Training in progress, epoch 6, checkpoint
Browse files
checkpoint-600/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"hidden_act": "gelu",
|
| 7 |
+
"hidden_dropout_prob": 0.1,
|
| 8 |
+
"hidden_size": 1024,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 4096,
|
| 11 |
+
"layer_norm_eps": 1e-07,
|
| 12 |
+
"legacy": true,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"pooler_dropout": 0,
|
| 20 |
+
"pooler_hidden_act": "gelu",
|
| 21 |
+
"pooler_hidden_size": 1024,
|
| 22 |
+
"pos_att_type": [
|
| 23 |
+
"c2p",
|
| 24 |
+
"p2c"
|
| 25 |
+
],
|
| 26 |
+
"position_biased_input": false,
|
| 27 |
+
"relative_attention": true,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.50.3",
|
| 30 |
+
"type_vocab_size": 0,
|
| 31 |
+
"vocab_size": 50265
|
| 32 |
+
}
|
checkpoint-600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6701a36269d89c9c99d4220e5e8401bdbda8cec0b53d410cd67a2e9ae6ab6bf
|
| 3 |
+
size 1624907048
|
checkpoint-600/trainer_state.json
ADDED
|
@@ -0,0 +1,310 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.0,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 600,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.5,
|
| 14 |
+
"grad_norm": 2.202085256576538,
|
| 15 |
+
"learning_rate": 2.75e-05,
|
| 16 |
+
"loss": 0.7001,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5,
|
| 21 |
+
"eval_electronics_AUC": 0.8274661508704062,
|
| 22 |
+
"eval_electronics_accuracy": 0.5875,
|
| 23 |
+
"eval_electronics_f1": 0.0,
|
| 24 |
+
"eval_electronics_loss": 0.7029502987861633,
|
| 25 |
+
"eval_electronics_macro_f1": 0.3700787401574803,
|
| 26 |
+
"eval_electronics_micro_f1": 0.5875,
|
| 27 |
+
"eval_electronics_precision": 0.0,
|
| 28 |
+
"eval_electronics_recall": 0.0,
|
| 29 |
+
"eval_electronics_runtime": 1.1511,
|
| 30 |
+
"eval_electronics_samples_per_second": 347.485,
|
| 31 |
+
"eval_electronics_specificity": 1.0,
|
| 32 |
+
"eval_electronics_steps_per_second": 0.869,
|
| 33 |
+
"step": 50
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.0,
|
| 37 |
+
"grad_norm": 5.9589738845825195,
|
| 38 |
+
"learning_rate": 2.5e-05,
|
| 39 |
+
"loss": 0.6259,
|
| 40 |
+
"step": 100
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.0,
|
| 44 |
+
"eval_electronics_AUC": 0.8812894906511928,
|
| 45 |
+
"eval_electronics_accuracy": 0.805,
|
| 46 |
+
"eval_electronics_f1": 0.7914438502673797,
|
| 47 |
+
"eval_electronics_loss": 0.44977375864982605,
|
| 48 |
+
"eval_electronics_macro_f1": 0.804172629359042,
|
| 49 |
+
"eval_electronics_micro_f1": 0.805,
|
| 50 |
+
"eval_electronics_precision": 0.7081339712918661,
|
| 51 |
+
"eval_electronics_recall": 0.896969696969697,
|
| 52 |
+
"eval_electronics_runtime": 1.1287,
|
| 53 |
+
"eval_electronics_samples_per_second": 354.379,
|
| 54 |
+
"eval_electronics_specificity": 0.7404255319148936,
|
| 55 |
+
"eval_electronics_steps_per_second": 0.886,
|
| 56 |
+
"step": 100
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.5,
|
| 60 |
+
"grad_norm": 15.954824447631836,
|
| 61 |
+
"learning_rate": 2.25e-05,
|
| 62 |
+
"loss": 0.5285,
|
| 63 |
+
"step": 150
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.5,
|
| 67 |
+
"eval_electronics_AUC": 0.8546228239845262,
|
| 68 |
+
"eval_electronics_accuracy": 0.75,
|
| 69 |
+
"eval_electronics_f1": 0.647887323943662,
|
| 70 |
+
