Upload 4 files
Browse files- config.json +39 -0
- model.safetensors +3 -0
- trainer_state.json +336 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "contradiction",
|
| 15 |
+
"1": "neutral",
|
| 16 |
+
"2": "entailment"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 4096,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"contradiction": 0,
|
| 22 |
+
"entailment": 2,
|
| 23 |
+
"neutral": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "xlm-roberta",
|
| 28 |
+
"num_attention_heads": 16,
|
| 29 |
+
"num_hidden_layers": 24,
|
| 30 |
+
"output_past": true,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"pretraining_tp": 1,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.39.3",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": false,
|
| 38 |
+
"vocab_size": 250002
|
| 39 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fbc92ac988b4eec85a8ba9c6f9b76e4ebee1f12b30d3270c9d2269af9af4580
|
| 3 |
+
size 2239622772
|
trainer_state.json
ADDED
|
@@ -0,0 +1,336 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5347539113428944,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 2100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 13.311190605163574,
|
| 14 |
+
"learning_rate": 4.991511756217638e-07,
|
| 15 |
+
"loss": 1.1106,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"eval_loss": 1.0980943441390991,
|
| 21 |
+
"eval_runtime": 444.5552,
|
| 22 |
+
"eval_samples_per_second": 22.116,
|
| 23 |
+
"eval_steps_per_second": 1.383,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05,
|
| 28 |
+
"grad_norm": 124.89850616455078,
|
| 29 |
+
"learning_rate": 4.983023512435277e-07,
|
| 30 |
+
"loss": 1.1058,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05,
|
| 35 |
+
"eval_loss": 1.0958582162857056,
|
| 36 |
+
"eval_runtime": 445.0884,
|
| 37 |
+
"eval_samples_per_second": 22.09,
|
| 38 |
+
"eval_steps_per_second": 1.382,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08,
|
| 43 |
+
"grad_norm": 4.540226459503174,
|
| 44 |
+
"learning_rate": 4.974535268652916e-07,
|
| 45 |
+
"loss": 1.1041,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.08,
|
| 50 |
+
"eval_loss": 1.0949292182922363,
|
| 51 |
+
"eval_runtime": 444.1007,
|
| 52 |
+
"eval_samples_per_second": 22.139,
|
| 53 |
+
"eval_steps_per_second": 1.385,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.1,
|
| 58 |
+
"grad_norm": 2.7475616931915283,
|
| 59 |
+
"learning_rate": 4.966047024870554e-07,
|
| 60 |
+
"loss": 1.1015,
|
| 61 |
+
"step": 400
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.1,
|
| 65 |
+
"eval_loss": 1.0947699546813965,
|
| 66 |
+
"eval_runtime": 444.3765,
|
| 67 |
+
"eval_samples_per_second": 22.125,
|
| 68 |
+
"eval_steps_per_second": 1.384,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13,
|
| 73 |
+
"grad_norm": 47.300941467285156,
|
| 74 |
+
"learning_rate": 4.957558781088193e-07,
|
| 75 |
+
"loss": 1.0996,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.13,
|
| 80 |
+
"eval_loss": 1.0897258520126343,
|
| 81 |
+
"eval_runtime": 444.8131,
|
| 82 |
+
"eval_samples_per_second": 22.104,
|
| 83 |
+
"eval_steps_per_second": 1.383,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.15,
|
| 88 |
+
"grad_norm": 5.65737771987915,
|
| 89 |
+
"learning_rate": 4.949070537305832e-07,
|
| 90 |
+
"loss": 1.0994,
|
| 91 |
+
"step": 600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.15,
|
| 95 |
+
"eval_loss": 1.0869251489639282,
|
| 96 |
+
"eval_runtime": 444.3561,
|
| 97 |
