Ubuntu
commited on
Commit
•
8c2be6d
1
Parent(s):
bd7574e
first version
Browse files- config.json +26 -0
- pytorch_model.bin +3 -0
- trainer_state.json +376 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"transformers_version": "4.4.0",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 50265
|
| 26 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19409a0c71f4c704059f3e511807f939812c2f1293a2ae93ce28e3f879fbc28e
|
| 3 |
+
size 1421620681
|
trainer_state.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.45565962643131613,
|
| 3 |
+
"best_model_checkpoint": "",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 255184,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 2e-10,
|
| 13 |
+
"loss": 0.5804,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 1e-06,
|
| 19 |
+
"loss": 0.3416,
|
| 20 |
+
"step": 5000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.16,
|
| 24 |
+
"learning_rate": 2e-06,
|
| 25 |
+
"loss": 0.2775,
|
| 26 |
+
"step": 10000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.24,
|
| 30 |
+
"learning_rate": 1.967635445659913e-06,
|
| 31 |
+
"loss": 0.2661,
|
| 32 |
+
"step": 15000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.31,
|
| 36 |
+
"learning_rate": 1.9352708913198264e-06,
|
| 37 |
+
"loss": 0.2615,
|
| 38 |
+
"step": 20000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.39,
|
| 42 |
+
"learning_rate": 1.9029063369797399e-06,
|
| 43 |
+
"loss": 0.2637,
|
| 44 |
+
"step": 25000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.47,
|
| 48 |
+
"learning_rate": 1.870541782639653e-06,
|
| 49 |
+
"loss": 0.2597,
|
| 50 |
+
"step": 30000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.55,
|
| 54 |
+
"learning_rate": 1.8381772282995661e-06,
|
| 55 |
+
"loss": 0.2546,
|
| 56 |
+
"step": 35000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.63,
|
| 60 |
+
"learning_rate": 1.8058126739594794e-06,
|
| 61 |
+
"loss": 0.2593,
|
| 62 |
+
"step": 40000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.71,
|
| 66 |
+
"learning_rate": 1.7734481196193926e-06,
|
| 67 |
+
"loss": 0.2515,
|
| 68 |
+
"step": 45000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.78,
|
| 72 |
+
"learning_rate": 1.741083565279306e-06,
|
| 73 |
+
"loss": 0.2546,
|
| 74 |
+
"step": 50000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.86,
|
| 78 |
+
"learning_rate": 1.7087190109392193e-06,
|
| 79 |
+
"loss": 0.2567,
|
| 80 |
+
"step": 55000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.94,
|
| 84 |
+
"learning_rate": 1.6763544565991326e-06,
|
| 85 |
+
"loss": 0.2528,
|
| 86 |
+
"step": 60000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"eval_accuracy": 0.21571615150195908,
|
| 91 |
+
"eval_auc": 0.9180686985375446,
|
| 92 |
+
"eval_f1": 0.22147402418434062,
|
| 93 |
+
"eval_loss": 1.4364598989486694,
|
| 94 |
+
"eval_precision": 0.908817624677932,
|
| 95 |
+
"eval_recall": 0.21571615150195908,
|
| 96 |
+
"eval_runtime": 4.8065,
|
| 97 |
+
"eval_samples_per_second": 955.789,
|
| 98 |
+
"step": 63796
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.02,
|
| 102 |
+
"learning_rate": 1.6439899022590458e-06,
|
| 103 |
+
"loss": 0.2493,
|
| 104 |
+
"step": 65000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.1,
|
| 108 |
+
"learning_rate": 1.611625347918959e-06,
|
| 109 |
+
"loss": 0.2448,
|
| 110 |
+
"step": 70000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.18,
|
| 114 |
+
"learning_rate": 1.5792607935788725e-06,
|
| 115 |
+
"loss": 0.2507,
|
| 116 |
+
"step": 75000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.25,
|
| 120 |
+
"learning_rate": 1.5468962392387856e-06,
|
| 121 |
+
"loss": 0.2445,
|
| 122 |
+
"step": 80000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.33,
