Commit
•
e396e59
1
Parent(s):
de2dcf0
Upload 6 files
Browse files- config.json +28 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +305 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "PlanTL-GOB-ES/roberta-base-biomedical-clinical-es",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.33.1",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 52000
|
| 28 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48f20b17afbae757c98bfd2ee8e27793e4a15474b5739695a02cd55eab970098
|
| 3 |
+
size 504196085
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30a4093a19e0b412d83a6a2e14e2c944d2c037f75b77aa98ebc1e04bae35343f
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:915ddf582b857296893c3eb37ae3089b1433ce30ab44ff60fdce553a683fa49c
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 22678,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 1.9823617602963227e-05,
|
| 14 |
+
"loss": 1.393,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.09,
|
| 19 |
+
"learning_rate": 1.964723520592645e-05,
|
| 20 |
+
"loss": 1.3599,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.13,
|
| 25 |
+
"learning_rate": 1.9470852808889677e-05,
|
| 26 |
+
"loss": 1.3453,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.18,
|
| 31 |
+
"learning_rate": 1.92944704118529e-05,
|
| 32 |
+
"loss": 1.3328,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.22,
|
| 37 |
+
"learning_rate": 1.9118088014816124e-05,
|
| 38 |
+
"loss": 1.3271,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.26,
|
| 43 |
+
"learning_rate": 1.8941705617779345e-05,
|
| 44 |
+
"loss": 1.3291,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.31,
|
| 49 |
+
"learning_rate": 1.876532322074257e-05,
|
| 50 |
+
"loss": 1.3199,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"learning_rate": 1.8588940823705796e-05,
|
| 56 |
+
"loss": 1.3173,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.4,
|
| 61 |
+
"learning_rate": 1.841255842666902e-05,
|
| 62 |
+
"loss": 1.3141,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.44,
|
| 67 |
+
"learning_rate": 1.8236176029632246e-05,
|
| 68 |
+
"loss": 1.3151,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.49,
|
| 73 |
+
"learning_rate": 1.8059793632595468e-05,
|
| 74 |
+
"loss": 1.3105,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.53,
|
| 79 |
+
"learning_rate": 1.7883411235558693e-05,
|
| 80 |
+
"loss": 1.3042,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.57,
|
| 85 |
+
"learning_rate": 1.7707028838521918e-05,
|
| 86 |
+
"loss": 1.2985,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.62,
|
| 91 |
+
"learning_rate": 1.7530646441485143e-05,
|
| 92 |
+
"loss": 1.2946,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.66,
|
| 97 |
+
"learning_rate": 1.7354264044448365e-05,
|
| 98 |
+
"loss": 1.2958,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.71,
|
| 103 |
+
"learning_rate": 1.717788164741159e-05,
|
| 104 |
+
"loss": 1.2867,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.75,
|
| 109 |
+
"learning_rate": 1.7001499250374815e-05,
|
| 110 |
+
"loss": 1.2938,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.79,
|
| 115 |
+
"learning_rate": 1.682511685333804e-05,
|
| 116 |
+
"loss": 1.2934,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.84,
|
| 121 |
+
"learning_rate": 1.664873445630126e-05,
|
| 122 |
+
"loss": 1.2892,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.88,
|
| 127 |
+
"learning_rate": 1.6472352059264487e-05,
|
| 128 |
+
"loss": 1.2835,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.93,
|
| 133 |
+
"learning_rate": 1.6295969662227712e-05,
|
| 134 |
+
"loss": 1.2838,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.97,
|
| 139 |
+
"learning_rate": 1.6119587265190934e-05,
|
| 140 |
+
"loss": 1.2842,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.0,
|
| 145 |
+
"eval_loss": 1.2190536260604858,
|
| 146 |
+
"eval_runtime": 28.9964,
|
| 147 |
+
"eval_samples_per_second": 30.728,
|
| 148 |
+
"eval_steps_per_second": 1.931,
|
| 149 |
+
"step": 11339
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.01,
|
| 153 |
+
"learning_rate": 1.594320486815416e-05,
|
| 154 |
+
"loss": 1.2845,
|
| 155 |
+
"step": 11500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.06,