+
"eval_samples_per_second": 22.126,
|
| 98 |
+
"eval_steps_per_second": 1.384,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.18,
|
| 103 |
+
"grad_norm": 14.847755432128906,
|
| 104 |
+
"learning_rate": 4.94058229352347e-07,
|
| 105 |
+
"loss": 1.0954,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.18,
|
| 110 |
+
"eval_loss": 1.0760304927825928,
|
| 111 |
+
"eval_runtime": 444.5382,
|
| 112 |
+
"eval_samples_per_second": 22.117,
|
| 113 |
+
"eval_steps_per_second": 1.383,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2,
|
| 118 |
+
"grad_norm": 11.20052433013916,
|
| 119 |
+
"learning_rate": 4.932094049741109e-07,
|
| 120 |
+
"loss": 1.0884,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2,
|
| 125 |
+
"eval_loss": 1.054417371749878,
|
| 126 |
+
"eval_runtime": 444.2308,
|
| 127 |
+
"eval_samples_per_second": 22.133,
|
| 128 |
+
"eval_steps_per_second": 1.384,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.23,
|
| 133 |
+
"grad_norm": 9.804169654846191,
|
| 134 |
+
"learning_rate": 4.923605805958747e-07,
|
| 135 |
+
"loss": 1.076,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.23,
|
| 140 |
+
"eval_loss": 1.027961254119873,
|
| 141 |
+
"eval_runtime": 444.5711,
|
| 142 |
+
"eval_samples_per_second": 22.116,
|
| 143 |
+
"eval_steps_per_second": 1.383,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.25,
|
| 148 |
+
"grad_norm": 8.616690635681152,
|
| 149 |
+
"learning_rate": 4.915117562176386e-07,
|
| 150 |
+
"loss": 1.0548,
|
| 151 |
+
"step": 1000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.25,
|
| 155 |
+
"eval_loss": 1.0113487243652344,
|
| 156 |
+
"eval_runtime": 444.7544,
|
| 157 |
+
"eval_samples_per_second": 22.107,
|
| 158 |
+
"eval_steps_per_second": 1.383,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.28,
|
| 163 |
+
"grad_norm": 26.81256103515625,
|
| 164 |
+
"learning_rate": 4.906629318394024e-07,
|
| 165 |
+
"loss": 1.0409,
|
| 166 |
+
"step": 1100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.28,
|
| 170 |
+
"eval_loss": 0.9771223664283752,
|
| 171 |
+
"eval_runtime": 444.4918,
|
| 172 |
+
"eval_samples_per_second": 22.12,
|
| 173 |
+
"eval_steps_per_second": 1.384,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.31,
|
| 178 |
+
"grad_norm": 37.97452163696289,
|
| 179 |
+
"learning_rate": 4.898141074611662e-07,
|
| 180 |
+
"loss": 1.0217,
|
| 181 |
+
"step": 1200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.31,
|
| 185 |
+
"eval_loss": 0.950868546962738,
|
| 186 |
+
"eval_runtime": 444.7062,
|
| 187 |
+
"eval_samples_per_second": 22.109,
|
| 188 |
+
"eval_steps_per_second": 1.383,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.33,
|
| 193 |
+
"grad_norm": 11.764458656311035,
|
| 194 |
+
"learning_rate": 4.889652830829301e-07,
|
| 195 |
+
"loss": 1.0015,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.33,
|
| 200 |
+
"eval_loss": 0.9277215600013733,
|
| 201 |
+
"eval_runtime": 444.451,
|
| 202 |
+
"eval_samples_per_second": 22.122,
|
| 203 |
+
"eval_steps_per_second": 1.384,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.36,
|
| 208 |
+
"grad_norm": 20.98186492919922,
|
| 209 |
+
"learning_rate": 4.88116458704694e-07,
|
| 210 |
+
"loss": 0.9817,
|
| 211 |
+
"step": 1400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.36,
|
| 215 |
+
"eval_loss": 0.9151755571365356,
|
| 216 |
+
"eval_runtime": 444.2262,
|
| 217 |
+
"eval_samples_per_second": 22.133,
|
| 218 |
+