"eval_electronics_loss": 0.5688791275024414,
|
| 71 |
+
"eval_electronics_macro_f1": 0.7270444371656295,
|
| 72 |
+
"eval_electronics_micro_f1": 0.75,
|
| 73 |
+
"eval_electronics_precision": 0.773109243697479,
|
| 74 |
+
"eval_electronics_recall": 0.5575757575757576,
|
| 75 |
+
"eval_electronics_runtime": 1.1417,
|
| 76 |
+
"eval_electronics_samples_per_second": 350.348,
|
| 77 |
+
"eval_electronics_specificity": 0.8851063829787233,
|
| 78 |
+
"eval_electronics_steps_per_second": 0.876,
|
| 79 |
+
"step": 150
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.0,
|
| 83 |
+
"grad_norm": 2.80739426612854,
|
| 84 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 85 |
+
"loss": 0.492,
|
| 86 |
+
"step": 200
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.0,
|
| 90 |
+
"eval_electronics_AUC": 0.8878401031592521,
|
| 91 |
+
"eval_electronics_accuracy": 0.79,
|
| 92 |
+
"eval_electronics_f1": 0.7741935483870968,
|
| 93 |
+
"eval_electronics_loss": 0.5164185762405396,
|
| 94 |
+
"eval_electronics_macro_f1": 0.7889659330720531,
|
| 95 |
+
"eval_electronics_micro_f1": 0.79,
|
| 96 |
+
"eval_electronics_precision": 0.6956521739130435,
|
| 97 |
+
"eval_electronics_recall": 0.8727272727272727,
|
| 98 |
+
"eval_electronics_runtime": 1.1374,
|
| 99 |
+
"eval_electronics_samples_per_second": 351.668,
|
| 100 |
+
"eval_electronics_specificity": 0.7319148936170212,
|
| 101 |
+
"eval_electronics_steps_per_second": 0.879,
|
| 102 |
+
"step": 200
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.5,
|
| 106 |
+
"grad_norm": 48.75403594970703,
|
| 107 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 108 |
+
"loss": 0.4042,
|
| 109 |
+
"step": 250
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.5,
|
| 113 |
+
"eval_electronics_AUC": 0.8810831721470018,
|
| 114 |
+
"eval_electronics_accuracy": 0.7525,
|
| 115 |
+
"eval_electronics_f1": 0.7579462102689487,
|
| 116 |
+
"eval_electronics_loss": 0.6417726874351501,
|
| 117 |
+
"eval_electronics_macro_f1": 0.7523746396613286,
|
| 118 |
+
"eval_electronics_micro_f1": 0.7525,
|
| 119 |
+
"eval_electronics_precision": 0.6352459016393442,
|
| 120 |
+
"eval_electronics_recall": 0.9393939393939394,
|
| 121 |
+
"eval_electronics_runtime": 1.176,
|
| 122 |
+
"eval_electronics_samples_per_second": 340.145,
|
| 123 |
+
"eval_electronics_specificity": 0.6212765957446809,
|
| 124 |
+
"eval_electronics_steps_per_second": 0.85,
|
| 125 |
+
"step": 250
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.0,
|
| 129 |
+
"grad_norm": 17.9029541015625,
|
| 130 |
+
"learning_rate": 1.5e-05,
|
| 131 |
+
"loss": 0.3676,
|
| 132 |
+
"step": 300
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.0,
|
| 136 |
+
"eval_electronics_AUC": 0.8895422308188267,
|
| 137 |
+
"eval_electronics_accuracy": 0.81,
|
| 138 |
+
"eval_electronics_f1": 0.7432432432432432,
|
| 139 |
+
"eval_electronics_loss": 0.5099908709526062,
|
| 140 |
+
"eval_electronics_macro_f1": 0.7962247962247961,
|
| 141 |
+
"eval_electronics_micro_f1": 0.81,
|
| 142 |
+
"eval_electronics_precision": 0.8396946564885496,
|
| 143 |
+
"eval_electronics_recall": 0.6666666666666666,
|
| 144 |
+
"eval_electronics_runtime": 1.1391,
|
| 145 |
+
"eval_electronics_samples_per_second": 351.16,
|
| 146 |
+
"eval_electronics_specificity": 0.9106382978723404,
|
| 147 |
+