|
| 159 |
+
"learning_rate": 1.5766822471117384e-05,
|
| 160 |
+
"loss": 1.276,
|
| 161 |
+
"step": 12000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.1,
|
| 165 |
+
"learning_rate": 1.559044007408061e-05,
|
| 166 |
+
"loss": 1.2702,
|
| 167 |
+
"step": 12500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.15,
|
| 171 |
+
"learning_rate": 1.541405767704383e-05,
|
| 172 |
+
"loss": 1.2726,
|
| 173 |
+
"step": 13000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.19,
|
| 177 |
+
"learning_rate": 1.5237675280007056e-05,
|
| 178 |
+
"loss": 1.2744,
|
| 179 |
+
"step": 13500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.23,
|
| 183 |
+
"learning_rate": 1.5061292882970279e-05,
|
| 184 |
+
"loss": 1.2741,
|
| 185 |
+
"step": 14000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.28,
|
| 189 |
+
"learning_rate": 1.4884910485933506e-05,
|
| 190 |
+
"loss": 1.2642,
|
| 191 |
+
"step": 14500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.32,
|
| 195 |
+
"learning_rate": 1.470852808889673e-05,
|
| 196 |
+
"loss": 1.2635,
|
| 197 |
+
"step": 15000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.37,
|
| 201 |
+
"learning_rate": 1.4532145691859953e-05,
|
| 202 |
+
"loss": 1.2656,
|
| 203 |
+
"step": 15500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.41,
|
| 207 |
+
"learning_rate": 1.4355763294823178e-05,
|
| 208 |
+
"loss": 1.2606,
|
| 209 |
+
"step": 16000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.46,
|
| 213 |
+
"learning_rate": 1.4179380897786401e-05,
|
| 214 |
+
"loss": 1.2652,
|
| 215 |
+
"step": 16500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.5,
|
| 219 |
+
"learning_rate": 1.4002998500749626e-05,
|
| 220 |
+
"loss": 1.2636,
|
| 221 |
+
"step": 17000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.54,
|
| 225 |
+
"learning_rate": 1.3826616103712851e-05,
|
| 226 |
+
"loss": 1.2712,
|
| 227 |
+
"step": 17500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.59,
|
| 231 |
+
"learning_rate": 1.3650233706676075e-05,
|
| 232 |
+
"loss": 1.2634,
|
| 233 |
+
"step": 18000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.63,
|
| 237 |
+
"learning_rate": 1.3473851309639298e-05,
|
| 238 |
+
"loss": 1.2585,
|
| 239 |
+
"step": 18500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.68,
|
| 243 |
+
"learning_rate": 1.3297468912602522e-05,
|
| 244 |
+
"loss": 1.2556,
|
| 245 |
+
"step": 19000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.72,
|
| 249 |
+
"learning_rate": 1.3121086515565748e-05,
|
| 250 |
+
"loss": 1.2595,
|
| 251 |
+
"step": 19500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.76,
|
| 255 |
+
"learning_rate": 1.2944704118528972e-05,
|
| 256 |
+
"loss": 1.2609,
|
| 257 |
+
"step": 20000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.81,
|
| 261 |
+
"learning_rate": 1.2768321721492197e-05,
|
| 262 |
+
"loss": 1.2552,
|
| 263 |
+
"step": 20500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.85,
|
| 267 |
+
"learning_rate": 1.259193932445542e-05,
|
| 268 |
+
"loss": 1.2548,
|
| 269 |
+
"step": 21000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.9,
|
| 273 |
+
"learning_rate": 1.2415556927418644e-05,
|
| 274 |
+
"loss": 1.2599,
|
| 275 |
+
"step": 21500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.94,
|
| 279 |
+
"learning_rate": 1.223917453038187e-05,
|
| 280 |
+
"loss": 1.2582,
|
| 281 |
+
"step": 22000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.98,
|
| 285 |
+
"learning_rate": 1.2062792133345094e-05,
|
| 286 |
+
"loss": 1.2563,
|
| 287 |
+
"step": 22500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.0,
|
| 291 |
+
"eval_loss": 1.1791033744812012,
|
| 292 |
+
"eval_runtime": 29.0168,
|
| 293 |
+
"eval_samples_per_second": 30.706,
|
| 294 |
+
"eval_steps_per_second": 1.93,
|
| 295 |
+
"step": 22678
|
| 296 |
+
}
|
| 297 |
+
],
|
| 298 |
+
"logging_steps": 500,
|
| 299 |
+
"max_steps": 56695,
|
| 300 |
+
"num_train_epochs": 5,
|
| 301 |
+
"save_steps": 500,
|
| 302 |
+
"total_flos": 9.552148881938842e+16,
|
| 303 |
+
"trial_name": null,
|
| 304 |
+
"trial_params": null
|
| 305 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19db034c821e200ea9eda289f1825e2f13a0556ca0338099099ff9d19a1fb63c
|
| 3 |
+
size 4091
|