Training in progress, epoch 6, checkpoint
Browse files
checkpoint-600/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-base",
|
| 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": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 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": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 768,
|
| 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:fa99ca1020668fdd81c9056985711af3730d294a5d83bf889cc20e34193280b4
|
| 3 |
+
size 556799560
|
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": 5.5827836990356445,
|
| 14 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 15 |
+
"loss": 0.5363,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5,
|
| 20 |
+
"eval_pet_AUC": 0.909333409007066,
|
| 21 |
+
"eval_pet_accuracy": 0.83,
|
| 22 |
+
"eval_pet_f1": 0.7536231884057971,
|
| 23 |
+
"eval_pet_loss": 0.3635893166065216,
|
| 24 |
+
"eval_pet_macro_f1": 0.8119260980196925,
|
| 25 |
+
"eval_pet_micro_f1": 0.83,
|
| 26 |
+
"eval_pet_precision": 0.7172413793103448,
|
| 27 |
+
"eval_pet_recall": 0.7938931297709924,
|
| 28 |
+
"eval_pet_runtime": 0.4423,
|
| 29 |
+
"eval_pet_samples_per_second": 904.376,
|
| 30 |
+
"eval_pet_specificity": 0.8475836431226765,
|
| 31 |
+
"eval_pet_steps_per_second": 2.261,
|
| 32 |
+
"step": 50
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"grad_norm": 10.243881225585938,
|
| 37 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 38 |
+
"loss": 0.3796,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0,
|
| 43 |
+
"eval_pet_AUC": 0.9267572859615767,
|
| 44 |
+
"eval_pet_accuracy": 0.8275,
|
| 45 |
+
"eval_pet_f1": 0.7628865979381443,
|
| 46 |
+
"eval_pet_loss": 0.34966903924942017,
|
| 47 |
+
"eval_pet_macro_f1": 0.813663338261803,
|
| 48 |
+
"eval_pet_micro_f1": 0.8275,
|
| 49 |
+
"eval_pet_precision": 0.69375,
|
| 50 |
+
"eval_pet_recall": 0.8473282442748091,
|
| 51 |
+
"eval_pet_runtime": 0.4238,
|
| 52 |
+
"eval_pet_samples_per_second": 943.952,
|
| 53 |
+
"eval_pet_specificity": 0.8178438661710037,
|
| 54 |
+
"eval_pet_steps_per_second": 2.36,
|
| 55 |
+
"step": 100
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.5,
|
| 59 |
+
"grad_norm": 7.141758918762207,
|
| 60 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 61 |
+
"loss": 0.2892,
|
| 62 |
+
"step": 150
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.5,
|
| 66 |
+
"eval_pet_AUC": 0.9297653168364596,
|
| 67 |
+
"eval_pet_accuracy": 0.8525,
|
| 68 |
+
"eval_pet_f1": 0.7790262172284644,
|
| 69 |
+
"eval_pet_loss": 0.3352491855621338,
|
| 70 |
+
"eval_pet_macro_f1": 0.8341660166817744,
|
| 71 |
+
"eval_pet_micro_f1": 0.8525,
|
| 72 |
+
"eval_pet_precision": 0.7647058823529411,
|
| 73 |
+
"eval_pet_recall": 0.7938931297709924,
|
| 74 |
+
"eval_pet_runtime": 0.4472,
|
| 75 |
+
"eval_pet_samples_per_second": 894.551,
|
| 76 |
+
"eval_pet_specificity": 0.8810408921933085,
|
| 77 |
+
"eval_pet_steps_per_second": 2.236,
|
| 78 |
+
"step": 150
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.0,
|
| 82 |
+
"grad_norm": 5.970040798187256,
|
| 83 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 84 |
+
"loss": 0.2701,
|
| 85 |
+
"step": 200
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 2.0,
|
| 89 |
+
"eval_pet_AUC": 0.931922018218451,
|
| 90 |
+
"eval_pet_accuracy": 0.865,
|
| 91 |
+
"eval_pet_f1": 0.7857142857142857,
|
| 92 |
+
"eval_pet_loss": 0.3177262246608734,
|
| 93 |
+
"eval_pet_macro_f1": 0.8435870698644421,
|
| 94 |
+
"eval_pet_micro_f1": 0.865,
|
| 95 |
+
"eval_pet_precision": 0.8181818181818182,
|
| 96 |
+
"eval_pet_recall": 0.7557251908396947,
|
| 97 |
+
"eval_pet_runtime": 0.4548,
