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 sha256:929173ded8c1e1ec585e08cea7e669115c68fca185f6ca47eec4881eee75fbb9
|
| 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": 7.576278209686279,
|
| 14 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 15 |
+
"loss": 0.5455,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5,
|
| 20 |
+
"eval_pet_AUC": 0.8744411211495174,
|
| 21 |
+
"eval_pet_accuracy": 0.7875,
|
| 22 |
+
"eval_pet_f1": 0.6413502109704642,
|
| 23 |
+
"eval_pet_loss": 0.40357428789138794,
|
| 24 |
+
"eval_pet_macro_f1": 0.7451866507783049,
|
| 25 |
+
"eval_pet_micro_f1": 0.7875,
|
| 26 |
+
"eval_pet_precision": 0.6129032258064516,
|
| 27 |
+
"eval_pet_recall": 0.672566371681416,
|
| 28 |
+
"eval_pet_runtime": 0.4329,
|
| 29 |
+
"eval_pet_samples_per_second": 924.048,
|
| 30 |
+
"eval_pet_specificity": 0.8327526132404182,
|
| 31 |
+
"eval_pet_steps_per_second": 2.31,
|
| 32 |
+
"step": 50
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"grad_norm": 7.2780537605285645,
|
| 37 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 38 |
+
"loss": 0.3767,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0,
|
| 43 |
+
"eval_pet_AUC": 0.9009589590206901,
|
| 44 |
+
"eval_pet_accuracy": 0.81,
|
| 45 |
+
"eval_pet_f1": 0.6935483870967742,
|
| 46 |
+
"eval_pet_loss": 0.3708844780921936,
|
| 47 |
+
"eval_pet_macro_f1": 0.7779336138382422,
|
| 48 |
+
"eval_pet_micro_f1": 0.81,
|
| 49 |
+
"eval_pet_precision": 0.6370370370370371,
|
| 50 |
+
"eval_pet_recall": 0.7610619469026548,
|
| 51 |
+
"eval_pet_runtime": 0.4373,
|
| 52 |
+
"eval_pet_samples_per_second": 914.609,
|
| 53 |
+
"eval_pet_specificity": 0.8292682926829268,
|
| 54 |
+
"eval_pet_steps_per_second": 2.287,
|
| 55 |
+
"step": 100
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.5,
|
| 59 |
+
"grad_norm": 4.364447116851807,
|
| 60 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 61 |
+
"loss": 0.2847,
|
| 62 |
+
"step": 150
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.5,
|
| 66 |
+
"eval_pet_AUC": 0.9033948999414141,
|
| 67 |
+
"eval_pet_accuracy": 0.8225,
|
| 68 |
+
"eval_pet_f1": 0.7171314741035857,
|
| 69 |
+
"eval_pet_loss": 0.4332599937915802,
|
| 70 |
+
"eval_pet_macro_f1": 0.7939027133723757,
|
| 71 |
+
"eval_pet_micro_f1": 0.8225,
|
| 72 |
+
"eval_pet_precision": 0.6521739130434783,
|
| 73 |
+
"eval_pet_recall": 0.7964601769911505,
|
| 74 |
+
"eval_pet_runtime": 0.436,
|
| 75 |
+
"eval_pet_samples_per_second": 917.428,
|
| 76 |
+
"eval_pet_specificity": 0.8327526132404182,
|
| 77 |
+
"eval_pet_steps_per_second": 2.294,
|
| 78 |
+
"step": 150
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.0,
|
| 82 |
+
"grad_norm": 10.42080020904541,
|
| 83 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 84 |
+
"loss": 0.2694,
|
| 85 |
+
"step": 200
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 2.0,
|
| 89 |
+
"eval_pet_AUC": 0.8989238691375535,
|
| 90 |
+
"eval_pet_accuracy": 0.84,
|
| 91 |
+
"eval_pet_f1": 0.6952380952380952,
|
| 92 |
+
"eval_pet_loss": 0.4126374125480652,
|
| 93 |
+
"eval_pet_macro_f1": 0.7933817594834545,
|
| 94 |
+
"eval_pet_micro_f1": 0.84,
|
| 95 |
+
"eval_pet_precision": 0.7525773195876289,
|
| 96 |
+
"eval_pet_recall": 0.6460176991150443,
|
| 97 |
+
"eval_pet_runtime": 0.4605,
|
| 98 |
+
"eval_pet_samples_per_second": 868.692,
|
| 99 |
+
"eval_pet_specificity": 0.9163763066202091,
|
| 100 |
+
"eval_pet_steps_per_second": 2.172,
|
| 101 |
+
"step": 200
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.5,