|
| 126 |
+
"learning_rate": 1.5145316848986988e-06,
|
| 127 |
+
"loss": 0.2481,
|
| 128 |
+
"step": 85000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.41,
|
| 132 |
+
"learning_rate": 1.482167130558612e-06,
|
| 133 |
+
"loss": 0.2452,
|
| 134 |
+
"step": 90000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.49,
|
| 138 |
+
"learning_rate": 1.4498025762185253e-06,
|
| 139 |
+
"loss": 0.2442,
|
| 140 |
+
"step": 95000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.57,
|
| 144 |
+
"learning_rate": 1.4174380218784387e-06,
|
| 145 |
+
"loss": 0.2443,
|
| 146 |
+
"step": 100000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.65,
|
| 150 |
+
"learning_rate": 1.385073467538352e-06,
|
| 151 |
+
"loss": 0.246,
|
| 152 |
+
"step": 105000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.72,
|
| 156 |
+
"learning_rate": 1.3527089131982652e-06,
|
| 157 |
+
"loss": 0.2503,
|
| 158 |
+
"step": 110000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.8,
|
| 162 |
+
"learning_rate": 1.3203443588581785e-06,
|
| 163 |
+
"loss": 0.2492,
|
| 164 |
+
"step": 115000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.88,
|
| 168 |
+
"learning_rate": 1.2879798045180917e-06,
|
| 169 |
+
"loss": 0.2429,
|
| 170 |
+
"step": 120000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.96,
|
| 174 |
+
"learning_rate": 1.255615250178005e-06,
|
| 175 |
+
"loss": 0.2491,
|
| 176 |
+
"step": 125000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.0,
|
| 180 |
+
"eval_accuracy": 0.3243360905528951,
|
| 181 |
+
"eval_auc": 0.9164518557207816,
|
| 182 |
+
"eval_f1": 0.3794720254407353,
|
| 183 |
+
"eval_loss": 1.2563140392303467,
|
| 184 |
+
"eval_precision": 0.9077943374743213,
|
| 185 |
+
"eval_recall": 0.3243360905528951,
|
| 186 |
+
"eval_runtime": 4.7493,
|
| 187 |
+
"eval_samples_per_second": 967.295,
|
| 188 |
+
"step": 127592
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.04,
|
| 192 |
+
"learning_rate": 1.2232506958379182e-06,
|
| 193 |
+
"loss": 0.2508,
|
| 194 |
+
"step": 130000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.12,
|
| 198 |
+
"learning_rate": 1.1908861414978315e-06,
|
| 199 |
+
"loss": 0.2422,
|
| 200 |
+
"step": 135000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.19,
|
| 204 |
+
"learning_rate": 1.1585215871577447e-06,
|
| 205 |
+
"loss": 0.2404,
|
| 206 |
+
"step": 140000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.27,
|
| 210 |
+
"learning_rate": 1.126157032817658e-06,
|
| 211 |
+
"loss": 0.2347,
|
| 212 |
+
"step": 145000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.35,
|
| 216 |
+
"learning_rate": 1.0937924784775714e-06,
|
| 217 |
+
"loss": 0.2441,
|
| 218 |
+
"step": 150000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.43,
|
| 222 |
+
"learning_rate": 1.0614279241374847e-06,
|
| 223 |
+
"loss": 0.2456,
|
| 224 |
+
"step": 155000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.51,
|
| 228 |
+
"learning_rate": 1.029063369797398e-06,
|
| 229 |
+
"loss": 0.2375,
|
| 230 |
+
"step": 160000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.59,
|
| 234 |
+
"learning_rate": 9.966988154573111e-07,
|
| 235 |
+
"loss": 0.2441,
|
| 236 |
+
"step": 165000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.66,
|
| 240 |
+
"learning_rate": 9.643342611172244e-07,
|
| 241 |
+
"loss": 0.2376,
|
| 242 |
+
"step": 170000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.74,
|
| 246 |
+
"learning_rate": 9.319697067771376e-07,
|
| 247 |
+
"loss": 0.2386,
|
| 248 |
+
"step": 175000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.82,
|
| 252 |
+
"learning_rate": 8.996051524370509e-07,
|
| 253 |
+
"loss": 0.2387,
|
| 254 |
+