|
| 98 |
+
"eval_pet_samples_per_second": 879.579,
|
| 99 |
+
"eval_pet_specificity": 0.9182156133828996,
|
| 100 |
+
"eval_pet_steps_per_second": 2.199,
|
| 101 |
+
"step": 200
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.5,
|
| 105 |
+
"grad_norm": 7.642846584320068,
|
| 106 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 107 |
+
"loss": 0.2012,
|
| 108 |
+
"step": 250
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.5,
|
| 112 |
+
"eval_pet_AUC": 0.9334260336558927,
|
| 113 |
+
"eval_pet_accuracy": 0.86,
|
| 114 |
+
"eval_pet_f1": 0.7925925925925926,
|
| 115 |
+
"eval_pet_loss": 0.39357075095176697,
|
| 116 |
+
"eval_pet_macro_f1": 0.8434661076170511,
|
| 117 |
+
"eval_pet_micro_f1": 0.86,
|
| 118 |
+
"eval_pet_precision": 0.7697841726618705,
|
| 119 |
+
"eval_pet_recall": 0.816793893129771,
|
| 120 |
+
"eval_pet_runtime": 0.4294,
|
| 121 |
+
"eval_pet_samples_per_second": 931.424,
|
| 122 |
+
"eval_pet_specificity": 0.8810408921933085,
|
| 123 |
+
"eval_pet_steps_per_second": 2.329,
|
| 124 |
+
"step": 250
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.0,
|
| 128 |
+
"grad_norm": 4.771540641784668,
|
| 129 |
+
"learning_rate": 1e-05,
|
| 130 |
+
"loss": 0.1595,
|
| 131 |
+
"step": 300
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.0,
|
| 135 |
+
"eval_pet_AUC": 0.936065155083856,
|
| 136 |
+
"eval_pet_accuracy": 0.86,
|
| 137 |
+
"eval_pet_f1": 0.7878787878787878,
|
| 138 |
+
"eval_pet_loss": 0.37874579429626465,
|
| 139 |
+
"eval_pet_macro_f1": 0.8417005879692447,
|
| 140 |
+
"eval_pet_micro_f1": 0.86,
|
| 141 |
+
"eval_pet_precision": 0.7819548872180451,
|
| 142 |
+
"eval_pet_recall": 0.7938931297709924,
|
| 143 |
+
"eval_pet_runtime": 0.437,
|
| 144 |
+
"eval_pet_samples_per_second": 915.404,
|
| 145 |
+
"eval_pet_specificity": 0.8921933085501859,
|
| 146 |
+
"eval_pet_steps_per_second": 2.289,
|
| 147 |
+
"step": 300
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 3.5,
|
| 151 |
+
"grad_norm": 30.385013580322266,
|
| 152 |
+
"learning_rate": 8.333333333333334e-06,
|
| 153 |
+
"loss": 0.1208,
|
| 154 |
+
"step": 350
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 3.5,
|
| 158 |
+
"eval_pet_AUC": 0.9345895172961775,
|
| 159 |
+
"eval_pet_accuracy": 0.87,
|
| 160 |
+
"eval_pet_f1": 0.8,
|
| 161 |
+
"eval_pet_loss": 0.486733078956604,
|
| 162 |
+
"eval_pet_macro_f1": 0.8518518518518519,
|
| 163 |
+
"eval_pet_micro_f1": 0.87,
|
| 164 |
+
"eval_pet_precision": 0.8062015503875969,
|
| 165 |
+
"eval_pet_recall": 0.7938931297709924,
|
| 166 |
+
"eval_pet_runtime": 0.4379,
|
| 167 |
+
"eval_pet_samples_per_second": 913.45,
|
| 168 |
+
"eval_pet_specificity": 0.9070631970260223,
|
| 169 |
+
"eval_pet_steps_per_second": 2.284,
|
| 170 |
+
"step": 350
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.0,
|
| 174 |
+
"grad_norm": 0.20905348658561707,
|
| 175 |
+
"learning_rate": 6.666666666666667e-06,
|
| 176 |
+
"loss": 0.1211,
|
| 177 |
+
"step": 400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.0,
|
| 181 |
+
"eval_pet_AUC": 0.9307585345781663,
|
| 182 |
+
"eval_pet_accuracy": 0.865,
|
| 183 |
+
"eval_pet_f1": 0.7985074626865671,
|
| 184 |
+
"eval_pet_loss": 0.5309534072875977,
|
| 185 |
+
"eval_pet_macro_f1": 0.8485018516440355,
|
| 186 |
+
"eval_pet_micro_f1": 0.865,
|
| 187 |
+
"eval_pet_precision": 0.781021897810219,
|
| 188 |
+
"eval_pet_recall": 0.816793893129771,
|
| 189 |
+
"eval_pet_runtime": 0.4369,
|
| 190 |
+
"eval_pet_samples_per_second": 915.552,
|
| 191 |
+
"eval_pet_specificity": 0.8884758364312267,
|
| 192 |
+
"eval_pet_steps_per_second": 2.289,
|
| 193 |
+
"step": 400