"eval_electronics_steps_per_second": 0.878,
|
| 148 |
+
"step": 300
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.5,
|
| 152 |
+
"grad_norm": 0.9845223426818848,
|
| 153 |
+
"learning_rate": 1.25e-05,
|
| 154 |
+
"loss": 0.2304,
|
| 155 |
+
"step": 350
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.5,
|
| 159 |
+
"eval_electronics_AUC": 0.885880077369439,
|
| 160 |
+
"eval_electronics_accuracy": 0.8275,
|
| 161 |
+
"eval_electronics_f1": 0.7964601769911505,
|
| 162 |
+
"eval_electronics_loss": 0.5810662508010864,
|
| 163 |
+
"eval_electronics_macro_f1": 0.8233927783003474,
|
| 164 |
+
"eval_electronics_micro_f1": 0.8275,
|
| 165 |
+
"eval_electronics_precision": 0.7758620689655172,
|
| 166 |
+
"eval_electronics_recall": 0.8181818181818182,
|
| 167 |
+
"eval_electronics_runtime": 1.1575,
|
| 168 |
+
"eval_electronics_samples_per_second": 345.569,
|
| 169 |
+
"eval_electronics_specificity": 0.8340425531914893,
|
| 170 |
+
"eval_electronics_steps_per_second": 0.864,
|
| 171 |
+
"step": 350
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.0,
|
| 175 |
+
"grad_norm": 0.663503110408783,
|
| 176 |
+
"learning_rate": 9.999999999999999e-06,
|
| 177 |
+
"loss": 0.2429,
|
| 178 |
+
"step": 400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 4.0,
|
| 182 |
+
"eval_electronics_AUC": 0.8947001934235976,
|
| 183 |
+
"eval_electronics_accuracy": 0.825,
|
| 184 |
+
"eval_electronics_f1": 0.7988505747126436,
|
| 185 |
+
"eval_electronics_loss": 0.4967746436595917,
|
| 186 |
+
"eval_electronics_macro_f1": 0.8219916590377377,
|
| 187 |
+
"eval_electronics_micro_f1": 0.825,
|
| 188 |
+
"eval_electronics_precision": 0.7595628415300546,
|
| 189 |
+
"eval_electronics_recall": 0.8424242424242424,
|
| 190 |
+
"eval_electronics_runtime": 1.1523,
|
| 191 |
+
"eval_electronics_samples_per_second": 347.119,
|
| 192 |
+
"eval_electronics_specificity": 0.8127659574468085,
|
| 193 |
+
"eval_electronics_steps_per_second": 0.868,
|
| 194 |
+
"step": 400
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.5,
|
| 198 |
+
"grad_norm": 1.9665794372558594,
|
| 199 |
+
"learning_rate": 7.5e-06,
|
| 200 |
+
"loss": 0.1609,
|
| 201 |
+
"step": 450
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.5,
|
| 205 |
+
"eval_electronics_AUC": 0.9006576402321084,
|
| 206 |
+
"eval_electronics_accuracy": 0.815,
|
| 207 |
+
"eval_electronics_f1": 0.7823529411764706,
|
| 208 |
+
"eval_electronics_loss": 0.7328701019287109,
|
| 209 |
+
"eval_electronics_macro_f1": 0.8107416879795397,
|
| 210 |
+
"eval_electronics_micro_f1": 0.815,
|
| 211 |
+
"eval_electronics_precision": 0.76,
|
| 212 |
+
"eval_electronics_recall": 0.806060606060606,
|
| 213 |
+
"eval_electronics_runtime": 1.1294,
|
| 214 |
+
"eval_electronics_samples_per_second": 354.163,
|
| 215 |
+
"eval_electronics_specificity": 0.8212765957446808,
|
| 216 |
+
"eval_electronics_steps_per_second": 0.885,
|
| 217 |
+
"step": 450
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 5.0,
|
| 221 |
+
"grad_norm": 3.498450994491577,
|
| 222 |
+
"learning_rate": 4.9999999999999996e-06,
|
| 223 |
+
"loss": 0.1561,
|
| 224 |
+
"step": 500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 5.0,
|
| 228 |
+
"eval_electronics_AUC": 0.8925338491295938,
|
| 229 |
+
"eval_electronics_accuracy": 0.81,
|
| 230 |
+
"eval_electronics_f1": 0.7639751552795031,