"eval_steps_per_second": 1.384,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.38,
|
| 223 |
+
"grad_norm": 19.44089126586914,
|
| 224 |
+
"learning_rate": 4.872676343264578e-07,
|
| 225 |
+
"loss": 0.9597,
|
| 226 |
+
"step": 1500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.38,
|
| 230 |
+
"eval_loss": 0.8940967321395874,
|
| 231 |
+
"eval_runtime": 444.5986,
|
| 232 |
+
"eval_samples_per_second": 22.114,
|
| 233 |
+
"eval_steps_per_second": 1.383,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.41,
|
| 238 |
+
"grad_norm": 70.98310089111328,
|
| 239 |
+
"learning_rate": 4.864188099482217e-07,
|
| 240 |
+
"loss": 0.9412,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.41,
|
| 245 |
+
"eval_loss": 0.8873820304870605,
|
| 246 |
+
"eval_runtime": 444.6432,
|
| 247 |
+
"eval_samples_per_second": 22.112,
|
| 248 |
+
"eval_steps_per_second": 1.383,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.43,
|
| 253 |
+
"grad_norm": 26.77646827697754,
|
| 254 |
+
"learning_rate": 4.855699855699855e-07,
|
| 255 |
+
"loss": 0.9246,
|
| 256 |
+
"step": 1700
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.43,
|
| 260 |
+
"eval_loss": 0.8573471903800964,
|
| 261 |
+
"eval_runtime": 444.4677,
|
| 262 |
+
"eval_samples_per_second": 22.121,
|
| 263 |
+
"eval_steps_per_second": 1.384,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.46,
|
| 268 |
+
"grad_norm": 14.278304100036621,
|
| 269 |
+
"learning_rate": 4.847211611917494e-07,
|
| 270 |
+
"loss": 0.9028,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.46,
|
| 275 |
+
"eval_loss": 0.8476628065109253,
|
| 276 |
+
"eval_runtime": 444.3449,
|
| 277 |
+
"eval_samples_per_second": 22.127,
|
| 278 |
+
"eval_steps_per_second": 1.384,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.48,
|
| 283 |
+
"grad_norm": 10.93651008605957,
|
| 284 |
+
"learning_rate": 4.838723368135133e-07,
|
| 285 |
+
"loss": 0.8823,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.48,
|
| 290 |
+
"eval_loss": 0.8142721652984619,
|
| 291 |
+
"eval_runtime": 444.2479,
|
| 292 |
+
"eval_samples_per_second": 22.132,
|
| 293 |
+
"eval_steps_per_second": 1.384,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.51,
|
| 298 |
+
"grad_norm": 20.362102508544922,
|
| 299 |
+
"learning_rate": 4.830235124352771e-07,
|
| 300 |
+
"loss": 0.8707,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.51,
|
| 305 |
+
"eval_loss": 0.7884088158607483,
|
| 306 |
+
"eval_runtime": 443.9954,
|
| 307 |
+
"eval_samples_per_second": 22.144,
|
| 308 |
+
"eval_steps_per_second": 1.385,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.53,
|
| 313 |
+
"grad_norm": 71.8848876953125,
|
| 314 |
+
"learning_rate": 4.82174688057041e-07,
|
| 315 |
+
"loss": 0.841,
|
| 316 |
+
"step": 2100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.53,
|
| 320 |
+
"eval_loss": 0.7523934245109558,
|
| 321 |
+
"eval_runtime": 443.8003,
|
| 322 |
+
"eval_samples_per_second": 22.154,
|
| 323 |
+
"eval_steps_per_second": 1.386,
|
| 324 |
+
"step": 2100
|
| 325 |
+
}
|
| 326 |
+
],
|
| 327 |
+
"logging_steps": 100,
|
| 328 |
+
"max_steps": 58905,
|
| 329 |
+
"num_input_tokens_seen": 0,
|
| 330 |
+
"num_train_epochs": 15,
|
| 331 |
+
"save_steps": 100,
|
| 332 |
+
"total_flos": 1.7850550446351974e+17,
|
| 333 |
+
"train_batch_size": 2,
|
| 334 |
+
"trial_name": null,
|
| 335 |
+
"trial_params": null
|
| 336 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08d2f8a0e6b970cb6d17806c3d5bf9b9df0041e8c6826265ab346e5555942920
|
| 3 |
+
size 5176
|