Training in progress, epoch 6, checkpoint
Browse files
checkpoint-600/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 4096,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"legacy": true,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"max_relative_positions": -1,
|
| 16 |
+
"model_type": "deberta",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 1024,
|
| 23 |
+
"pos_att_type": [
|
| 24 |
+
"c2p",
|
| 25 |
+
"p2c"
|
| 26 |
+
],
|
| 27 |
+
"position_biased_input": false,
|
| 28 |
+
"relative_attention": true,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.48.3",
|
| 31 |
+
"type_vocab_size": 0,
|
| 32 |
+
"vocab_size": 50265
|
| 33 |
+
}
|
checkpoint-600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae4cfb9c404fca1b58825310df4535d24fe91ad5a28456d8ad7018cf9b0e91f8
|
| 3 |
+
size 1624907048
|
checkpoint-600/trainer_state.json
ADDED
|
@@ -0,0 +1,309 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5,
|
| 13 |
+
"grad_norm": 14.797772407531738,
|
| 14 |
+
"learning_rate": 2.75e-05,
|
| 15 |
+
"loss": 0.5962,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5,
|
| 20 |
+
"eval_pet_AUC": 0.8351851851851851,
|
| 21 |
+
"eval_pet_accuracy": 0.8025,
|
| 22 |
+
"eval_pet_f1": 0.6775510204081633,
|
| 23 |
+
"eval_pet_loss": 0.5332173705101013,
|
| 24 |
+
"eval_pet_macro_f1": 0.7676043390329105,
|
| 25 |
+
"eval_pet_micro_f1": 0.8025,
|
| 26 |
+
"eval_pet_precision": 0.7217391304347827,
|
| 27 |
+
"eval_pet_recall": 0.6384615384615384,
|
| 28 |
+
"eval_pet_runtime": 0.9704,
|
| 29 |
+
"eval_pet_samples_per_second": 412.209,
|
| 30 |
+
"eval_pet_specificity": 0.8814814814814815,
|
| 31 |
+
"eval_pet_steps_per_second": 1.031,
|
| 32 |
+
"step": 50
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"grad_norm": 2.127084493637085,
|
| 37 |
+
"learning_rate": 2.5e-05,
|
| 38 |
+
"loss": 0.5733,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0,
|
| 43 |
+
"eval_pet_AUC": 0.27964387464387463,
|
| 44 |
+
"eval_pet_accuracy": 0.6875,
|
| 45 |
+
"eval_pet_f1": 0.07407407407407407,
|
| 46 |
+
"eval_pet_loss": 0.6733165979385376,
|
| 47 |
+
"eval_pet_macro_f1": 0.443052074631022,
|
| 48 |
+
"eval_pet_micro_f1": 0.6875,
|
| 49 |
+
"eval_pet_precision": 1.0,
|
| 50 |
+
"eval_pet_recall": 0.038461538461538464,
|
| 51 |
+
"eval_pet_runtime": 0.9613,
|
| 52 |
+
"eval_pet_samples_per_second": 416.088,
|
| 53 |
+
"eval_pet_specificity": 1.0,
|
| 54 |
+
"eval_pet_steps_per_second": 1.04,
|
| 55 |
+
"step": 100
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.5,
|
| 59 |
+
"grad_norm": 7.847217559814453,
|
| 60 |
+
"learning_rate": 2.25e-05,
|
| 61 |
+
"loss": 0.5866,
|
| 62 |
+
"step": 150
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.5,
|
| 66 |
+
"eval_pet_AUC": 0.8843874643874644,
|
| 67 |
+
"eval_pet_accuracy": 0.7975,
|
| 68 |
+
"eval_pet_f1": 0.7361563517915309,
|
| 69 |
+
"eval_pet_loss": 0.46060317754745483,
|
| 70 |
+
"eval_pet_macro_f1": 0.7859280744758872,
|
| 71 |
+