|
| 105 |
+
"grad_norm": 13.263297080993652,
|
| 106 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 107 |
+
"loss": 0.157,
|
| 108 |
+
"step": 250
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.5,
|
| 112 |
+
"eval_pet_AUC": 0.9052141469581574,
|
| 113 |
+
"eval_pet_accuracy": 0.8425,
|
| 114 |
+
"eval_pet_f1": 0.6956521739130435,
|
| 115 |
+
"eval_pet_loss": 0.5520845055580139,
|
| 116 |
+
"eval_pet_macro_f1": 0.7947063567710242,
|
| 117 |
+
"eval_pet_micro_f1": 0.8425,
|
| 118 |
+
"eval_pet_precision": 0.7659574468085106,
|
| 119 |
+
"eval_pet_recall": 0.6371681415929203,
|
| 120 |
+
"eval_pet_runtime": 0.4377,
|
| 121 |
+
"eval_pet_samples_per_second": 913.907,
|
| 122 |
+
"eval_pet_specificity": 0.9233449477351916,
|
| 123 |
+
"eval_pet_steps_per_second": 2.285,
|
| 124 |
+
"step": 250
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.0,
|
| 128 |
+
"grad_norm": 15.089917182922363,
|
| 129 |
+
"learning_rate": 1e-05,
|
| 130 |
+
"loss": 0.1704,
|
| 131 |
+
"step": 300
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.0,
|
| 135 |
+
"eval_pet_AUC": 0.9130769942339121,
|
| 136 |
+
"eval_pet_accuracy": 0.825,
|
| 137 |
+
"eval_pet_f1": 0.7265625,
|
| 138 |
+
"eval_pet_loss": 0.6370885968208313,
|
| 139 |
+
"eval_pet_macro_f1": 0.7989430147058824,
|
| 140 |
+
"eval_pet_micro_f1": 0.825,
|
| 141 |
+
"eval_pet_precision": 0.6503496503496503,
|
| 142 |
+
"eval_pet_recall": 0.8230088495575221,
|
| 143 |
+
"eval_pet_runtime": 0.4271,
|
| 144 |
+
"eval_pet_samples_per_second": 936.455,
|
| 145 |
+
"eval_pet_specificity": 0.8257839721254355,
|
| 146 |
+
"eval_pet_steps_per_second": 2.341,
|
| 147 |
+
"step": 300
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 3.5,
|
| 151 |
+
"grad_norm": 0.6412437558174133,
|
| 152 |
+
"learning_rate": 8.333333333333334e-06,
|
| 153 |
+
"loss": 0.1028,
|
| 154 |
+
"step": 350
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 3.5,
|
| 158 |
+
"eval_pet_AUC": 0.9160987943634178,
|
| 159 |
+
"eval_pet_accuracy": 0.8475,
|
| 160 |
+
"eval_pet_f1": 0.7336244541484717,
|
| 161 |
+
"eval_pet_loss": 0.663390040397644,
|
| 162 |
+
"eval_pet_macro_f1": 0.8133971657782639,
|
| 163 |
+
"eval_pet_micro_f1": 0.8475,
|
| 164 |
+
"eval_pet_precision": 0.7241379310344828,
|
| 165 |
+
"eval_pet_recall": 0.7433628318584071,
|
| 166 |
+
"eval_pet_runtime": 0.441,
|
| 167 |
+
"eval_pet_samples_per_second": 906.956,
|
| 168 |
+
"eval_pet_specificity": 0.8885017421602788,
|
| 169 |
+
"eval_pet_steps_per_second": 2.267,
|
| 170 |
+
"step": 350
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.0,
|
| 174 |
+
"grad_norm": 4.150225639343262,
|
| 175 |
+
"learning_rate": 6.666666666666667e-06,
|
| 176 |
+
"loss": 0.1162,
|
| 177 |
+
"step": 400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.0,
|
| 181 |
+
"eval_pet_AUC": 0.9196139496161081,
|
| 182 |
+
"eval_pet_accuracy": 0.8375,
|
| 183 |
+
"eval_pet_f1": 0.7430830039525692,
|
| 184 |
+
"eval_pet_loss": 0.7081860303878784,
|
| 185 |
+
"eval_pet_macro_f1": 0.8121265111170524,
|
| 186 |
+
"eval_pet_micro_f1": 0.8375,
|
| 187 |
+
"eval_pet_precision": 0.6714285714285714,
|
| 188 |
+
"eval_pet_recall": 0.831858407079646,
|
| 189 |
+
"eval_pet_runtime": 0.4313,
|
| 190 |
+
"eval_pet_samples_per_second": 927.468,
|
| 191 |
+
"eval_pet_specificity": 0.8397212543554007,
|
| 192 |
+
"eval_pet_steps_per_second": 2.319,
|
| 193 |
+
"step": 400
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 4.5,
|
| 197 |