"step": 180000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.9,
|
| 258 |
+
"learning_rate": 8.672405980969641e-07,
|
| 259 |
+
"loss": 0.238,
|
| 260 |
+
"step": 185000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.98,
|
| 264 |
+
"learning_rate": 8.348760437568775e-07,
|
| 265 |
+
"loss": 0.234,
|
| 266 |
+
"step": 190000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.0,
|
| 270 |
+
"eval_accuracy": 0.32063561166739224,
|
| 271 |
+
"eval_auc": 0.9156791507926754,
|
| 272 |
+
"eval_f1": 0.3746009193872616,
|
| 273 |
+
"eval_loss": 1.388353705406189,
|
| 274 |
+
"eval_precision": 0.9076853642985949,
|
| 275 |
+
"eval_recall": 0.32063561166739224,
|
| 276 |
+
"eval_runtime": 4.7646,
|
| 277 |
+
"eval_samples_per_second": 964.188,
|
| 278 |
+
"step": 191388
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.06,
|
| 282 |
+
"learning_rate": 8.025114894167907e-07,
|
| 283 |
+
"loss": 0.2366,
|
| 284 |
+
"step": 195000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.13,
|
| 288 |
+
"learning_rate": 7.70146935076704e-07,
|
| 289 |
+
"loss": 0.2343,
|
| 290 |
+
"step": 200000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.21,
|
| 294 |
+
"learning_rate": 7.377823807366172e-07,
|
| 295 |
+
"loss": 0.2353,
|
| 296 |
+
"step": 205000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.29,
|
| 300 |
+
"learning_rate": 7.054178263965305e-07,
|
| 301 |
+
"loss": 0.2353,
|
| 302 |
+
"step": 210000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.37,
|
| 306 |
+
"learning_rate": 6.730532720564438e-07,
|
| 307 |
+
"loss": 0.2328,
|
| 308 |
+
"step": 215000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.45,
|
| 312 |
+
"learning_rate": 6.40688717716357e-07,
|
| 313 |
+
"loss": 0.2332,
|
| 314 |
+
"step": 220000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.53,
|
| 318 |
+
"learning_rate": 6.083241633762702e-07,
|
| 319 |
+
"loss": 0.2374,
|
| 320 |
+
"step": 225000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.61,
|
| 324 |
+
"learning_rate": 5.759596090361835e-07,
|
| 325 |
+
"loss": 0.2367,
|
| 326 |
+
"step": 230000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.68,
|
| 330 |
+
"learning_rate": 5.435950546960968e-07,
|
| 331 |
+
"loss": 0.2379,
|
| 332 |
+
"step": 235000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.76,
|
| 336 |
+
"learning_rate": 5.112305003560101e-07,
|
| 337 |
+
"loss": 0.2354,
|
| 338 |
+
"step": 240000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.84,
|
| 342 |
+
"learning_rate": 4.788659460159234e-07,
|
| 343 |
+
"loss": 0.235,
|
| 344 |
+
"step": 245000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.92,
|
| 348 |
+
"learning_rate": 4.4650139167583663e-07,
|
| 349 |
+
"loss": 0.2362,
|
| 350 |
+
"step": 250000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.0,
|
| 354 |
+
"learning_rate": 4.1413683733574987e-07,
|
| 355 |
+
"loss": 0.24,
|
| 356 |
+
"step": 255000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.0,
|
| 360 |
+
"eval_accuracy": 0.38528515454941226,
|
| 361 |
+
"eval_auc": 0.9194136352464053,
|
| 362 |
+
"eval_f1": 0.45565962643131613,
|
| 363 |
+
"eval_loss": 1.2999894618988037,
|
| 364 |
+
"eval_precision": 0.9088106767314909,
|
| 365 |
+
"eval_recall": 0.38528515454941226,
|
| 366 |
+
"eval_runtime": 4.7332,
|
| 367 |
+
"eval_samples_per_second": 970.591,
|
| 368 |
+
"step": 255184
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"max_steps": 318980,
|
| 372 |
+
"num_train_epochs": 5,
|
| 373 |
+
"total_flos": 4.841807205051138e+18,
|
| 374 |
+
"trial_name": null,
|
| 375 |
+
"trial_params": null
|
| 376 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3a8272ddb783ba53f59cd8b37ec313c86f17364074e3f6a80a4f253d967b2b9
|
| 3 |
+
size 2287
|