"eval_pet_micro_f1": 0.7975,
|
| 72 |
+
"eval_pet_precision": 0.6384180790960452,
|
| 73 |
+
"eval_pet_recall": 0.8692307692307693,
|
| 74 |
+
"eval_pet_runtime": 0.9636,
|
| 75 |
+
"eval_pet_samples_per_second": 415.11,
|
| 76 |
+
"eval_pet_specificity": 0.762962962962963,
|
| 77 |
+
"eval_pet_steps_per_second": 1.038,
|
| 78 |
+
"step": 150
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.0,
|
| 82 |
+
"grad_norm": 7.877416610717773,
|
| 83 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 84 |
+
"loss": 0.3741,
|
| 85 |
+
"step": 200
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 2.0,
|
| 89 |
+
"eval_pet_AUC": 0.8881766381766382,
|
| 90 |
+
"eval_pet_accuracy": 0.815,
|
| 91 |
+
"eval_pet_f1": 0.7581699346405228,
|
| 92 |
+
"eval_pet_loss": 0.4415346384048462,
|
| 93 |
+
"eval_pet_macro_f1": 0.8041861818951602,
|
| 94 |
+
"eval_pet_micro_f1": 0.815,
|
| 95 |
+
"eval_pet_precision": 0.6590909090909091,
|
| 96 |
+
"eval_pet_recall": 0.8923076923076924,
|
| 97 |
+
"eval_pet_runtime": 0.9595,
|
| 98 |
+
"eval_pet_samples_per_second": 416.867,
|
| 99 |
+
"eval_pet_specificity": 0.7777777777777778,
|
| 100 |
+
"eval_pet_steps_per_second": 1.042,
|
| 101 |
+
"step": 200
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.5,
|
| 105 |
+
"grad_norm": 11.366959571838379,
|
| 106 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 107 |
+
"loss": 0.4004,
|
| 108 |
+
"step": 250
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.5,
|
| 112 |
+
"eval_pet_AUC": 0.9125498575498576,
|
| 113 |
+
"eval_pet_accuracy": 0.83,
|
| 114 |
+
"eval_pet_f1": 0.782051282051282,
|
| 115 |
+
"eval_pet_loss": 0.4811069071292877,
|
| 116 |
+
"eval_pet_macro_f1": 0.8213535098781,
|
| 117 |
+
"eval_pet_micro_f1": 0.83,
|
| 118 |
+
"eval_pet_precision": 0.6703296703296703,
|
| 119 |
+
"eval_pet_recall": 0.9384615384615385,
|
| 120 |
+
"eval_pet_runtime": 0.9612,
|
| 121 |
+
"eval_pet_samples_per_second": 416.154,
|
| 122 |
+
"eval_pet_specificity": 0.7777777777777778,
|
| 123 |
+
"eval_pet_steps_per_second": 1.04,
|
| 124 |
+
"step": 250
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.0,
|
| 128 |
+
"grad_norm": 17.459558486938477,
|
| 129 |
+
"learning_rate": 1.5e-05,
|
| 130 |
+
"loss": 0.2983,
|
| 131 |
+
"step": 300
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.0,
|
| 135 |
+
"eval_pet_AUC": 0.8991737891737892,
|
| 136 |
+
"eval_pet_accuracy": 0.7925,
|
| 137 |
+
"eval_pet_f1": 0.7446153846153846,
|
| 138 |
+
"eval_pet_loss": 0.5743342638015747,
|
| 139 |
+
"eval_pet_macro_f1": 0.7849392712550607,
|
| 140 |
+
"eval_pet_micro_f1": 0.7925,
|
| 141 |
+
"eval_pet_precision": 0.6205128205128205,
|
| 142 |
+
"eval_pet_recall": 0.9307692307692308,
|
| 143 |
+
"eval_pet_runtime": 0.9582,
|
| 144 |
+
"eval_pet_samples_per_second": 417.438,
|
| 145 |
+
"eval_pet_specificity": 0.725925925925926,
|
| 146 |
+
"eval_pet_steps_per_second": 1.044,
|
| 147 |
+
"step": 300
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 3.5,
|
| 151 |