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 4.5,
|
| 197 |
+
"grad_norm": 0.29343461990356445,
|
| 198 |
+
"learning_rate": 5e-06,
|
| 199 |
+
"loss": 0.0735,
|
| 200 |
+
"step": 450
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.5,
|
| 204 |
+
"eval_pet_AUC": 0.9274383495558898,
|
| 205 |
+
"eval_pet_accuracy": 0.865,
|
| 206 |
+
"eval_pet_f1": 0.7857142857142857,
|
| 207 |
+
"eval_pet_loss": 0.5884985327720642,
|
| 208 |
+
"eval_pet_macro_f1": 0.8435870698644421,
|
| 209 |
+
"eval_pet_micro_f1": 0.865,
|
| 210 |
+
"eval_pet_precision": 0.8181818181818182,
|
| 211 |
+
"eval_pet_recall": 0.7557251908396947,
|
| 212 |
+
"eval_pet_runtime": 0.646,
|
| 213 |
+
"eval_pet_samples_per_second": 619.179,
|
| 214 |
+
"eval_pet_specificity": 0.9182156133828996,
|
| 215 |
+
"eval_pet_steps_per_second": 1.548,
|
| 216 |
+
"step": 450
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.0,
|
| 220 |
+
"grad_norm": 15.837231636047363,
|
| 221 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 222 |
+
"loss": 0.063,
|
| 223 |
+
"step": 500
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.0,
|
| 227 |
+
"eval_pet_AUC": 0.9294815403388292,
|
| 228 |
+
"eval_pet_accuracy": 0.855,
|
| 229 |
+
"eval_pet_f1": 0.7835820895522388,
|
| 230 |
+
"eval_pet_loss": 0.6990612745285034,
|
| 231 |
+
"eval_pet_macro_f1": 0.8372797665806306,
|
| 232 |
+
"eval_pet_micro_f1": 0.855,
|
| 233 |
+
"eval_pet_precision": 0.7664233576642335,
|
| 234 |
+
"eval_pet_recall": 0.8015267175572519,
|
| 235 |
+
"eval_pet_runtime": 0.4327,
|
| 236 |
+
"eval_pet_samples_per_second": 924.432,
|
| 237 |
+
"eval_pet_specificity": 0.8810408921933085,
|
| 238 |
+
"eval_pet_steps_per_second": 2.311,
|
| 239 |
+
"step": 500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 5.5,
|
| 243 |
+
"grad_norm": 0.02970566414296627,
|
| 244 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 245 |
+
"loss": 0.0302,
|
| 246 |
+
"step": 550
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.5,
|
| 250 |
+
"eval_pet_AUC": 0.92874372144499,
|
| 251 |
+
"eval_pet_accuracy": 0.86,
|
| 252 |
+
"eval_pet_f1": 0.7878787878787878,
|
| 253 |
+
"eval_pet_loss": 0.711138129234314,
|
| 254 |
+
"eval_pet_macro_f1": 0.8417005879692447,
|
| 255 |
+
"eval_pet_micro_f1": 0.86,
|
| 256 |
+
"eval_pet_precision": 0.7819548872180451,
|
| 257 |
+
"eval_pet_recall": 0.7938931297709924,
|
| 258 |
+
"eval_pet_runtime": 0.4333,
|
| 259 |
+
"eval_pet_samples_per_second": 923.212,
|
| 260 |
+
"eval_pet_specificity": 0.8921933085501859,
|
| 261 |
+
"eval_pet_steps_per_second": 2.308,
|
| 262 |
+
"step": 550
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 6.0,
|
| 266 |
+
"grad_norm": 0.10018513351678848,
|
| 267 |
+
"learning_rate": 0.0,
|
| 268 |
+
"loss": 0.0414,
|
| 269 |
+
"step": 600
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 6.0,
|
| 273 |
+
"eval_pet_AUC": 0.9274951048554159,
|
| 274 |
+
"eval_pet_accuracy": 0.865,
|
| 275 |
+
"eval_pet_f1": 0.7938931297709924,
|
| 276 |
+
"eval_pet_loss": 0.7137818932533264,
|
| 277 |
+
"eval_pet_macro_f1": 0.8467606912795482,
|
| 278 |
+
"eval_pet_micro_f1": 0.865,
|
| 279 |
+
"eval_pet_precision": 0.7938931297709924,
|
| 280 |
+
"eval_pet_recall": 0.7938931297709924,
|
| 281 |
+
"eval_pet_runtime": 0.4372,
|
| 282 |
+
"eval_pet_samples_per_second": 914.863,
|
| 283 |
+
"eval_pet_specificity": 0.8996282527881041,
|
| 284 |
+
"eval_pet_steps_per_second": 2.287,
|
| 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": 229948199424000.0,
|
| 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 sha256:60a4a1a99d93293e076c082c8cd72052c9dbde4a41bd85babe4aa19d6bfdf8dd
|
| 3 |
+
size 5432
|