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:bbc8d21dba82cd2d96c05789ed2d87b1c3090d548089a022a62f3e012cc68eaf
|
| 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": 6.080199718475342,
|
| 14 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 15 |
+
"loss": 0.5304,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5,
|
| 20 |
+
"eval_pet_AUC": 0.8846723646723647,
|
| 21 |
+
"eval_pet_accuracy": 0.825,
|
| 22 |
+
"eval_pet_f1": 0.7569444444444444,
|
| 23 |
+
"eval_pet_loss": 0.4055028557777405,
|
| 24 |
+
"eval_pet_macro_f1": 0.8101128472222222,
|
| 25 |
+
"eval_pet_micro_f1": 0.825,
|
| 26 |
+
"eval_pet_precision": 0.689873417721519,
|
| 27 |
+
"eval_pet_recall": 0.8384615384615385,
|
| 28 |
+
"eval_pet_runtime": 0.9669,
|
| 29 |
+
"eval_pet_samples_per_second": 413.704,
|
| 30 |
+
"eval_pet_specificity": 0.8185185185185185,
|
| 31 |
+
"eval_pet_steps_per_second": 1.034,
|
| 32 |
+
"step": 50
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"grad_norm": 7.429731369018555,
|
| 37 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 38 |
+
"loss": 0.4825,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0,
|
| 43 |
+
"eval_pet_AUC": 0.9121652421652421,
|
| 44 |
+
"eval_pet_accuracy": 0.8325,
|
| 45 |
+
"eval_pet_f1": 0.7598566308243727,
|
| 46 |
+
"eval_pet_loss": 0.35728055238723755,
|
| 47 |
+
"eval_pet_macro_f1": 0.8156288912279253,
|
| 48 |
+
"eval_pet_micro_f1": 0.8325,
|
| 49 |
+
"eval_pet_precision": 0.7114093959731543,
|
| 50 |
+
"eval_pet_recall": 0.8153846153846154,
|
| 51 |
+
"eval_pet_runtime": 0.9571,
|
| 52 |
+
"eval_pet_samples_per_second": 417.916,
|
| 53 |
+
"eval_pet_specificity": 0.8407407407407408,
|
| 54 |
+
"eval_pet_steps_per_second": 1.045,
|
| 55 |
+
"step": 100
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.5,
|
| 59 |
+
"grad_norm": 7.952208042144775,
|
| 60 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 61 |
+
"loss": 0.3115,
|
| 62 |
+
"step": 150
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.5,
|
| 66 |
+
"eval_pet_AUC": 0.9031339031339031,
|
| 67 |
+
"eval_pet_accuracy": 0.85,
|
| 68 |
+
"eval_pet_f1": 0.7744360902255639,
|
| 69 |
+
"eval_pet_loss": 0.5131158828735352,
|
| 70 |
+
"eval_pet_macro_f1": 0.831038269831883,
|
| 71 |
+
"eval_pet_micro_f1": 0.85,
|
| 72 |
+
"eval_pet_precision": 0.7573529411764706,
|
| 73 |
+
"eval_pet_recall": 0.7923076923076923,
|
| 74 |
+
"eval_pet_runtime": 0.9601,
|
| 75 |
+
"eval_pet_samples_per_second": 416.631,
|
| 76 |
+
"eval_pet_specificity": 0.8777777777777778,
|
| 77 |
+
"eval_pet_steps_per_second": 1.042,
|
| 78 |
+
"step": 150
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.0,
|
| 82 |
+
"grad_norm": 3.0394058227539062,
|
| 83 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 84 |
+
"loss": 0.2963,
|
| 85 |
+
"step": 200
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 2.0,
|
| 89 |
+
"eval_pet_AUC": 0.9202564102564103,
|
| 90 |
+
"eval_pet_accuracy": 0.8425,
|
| 91 |
+
"eval_pet_f1": 0.7622641509433963,
|
| 92 |
+
"eval_pet_loss": 0.3516935706138611,
|
| 93 |
+
"eval_pet_macro_f1": 0.822253570798801,
|
| 94 |
+
"eval_pet_micro_f1": 0.8425,
|
| 95 |
+
"eval_pet_precision": 0.7481481481481481,
|
| 96 |
+
"eval_pet_recall": 0.7769230769230769,
|
| 97 |
+
"eval_pet_runtime": 0.9543,
|
| 98 |
+
"eval_pet_samples_per_second": 419.175,
|
| 99 |
+
"eval_pet_specificity": 0.8740740740740741,
|
| 100 |
+
"eval_pet_steps_per_second": 1.048,
|
| 101 |
+
"step": 200
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.5,