+
"grad_norm": 0.6785043478012085,
|
| 152 |
+
"learning_rate": 1.25e-05,
|
| 153 |
+
"loss": 0.251,
|
| 154 |
+
"step": 350
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 3.5,
|
| 158 |
+
"eval_pet_AUC": 0.9170655270655271,
|
| 159 |
+
"eval_pet_accuracy": 0.845,
|
| 160 |
+
"eval_pet_f1": 0.7769784172661871,
|
| 161 |
+
"eval_pet_loss": 0.5284662246704102,
|
| 162 |
+
"eval_pet_macro_f1": 0.8291022354530169,
|
| 163 |
+
"eval_pet_micro_f1": 0.845,
|
| 164 |
+
"eval_pet_precision": 0.7297297297297297,
|
| 165 |
+
"eval_pet_recall": 0.8307692307692308,
|
| 166 |
+
"eval_pet_runtime": 0.9761,
|
| 167 |
+
"eval_pet_samples_per_second": 409.779,
|
| 168 |
+
"eval_pet_specificity": 0.8518518518518519,
|
| 169 |
+
"eval_pet_steps_per_second": 1.024,
|
| 170 |
+
"step": 350
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.0,
|
| 174 |
+
"grad_norm": 6.269617557525635,
|
| 175 |
+
"learning_rate": 9.999999999999999e-06,
|
| 176 |
+
"loss": 0.2556,
|
| 177 |
+
"step": 400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.0,
|
| 181 |
+
"eval_pet_AUC": 0.9231054131054132,
|
| 182 |
+
"eval_pet_accuracy": 0.8475,
|
| 183 |
+
"eval_pet_f1": 0.779783393501805,
|
| 184 |
+
"eval_pet_loss": 0.38620322942733765,
|
| 185 |
+
"eval_pet_macro_f1": 0.8315742971333118,
|
| 186 |
+
"eval_pet_micro_f1": 0.8475,
|
| 187 |
+
"eval_pet_precision": 0.7346938775510204,
|
| 188 |
+
"eval_pet_recall": 0.8307692307692308,
|
| 189 |
+
"eval_pet_runtime": 0.9582,
|
| 190 |
+
"eval_pet_samples_per_second": 417.437,
|
| 191 |
+
"eval_pet_specificity": 0.8555555555555555,
|
| 192 |
+
"eval_pet_steps_per_second": 1.044,
|
| 193 |
+
"step": 400
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 4.5,
|
| 197 |
+
"grad_norm": 268.5960998535156,
|
| 198 |
+
"learning_rate": 7.5e-06,
|
| 199 |
+
"loss": 0.1711,
|
| 200 |
+
"step": 450
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.5,
|
| 204 |
+
"eval_pet_AUC": 0.9212250712250712,
|
| 205 |
+
"eval_pet_accuracy": 0.85,
|
| 206 |
+
"eval_pet_f1": 0.7857142857142857,
|
| 207 |
+
"eval_pet_loss": 0.5741958022117615,
|
| 208 |
+
"eval_pet_macro_f1": 0.8351648351648351,
|
| 209 |
+
"eval_pet_micro_f1": 0.85,
|
| 210 |
+
"eval_pet_precision": 0.7333333333333333,
|
| 211 |
+
"eval_pet_recall": 0.8461538461538461,
|
| 212 |
+
"eval_pet_runtime": 0.9798,
|
| 213 |
+
"eval_pet_samples_per_second": 408.226,
|
| 214 |
+
"eval_pet_specificity": 0.8518518518518519,
|
| 215 |
+
"eval_pet_steps_per_second": 1.021,
|
| 216 |
+
"step": 450
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.0,
|
| 220 |
+
"grad_norm": 2.5370795726776123,
|
| 221 |
+
"learning_rate": 4.9999999999999996e-06,
|
| 222 |
+
"loss": 0.1942,
|
| 223 |
+
"step": 500
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.0,
|
| 227 |
+
"eval_pet_AUC": 0.9196296296296297,
|
| 228 |
+
"eval_pet_accuracy": 0.8375,
|
| 229 |
+
"eval_pet_f1": 0.7653429602888087,
|
| 230 |
+
"eval_pet_loss": 0.5052361488342285,
|
| 231 |
+
