Commit
•
42c8927
1
Parent(s):
012bb1e
Model save
Browse files- last-checkpoint/config.json +0 -47
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scaler.pt +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/special_tokens_map.json +0 -9
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +0 -12
- last-checkpoint/trainer_state.json +0 -361
- last-checkpoint/training_args.bin +0 -3
last-checkpoint/config.json
DELETED
|
@@ -1,47 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "data/plms/legal-swiss-longformer-base",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"LongformerForMaskedLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_mode": "longformer",
|
| 7 |
-
"attention_probs_dropout_prob": 0.1,
|
| 8 |
-
"attention_window": [
|
| 9 |
-
128,
|
| 10 |
-
128,
|
| 11 |
-
128,
|
| 12 |
-
128,
|
| 13 |
-
128,
|
| 14 |
-
128,
|
| 15 |
-
128,
|
| 16 |
-
128,
|
| 17 |
-
128,
|
| 18 |
-
128,
|
| 19 |
-
128,
|
| 20 |
-
128
|
| 21 |
-
],
|
| 22 |
-
"bos_token_id": 1,
|
| 23 |
-
"classifier_dropout": null,
|
| 24 |
-
"cls_token_id": 1,
|
| 25 |
-
"eos_token_id": 2,
|
| 26 |
-
"gradient_checkpointing": false,
|
| 27 |
-
"hidden_act": "gelu",
|
| 28 |
-
"hidden_dropout_prob": 0.1,
|
| 29 |
-
"hidden_size": 768,
|
| 30 |
-
"ignore_attention_mask": false,
|
| 31 |
-
"initializer_range": 0.02,
|
| 32 |
-
"intermediate_size": 3072,
|
| 33 |
-
"layer_norm_eps": 1e-05,
|
| 34 |
-
"max_position_embeddings": 4098,
|
| 35 |
-
"model_max_length": 4096,
|
| 36 |
-
"model_type": "longformer",
|
| 37 |
-
"num_attention_heads": 12,
|
| 38 |
-
"num_hidden_layers": 12,
|
| 39 |
-
"onnx_export": false,
|
| 40 |
-
"pad_token_id": 0,
|
| 41 |
-
"position_embedding_type": "absolute",
|
| 42 |
-
"sep_token_id": 2,
|
| 43 |
-
"torch_dtype": "float32",
|
| 44 |
-
"transformers_version": "4.28.1",
|
| 45 |
-
"type_vocab_size": 1,
|
| 46 |
-
"vocab_size": 128000
|
| 47 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3a7a7b74f0bb8ba3dd1dd4dc306821d513a5b6eb6e1e61b35cfa900acf2184d9
|
| 3 |
-
size 1668076741
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:673ac62a80dcc8c7dcaf1349eabda0bda23e6d751fefb44d0b2d19229735b6e6
|
| 3 |
-
size 834053717
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9798dba2e223f6f58089e1ac563fc21dbbd2a04ee79b7799a73465905128acbc
|
| 3 |
-
size 15597
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/scaler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:111b606e2964954247e4280c4d2523625af5e370ffbcc02565e12f30d3a20502
|
| 3 |
-
size 557
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:65f46bcd9b706c3b50e169ec7299f52079cd259ed510e5bb7185501f5df4ed46
|
| 3 |
-
size 627
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/special_tokens_map.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
-
"cls_token": "<s>",
|
| 4 |
-
"eos_token": "</s>",
|
| 5 |
-
"mask_token": "<mask>",
|
| 6 |
-
"pad_token": "<pad>",
|
| 7 |
-
"sep_token": "</s>",
|
| 8 |
-
"unk_token": "<unk>"
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
-
"clean_up_tokenization_spaces": true,
|
| 4 |
-
"cls_token": "<s>",
|
| 5 |
-
"eos_token": "</s>",
|
| 6 |
-
"mask_token": "<mask>",
|
| 7 |
-
"model_max_length": 4096,
|
| 8 |
-
"pad_token": "<pad>",
|
| 9 |
-
"sep_token": "</s>",
|
| 10 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 11 |
-
"unk_token": "<unk>"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
|
@@ -1,361 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.0,
|
| 5 |
-
"global_step": 50000,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.02,
|
| 12 |
-
"learning_rate": 1.1904e-05,
|
| 13 |
-
"loss": 1.4759,
|
| 14 |
-
"step": 1000
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.04,
|
| 18 |
-
"learning_rate": 2.3880000000000002e-05,
|
| 19 |
-
"loss": 2.0784,
|
| 20 |
-
"step": 2000
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.06,
|
| 24 |
-
"learning_rate": 2.9992187757207995e-05,
|
| 25 |
-
"loss": 1.8615,
|
| 26 |
-
"step": 3000
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 0.08,
|
| 30 |
-
"learning_rate": 2.9927417972317198e-05,
|
| 31 |
-
"loss": 0.9561,
|
| 32 |
-
"step": 4000
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.1,
|
| 36 |
-
"learning_rate": 2.97973743867291e-05,
|
| 37 |
-
"loss": 0.8567,
|
| 38 |
-
"step": 5000
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.12,
|
| 42 |
-
"learning_rate": 2.9602625647955514e-05,
|
| 43 |
-
"loss": 0.7767,
|
| 44 |
-
"step": 6000
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.14,
|
| 48 |
-
"learning_rate": 2.9344023342679696e-05,
|
| 49 |
-
"loss": 0.7502,
|
| 50 |
-
"step": 7000
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.16,
|
| 54 |
-
"learning_rate": 2.9022698272984482e-05,
|
| 55 |
-
"loss": 0.8425,
|
| 56 |
-
"step": 8000