+
"grad_norm": 2.4922666549682617,
|
| 198 |
+
"learning_rate": 5e-06,
|
| 199 |
+
"loss": 0.0467,
|
| 200 |
+
"step": 450
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.5,
|
| 204 |
+
"eval_pet_AUC": 0.9188584995837316,
|
| 205 |
+
"eval_pet_accuracy": 0.835,
|
| 206 |
+
"eval_pet_f1": 0.717948717948718,
|
| 207 |
+
"eval_pet_loss": 0.7905848622322083,
|
| 208 |
+
"eval_pet_macro_f1": 0.8006704720485639,
|
| 209 |
+
"eval_pet_micro_f1": 0.835,
|
| 210 |
+
"eval_pet_precision": 0.6942148760330579,
|
| 211 |
+
"eval_pet_recall": 0.7433628318584071,
|
| 212 |
+
"eval_pet_runtime": 2.116,
|
| 213 |
+
"eval_pet_samples_per_second": 189.033,
|
| 214 |
+
"eval_pet_specificity": 0.8710801393728222,
|
| 215 |
+
"eval_pet_steps_per_second": 0.473,
|
| 216 |
+
"step": 450
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.0,
|
| 220 |
+
"grad_norm": 34.0222053527832,
|
| 221 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 222 |
+
"loss": 0.067,
|
| 223 |
+
"step": 500
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.0,
|
| 227 |
+
"eval_pet_AUC": 0.9199222965680984,
|
| 228 |
+
"eval_pet_accuracy": 0.8375,
|
| 229 |
+
"eval_pet_f1": 0.7346938775510204,
|
| 230 |
+
"eval_pet_loss": 0.793322741985321,
|
| 231 |
+
"eval_pet_macro_f1": 0.8087883802169517,
|
| 232 |
+
"eval_pet_micro_f1": 0.8375,
|
| 233 |
+
"eval_pet_precision": 0.6818181818181818,
|
| 234 |
+
"eval_pet_recall": 0.7964601769911505,
|
| 235 |
+
"eval_pet_runtime": 0.4388,
|
| 236 |
+
"eval_pet_samples_per_second": 911.572,
|
| 237 |
+
"eval_pet_specificity": 0.8536585365853658,
|
| 238 |
+
"eval_pet_steps_per_second": 2.279,
|
| 239 |
+
"step": 500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 5.5,
|
| 243 |
+
"grad_norm": 57.120513916015625,
|
| 244 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 245 |
+
"loss": 0.0393,
|
| 246 |
+
"step": 550
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.5,
|
| 250 |
+
"eval_pet_AUC": 0.9177638679041658,
|
| 251 |
+
"eval_pet_accuracy": 0.8375,
|
| 252 |
+
"eval_pet_f1": 0.721030042918455,
|
| 253 |
+
"eval_pet_loss": 0.8078400492668152,
|
| 254 |
+
"eval_pet_macro_f1": 0.8031957974733368,
|
| 255 |
+
"eval_pet_micro_f1": 0.8375,
|
| 256 |
+
"eval_pet_precision": 0.7,
|
| 257 |
+
"eval_pet_recall": 0.7433628318584071,
|
| 258 |
+
"eval_pet_runtime": 0.4363,
|
| 259 |
+
"eval_pet_samples_per_second": 916.751,
|
| 260 |
+
"eval_pet_specificity": 0.8745644599303136,
|
| 261 |
+
"eval_pet_steps_per_second": 2.292,
|
| 262 |
+
"step": 550
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 6.0,
|
| 266 |
+
"grad_norm": 37.04859924316406,
|
| 267 |
+
"learning_rate": 0.0,
|
| 268 |
+
"loss": 0.061,
|
| 269 |
+
"step": 600
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 6.0,
|
| 273 |
+
"eval_pet_AUC": 0.9180722148561561,
|
| 274 |
+
"eval_pet_accuracy": 0.84,
|
| 275 |
+
"eval_pet_f1": 0.7241379310344828,
|
| 276 |
+
"eval_pet_loss": 0.803439199924469,
|
| 277 |
+
"eval_pet_macro_f1": 0.8057309373482273,
|
| 278 |
+
"eval_pet_micro_f1": 0.84,
|
| 279 |
+
"eval_pet_precision": 0.7058823529411765,
|
| 280 |
+
"eval_pet_recall": 0.7433628318584071,
|
| 281 |
+
"eval_pet_runtime": 0.4272,
|
| 282 |
+
"eval_pet_samples_per_second": 936.379,
|
| 283 |
+
"eval_pet_specificity": 0.8780487804878049,
|
| 284 |
+
"eval_pet_steps_per_second": 2.341,
|
| 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 sha256:75165ed46ad9ff161917859a5f4064580d3dc749becc3cf672a988710e00d3bc
|
| 3 |
+
size 5432
|