|
| 105 |
+
"grad_norm": 13.06711483001709,
|
| 106 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 107 |
+
"loss": 0.2196,
|
| 108 |
+
"step": 250
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.5,
|
| 112 |
+
"eval_pet_AUC": 0.9203703703703704,
|
| 113 |
+
"eval_pet_accuracy": 0.85,
|
| 114 |
+
"eval_pet_f1": 0.7902097902097902,
|
| 115 |
+
"eval_pet_loss": 0.4240196645259857,
|
| 116 |
+
"eval_pet_macro_f1": 0.8367391363500313,
|
| 117 |
+
"eval_pet_micro_f1": 0.85,
|
| 118 |
+
"eval_pet_precision": 0.7243589743589743,
|
| 119 |
+
"eval_pet_recall": 0.8692307692307693,
|
| 120 |
+
"eval_pet_runtime": 0.9601,
|
| 121 |
+
"eval_pet_samples_per_second": 416.603,
|
| 122 |
+
"eval_pet_specificity": 0.8407407407407408,
|
| 123 |
+
"eval_pet_steps_per_second": 1.042,
|
| 124 |
+
"step": 250
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.0,
|
| 128 |
+
"grad_norm": 18.414968490600586,
|
| 129 |
+
"learning_rate": 1e-05,
|
| 130 |
+
"loss": 0.1567,
|
| 131 |
+
"step": 300
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.0,
|
| 135 |
+
"eval_pet_AUC": 0.9211965811965812,
|
| 136 |
+
"eval_pet_accuracy": 0.8475,
|
| 137 |
+
"eval_pet_f1": 0.769811320754717,
|
| 138 |
+
"eval_pet_loss": 0.492168128490448,
|
| 139 |
+
"eval_pet_macro_f1": 0.827896314582966,
|
| 140 |
+
"eval_pet_micro_f1": 0.8475,
|
| 141 |
+
"eval_pet_precision": 0.7555555555555555,
|
| 142 |
+
"eval_pet_recall": 0.7846153846153846,
|
| 143 |
+
"eval_pet_runtime": 0.9572,
|
| 144 |
+
"eval_pet_samples_per_second": 417.89,
|
| 145 |
+
"eval_pet_specificity": 0.8777777777777778,
|
| 146 |
+
"eval_pet_steps_per_second": 1.045,
|
| 147 |
+
"step": 300
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 3.5,
|
| 151 |
+
"grad_norm": 0.0726945623755455,
|
| 152 |
+
"learning_rate": 8.333333333333334e-06,
|
| 153 |
+
"loss": 0.102,
|
| 154 |
+
"step": 350
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 3.5,
|
| 158 |
+
"eval_pet_AUC": 0.9077207977207977,
|
| 159 |
+
"eval_pet_accuracy": 0.8575,
|
| 160 |
+
"eval_pet_f1": 0.7927272727272727,
|
| 161 |
+
"eval_pet_loss": 0.6835651397705078,
|
| 162 |
+
"eval_pet_macro_f1": 0.8420779220779221,
|
| 163 |
+
"eval_pet_micro_f1": 0.8575,
|
| 164 |
+
"eval_pet_precision": 0.7517241379310344,
|
| 165 |
+
"eval_pet_recall": 0.8384615384615385,
|
| 166 |
+
"eval_pet_runtime": 0.9587,
|
| 167 |
+
"eval_pet_samples_per_second": 417.215,
|
| 168 |
+
"eval_pet_specificity": 0.8666666666666667,
|
| 169 |
+
"eval_pet_steps_per_second": 1.043,
|
| 170 |
+
"step": 350
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.0,
|
| 174 |
+
"grad_norm": 17.67284393310547,
|
| 175 |
+
"learning_rate": 6.666666666666667e-06,
|
| 176 |
+
"loss": 0.1043,
|
| 177 |
+
"step": 400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.0,
|
| 181 |
+
"eval_pet_AUC": 0.9203418803418804,
|
| 182 |
+
"eval_pet_accuracy": 0.865,
|
| 183 |
+
"eval_pet_f1": 0.7923076923076923,
|
| 184 |
+
"eval_pet_loss": 0.7219401597976685,
|
| 185 |
+
"eval_pet_macro_f1": 0.8461538461538461,
|
| 186 |
+
"eval_pet_micro_f1": 0.865,
|
| 187 |
+
"eval_pet_precision": 0.7923076923076923,
|
| 188 |
+
"eval_pet_recall": 0.7923076923076923,
|
| 189 |
+
"eval_pet_runtime": 0.9547,
|
| 190 |
+
"eval_pet_samples_per_second": 418.975,
|
| 191 |
+
"eval_pet_specificity": 0.9,
|
| 192 |
+
"eval_pet_steps_per_second": 1.047,
|
| 193 |
+
"step": 400
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 4.5,
|
| 197 |
+
"grad_norm": 5.668124675750732,