"eval_pet_macro_f1": 0.8205299887486108,
|
| 232 |
+
"eval_pet_micro_f1": 0.8375,
|
| 233 |
+
"eval_pet_precision": 0.7210884353741497,
|
| 234 |
+
"eval_pet_recall": 0.8153846153846154,
|
| 235 |
+
"eval_pet_runtime": 0.9739,
|
| 236 |
+
"eval_pet_samples_per_second": 410.701,
|
| 237 |
+
"eval_pet_specificity": 0.8481481481481481,
|
| 238 |
+
"eval_pet_steps_per_second": 1.027,
|
| 239 |
+
"step": 500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 5.5,
|
| 243 |
+
"grad_norm": 65.75556945800781,
|
| 244 |
+
"learning_rate": 2.4999999999999998e-06,
|
| 245 |
+
"loss": 0.1122,
|
| 246 |
+
"step": 550
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.5,
|
| 250 |
+
"eval_pet_AUC": 0.913931623931624,
|
| 251 |
+
"eval_pet_accuracy": 0.845,
|
| 252 |
+
"eval_pet_f1": 0.7785714285714286,
|
| 253 |
+
"eval_pet_loss": 0.590245246887207,
|
| 254 |
+
"eval_pet_macro_f1": 0.8296703296703296,
|
| 255 |
+
"eval_pet_micro_f1": 0.845,
|
| 256 |
+
"eval_pet_precision": 0.7266666666666667,
|
| 257 |
+
"eval_pet_recall": 0.8384615384615385,
|
| 258 |
+
"eval_pet_runtime": 0.9755,
|
| 259 |
+
"eval_pet_samples_per_second": 410.028,
|
| 260 |
+
"eval_pet_specificity": 0.8481481481481481,
|
| 261 |
+
"eval_pet_steps_per_second": 1.025,
|
| 262 |
+
"step": 550
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 6.0,
|
| 266 |
+
"grad_norm": 0.31698858737945557,
|
| 267 |
+
"learning_rate": 0.0,
|
| 268 |
+
"loss": 0.138,
|
| 269 |
+
"step": 600
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 6.0,
|
| 273 |
+
"eval_pet_AUC": 0.9194301994301994,
|
| 274 |
+
"eval_pet_accuracy": 0.845,
|
| 275 |
+
"eval_pet_f1": 0.7785714285714286,
|
| 276 |
+
"eval_pet_loss": 0.5720162391662598,
|
| 277 |
+
"eval_pet_macro_f1": 0.8296703296703296,
|
| 278 |
+
"eval_pet_micro_f1": 0.845,
|
| 279 |
+
"eval_pet_precision": 0.7266666666666667,
|
| 280 |
+
"eval_pet_recall": 0.8384615384615385,
|
| 281 |
+
"eval_pet_runtime": 0.9564,
|
| 282 |
+
"eval_pet_samples_per_second": 418.255,
|
| 283 |
+
"eval_pet_specificity": 0.8481481481481481,
|
| 284 |
+
"eval_pet_steps_per_second": 1.046,
|
| 285 |
+
"step": 600
|
| 286 |
+
}
|
| 287 |
+
],
|
| 288 |
+
"logging_steps": 50,
|
| 289 |
+
"max_steps": 600,
|
| 290 |
+
"num_input_tokens_seen": 0,
|
| 291 |
+
"num_train_epochs": 6,
|
| 292 |
+
"save_steps": 500,
|
| 293 |
+
"stateful_callbacks": {
|
| 294 |
+
"TrainerControl": {
|
| 295 |
+
"args": {
|
| 296 |
+
"should_epoch_stop": false,
|
| 297 |
+
"should_evaluate": false,
|
| 298 |
+
"should_log": false,
|
| 299 |
+
"should_save": true,
|
| 300 |
+
"should_training_stop": true
|
| 301 |
+
},
|
| 302 |
+
"attributes": {}
|
| 303 |
+
}
|
| 304 |
+
},
|
| 305 |
+
"total_flos": 814912639488000.0,
|
| 306 |
+
"train_batch_size": 16,
|
| 307 |
+
"trial_name": null,
|
| 308 |
+
"trial_params": null
|
| 309 |
+
}
|
checkpoint-600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3b0216cc5eff463ac2446af91ddb08c5dd1f7f444a009f566b7314b5057e685
|
| 3 |
+
size 5432
|