615631104,
|
| 304 |
+
"learning_rate": 0.0,
|
| 305 |
+
"loss": 0.6438,
|
| 306 |
+
"step": 620
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 10.32,
|
| 310 |
+
"grad_norm": 2.3684651851654053,
|
| 311 |
+
"learning_rate": 0.00011009174311926606,
|
| 312 |
+
"loss": 0.6419,
|
| 313 |
+
"step": 640
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 10.64,
|
| 317 |
+
"grad_norm": 1.4250073432922363,
|
| 318 |
+
"learning_rate": 0.00010642201834862387,
|
| 319 |
+
"loss": 0.6464,
|
| 320 |
+
"step": 660
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 10.64,
|
| 324 |
+
"eval_loss": 0.6687487363815308,
|
| 325 |
+
"eval_runtime": 50.793,
|
| 326 |
+
"eval_samples_per_second": 33.843,
|
| 327 |
+
"eval_steps_per_second": 1.063,
|
| 328 |
+
"step": 660
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 10.96,
|
| 332 |
+
"grad_norm": 0.8611794114112854,
|
| 333 |
+
"learning_rate": 0.00010275229357798166,
|
| 334 |
+
"loss": 0.6436,
|
| 335 |
+
"step": 680
|
| 336 |
+
}
|
| 337 |
+
],
|
| 338 |
+
"logging_steps": 20,
|
| 339 |
+
"max_steps": 1240,
|
| 340 |
+
"num_input_tokens_seen": 0,
|
| 341 |
+
"num_train_epochs": 20,
|
| 342 |
+
"save_steps": 500,
|
| 343 |
+
"stateful_callbacks": {
|
| 344 |
+
"TrainerControl": {
|
| 345 |
+
"args": {
|
| 346 |
+
"should_epoch_stop": false,
|
| 347 |
+
"should_evaluate": false,
|
| 348 |
+
"should_log": false,
|
| 349 |
+
"should_save": true,
|
| 350 |
+
"should_training_stop": false
|
| 351 |
+
},
|
| 352 |
+
"attributes": {}
|
| 353 |
+
}
|
| 354 |
+
},
|
| 355 |
+
"total_flos": 2.298579454918656e+16,
|
| 356 |
+
"train_batch_size": 32,
|
| 357 |
+
"trial_name": null,
|
| 358 |
+
"trial_params": null
|
| 359 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2045522d8e83b31347e07b8fae423310fd1e1a5c9bb20ee878f63a1b368d9e5e
|
| 3 |
+
size 5112
|