|
| 198 |
+
"learning_rate": 5e-06,
|
| 199 |
+
"loss": 0.0554,
|
| 200 |
+
"step": 450
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.5,
|
| 204 |
+
"eval_pet_AUC": 0.9286039886039885,
|
| 205 |
+
"eval_pet_accuracy": 0.8625,
|
| 206 |
+
"eval_pet_f1": 0.8056537102473498,
|
| 207 |
+
"eval_pet_loss": 0.6998915672302246,
|
| 208 |
+
"eval_pet_macro_f1": 0.8496353657619727,
|
| 209 |
+
"eval_pet_micro_f1": 0.8625,
|
| 210 |
+
"eval_pet_precision": 0.7450980392156863,
|
| 211 |
+
"eval_pet_recall": 0.8769230769230769,
|
| 212 |
+
"eval_pet_runtime": 0.9948,
|
| 213 |
+
"eval_pet_samples_per_second": 402.105,
|
| 214 |
+
"eval_pet_specificity": 0.8555555555555555,
|
| 215 |
+
"eval_pet_steps_per_second": 1.005,
|
| 216 |
+
"step": 450
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.0,
|
| 220 |
+
"grad_norm": 0.18213483691215515,
|
| 221 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 222 |
+
"loss": 0.0611,
|
| 223 |
+
"step": 500
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.0,
|
| 227 |
+
"eval_pet_AUC": 0.9289743589743589,
|
| 228 |
+
"eval_pet_accuracy": 0.865,
|
| 229 |
+
"eval_pet_f1": 0.8029197080291971,
|
| 230 |
+
"eval_pet_loss": 0.6941245794296265,
|
| 231 |
+
"eval_pet_macro_f1": 0.8501290555355111,
|
| 232 |
+
"eval_pet_micro_f1": 0.865,
|
| 233 |
+
"eval_pet_precision": 0.7638888888888888,
|
| 234 |
+
"eval_pet_recall": 0.8461538461538461,
|
| 235 |
+
"eval_pet_runtime": 0.964,
|
| 236 |
+
"eval_pet_samples_per_second": 414.946,
|
| 237 |
+
"eval_pet_specificity": 0.8740740740740741,
|
| 238 |
+
"eval_pet_steps_per_second": 1.037,
|
| 239 |
+
"step": 500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 5.5,
|
| 243 |
+
"grad_norm": 0.1536085605621338,
|
| 244 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 245 |
+
"loss": 0.0372,
|
| 246 |
+
"step": 550
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.5,
|
| 250 |
+
"eval_pet_AUC": 0.9222222222222222,
|
| 251 |
+
"eval_pet_accuracy": 0.8575,
|
| 252 |
+
"eval_pet_f1": 0.7956989247311828,
|
| 253 |
+
"eval_pet_loss": 0.7272201776504517,
|
| 254 |
+
"eval_pet_macro_f1": 0.8431469671640559,
|
| 255 |
+
"eval_pet_micro_f1": 0.8575,
|
| 256 |
+
"eval_pet_precision": 0.7449664429530202,
|
| 257 |
+
"eval_pet_recall": 0.8538461538461538,
|
| 258 |
+
"eval_pet_runtime": 0.9644,
|
| 259 |
+
"eval_pet_samples_per_second": 414.759,
|
| 260 |
+
"eval_pet_specificity": 0.8592592592592593,
|
| 261 |
+
"eval_pet_steps_per_second": 1.037,
|
| 262 |
+
"step": 550
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 6.0,
|
| 266 |
+
"grad_norm": 0.06249264255166054,
|
| 267 |
+
"learning_rate": 0.0,
|
| 268 |
+
"loss": 0.0222,
|
| 269 |
+
"step": 600
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 6.0,
|
| 273 |
+
"eval_pet_AUC": 0.921011396011396,
|
| 274 |
+
"eval_pet_accuracy": 0.865,
|
| 275 |
+
"eval_pet_f1": 0.8014705882352942,
|
| 276 |
+
"eval_pet_loss": 0.7324556112289429,
|
| 277 |
+
"eval_pet_macro_f1": 0.8495989304812834,
|
| 278 |
+
"eval_pet_micro_f1": 0.865,
|
| 279 |
+
"eval_pet_precision": 0.7676056338028169,
|
| 280 |
+
"eval_pet_recall": 0.8384615384615385,
|
| 281 |
+
"eval_pet_runtime": 0.9532,
|
| 282 |
+
"eval_pet_samples_per_second": 419.653,
|
| 283 |
+
"eval_pet_specificity": 0.8777777777777778,
|
| 284 |
+
"eval_pet_steps_per_second": 1.049,
|
| 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 sha256:0764263474b97260fc37ee4a274e139015dd761304086c91f05087cd69a8986e
|
| 3 |
+
size 5432
|