|
| 231 |
+
"eval_electronics_loss": 0.6941885948181152,
|
| 232 |
+
"eval_electronics_macro_f1": 0.8024896696899608,
|
| 233 |
+
"eval_electronics_micro_f1": 0.81,
|
| 234 |
+
"eval_electronics_precision": 0.7834394904458599,
|
| 235 |
+
"eval_electronics_recall": 0.7454545454545455,
|
| 236 |
+
"eval_electronics_runtime": 1.1466,
|
| 237 |
+
"eval_electronics_samples_per_second": 348.853,
|
| 238 |
+
"eval_electronics_specificity": 0.8553191489361702,
|
| 239 |
+
"eval_electronics_steps_per_second": 0.872,
|
| 240 |
+
"step": 500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.5,
|
| 244 |
+
"grad_norm": 15.850218772888184,
|
| 245 |
+
"learning_rate": 2.4999999999999998e-06,
|
| 246 |
+
"loss": 0.1236,
|
| 247 |
+
"step": 550
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 5.5,
|
| 251 |
+
"eval_electronics_AUC": 0.8960928433268858,
|
| 252 |
+
"eval_electronics_accuracy": 0.815,
|
| 253 |
+
"eval_electronics_f1": 0.7797619047619048,
|
| 254 |
+
"eval_electronics_loss": 0.7811417579650879,
|
| 255 |
+
"eval_electronics_macro_f1": 0.8101395730706076,
|
| 256 |
+
"eval_electronics_micro_f1": 0.815,
|
| 257 |
+
"eval_electronics_precision": 0.7660818713450293,
|
| 258 |
+
"eval_electronics_recall": 0.793939393939394,
|
| 259 |
+
"eval_electronics_runtime": 1.1464,
|
| 260 |
+
"eval_electronics_samples_per_second": 348.932,
|
| 261 |
+
"eval_electronics_specificity": 0.8297872340425532,
|
| 262 |
+
"eval_electronics_steps_per_second": 0.872,
|
| 263 |
+
"step": 550
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 6.0,
|
| 267 |
+
"grad_norm": 0.2115035206079483,
|
| 268 |
+
"learning_rate": 0.0,
|
| 269 |
+
"loss": 0.1345,
|
| 270 |
+
"step": 600
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 6.0,
|
| 274 |
+
"eval_electronics_AUC": 0.8953449387491941,
|
| 275 |
+
"eval_electronics_accuracy": 0.8125,
|
| 276 |
+
"eval_electronics_f1": 0.7720364741641338,
|
| 277 |
+
"eval_electronics_loss": 0.7612780928611755,
|
| 278 |
+
"eval_electronics_macro_f1": 0.8064004026871625,
|
| 279 |
+
"eval_electronics_micro_f1": 0.8125,
|
| 280 |
+
"eval_electronics_precision": 0.774390243902439,
|
| 281 |
+
"eval_electronics_recall": 0.7696969696969697,
|
| 282 |
+
"eval_electronics_runtime": 1.151,
|
| 283 |
+
"eval_electronics_samples_per_second": 347.525,
|
| 284 |
+
"eval_electronics_specificity": 0.8425531914893617,
|
| 285 |
+
"eval_electronics_steps_per_second": 0.869,
|
| 286 |
+
"step": 600
|
| 287 |
+
}
|
| 288 |
+
],
|
| 289 |
+
"logging_steps": 50,
|
| 290 |
+
"max_steps": 600,
|
| 291 |
+
"num_input_tokens_seen": 0,
|
| 292 |
+
"num_train_epochs": 6,
|
| 293 |
+
"save_steps": 500,
|
| 294 |
+
"stateful_callbacks": {
|
| 295 |
+
"TrainerControl": {
|
| 296 |
+
"args": {
|
| 297 |
+
"should_epoch_stop": false,
|
| 298 |
+
"should_evaluate": false,
|
| 299 |
+
"should_log": false,
|
| 300 |
+
"should_save": true,
|
| 301 |
+
"should_training_stop": true
|
| 302 |
+
},
|
| 303 |
+
"attributes": {}
|
| 304 |
+
}
|
| 305 |
+
},
|
| 306 |
+
"total_flos": 814912639488000.0,
|
| 307 |
+
"train_batch_size": 16,
|
| 308 |
+
"trial_name": null,
|
| 309 |
+
"trial_params": null
|
| 310 |
+
}
|
checkpoint-600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47871193157119808f8d00b7d97c1b2cdfffd44e2a841575fc1c03ac79100709
|
| 3 |
+
size 5432
|