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.18,
|
| 60 |
-
"learning_rate": 2.8640055511642487e-05,
|
| 61 |
-
"loss": 0.7989,
|
| 62 |
-
"step": 9000
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.2,
|
| 66 |
-
"learning_rate": 2.8197768258090375e-05,
|
| 67 |
-
"loss": 0.8392,
|
| 68 |
-
"step": 10000
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 0.2,
|
| 72 |
-
"eval_accuracy": 0.8492928069198428,
|
| 73 |
-
"eval_loss": 0.6663709282875061,
|
| 74 |
-
"eval_runtime": 121.7475,
|
| 75 |
-
"eval_samples_per_second": 41.069,
|
| 76 |
-
"eval_steps_per_second": 2.571,
|
| 77 |
-
"step": 10000
|
| 78 |
-
},
|
| 79 |
-
{
|
| 80 |
-
"epoch": 0.22,
|
| 81 |
-
"learning_rate": 2.7697770521953444e-05,
|
| 82 |
-
"loss": 0.8444,
|
| 83 |
-
"step": 11000
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 0.24,
|
| 87 |
-
"learning_rate": 2.714224866611362e-05,
|
| 88 |
-
"loss": 0.7575,
|
| 89 |
-
"step": 12000
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 0.26,
|
| 93 |
-
"learning_rate": 2.6533631846300875e-05,
|
| 94 |
-
"loss": 0.7919,
|
| 95 |
-
"step": 13000
|
| 96 |
-
},
|
| 97 |
-
{
|
| 98 |
-
"epoch": 0.28,
|
| 99 |
-
"learning_rate": 2.587458138901327e-05,
|
| 100 |
-
"loss": 0.833,
|
| 101 |
-
"step": 14000
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 0.3,
|
| 105 |
-
"learning_rate": 2.516797915421335e-05,
|
| 106 |
-
"loss": 0.8335,
|
| 107 |
-
"step": 15000
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.32,
|
| 111 |
-
"learning_rate": 2.4416914933687753e-05,
|
| 112 |
-
"loss": 0.8382,
|
| 113 |
-
"step": 16000
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 0.34,
|
| 117 |
-
"learning_rate": 2.3624672940173894e-05,
|
| 118 |
-
"loss": 0.8253,
|
| 119 |
-
"step": 17000
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 0.36,
|
| 123 |
-
"learning_rate": 2.27947174463333e-05,
|
| 124 |
-
"loss": 0.8442,
|
| 125 |
-
"step": 18000
|
| 126 |
-
},
|
| 127 |
-
{
|
| 128 |
-
"epoch": 0.38,
|
| 129 |
-
"learning_rate": 2.193067763636869e-05,
|
| 130 |
-
"loss": 0.8794,
|
| 131 |
-
"step": 19000
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch": 0.4,
|
| 135 |
-
"learning_rate": 2.1036331736524874e-05,
|
| 136 |
-
"loss": 0.8631,
|
| 137 |
-
"step": 20000
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 0.4,
|
| 141 |
-
"eval_accuracy": 0.855058580917128,
|
| 142 |
-
"eval_loss": 0.6343714594841003,
|
| 143 |
-
"eval_runtime": 151.1949,
|
| 144 |
-
"eval_samples_per_second": 33.07,
|
| 145 |
-
"eval_steps_per_second": 2.07,
|
| 146 |
-
"step": 20000
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 0.42,
|
| 150 |
-
"learning_rate": 2.011652308828144e-05,
|
| 151 |
-
"loss": 0.7647,
|
| 152 |
-
"step": 21000
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 0.44,
|
| 156 |
-
"learning_rate": 1.917343299405194e-05,
|
| 157 |
-
"loss": 0.7081,
|
| 158 |
-
"step": 22000
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 0.46,
|
| 162 |
-
"learning_rate": 1.8212093539217514e-05,
|
| 163 |
-
"loss": 0.7579,
|
| 164 |
-
"step": 23000
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 0.48,
|
| 168 |
-
"learning_rate": 1.72367084166133e-05,
|
| 169 |
-
"loss": 0.7132,
|
| 170 |
-
"step": 24000
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.5,
|
| 174 |
-
"learning_rate": 1.6252531357090434e-05,
|
| 175 |
-
"loss": 0.7895,
|
| 176 |
-
"step": 25000
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 0.52,
|
| 180 |
-
"learning_rate": 1.52618963110846e-05,
|
| 181 |
-
"loss": 0.7258,
|
| 182 |
-
"step": 26000
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 0.54,
|
| 186 |
-
"learning_rate": 1.4270116059146648e-05,
|
| 187 |
-
"loss": 0.7327,
|
| 188 |
-
"step": 27000
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 0.56,
|
| 192 |
-
"learning_rate": 1.328152740397216e-05,
|
| 193 |
-
"loss": 0.8063,
|
| 194 |
-
"step": 28000
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 0.58,
|
| 198 |
-
"learning_rate": 1.2301429081434528e-05,
|
| 199 |
-
"loss": 0.7966,
|
| 200 |
-
"step": 29000
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 0.6,
|
| 204 |
-
"learning_rate": 1.1332145369350178e-05,
|
| 205 |
-
"loss": 0.7693,
|
| 206 |
-
"step": 30000
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.6,
|
| 210 |
-
"eval_accuracy": 0.8589594943032635,
|
| 211 |
-
"eval_loss": 0.6138944029808044,
|
| 212 |
-
"eval_runtime": 125.8255,
|
| 213 |
-
"eval_samples_per_second": 39.738,
|
| 214 |
-
"eval_steps_per_second": 2.488,
|
| 215 |
-
"step": 30000
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 0.62,
|
| 219 |
-
"learning_rate": 1.0379844092057256e-05,
|
| 220 |
-
"loss": 0.7337,
|
| 221 |
-
"step": 31000
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 0.64,
|
| 225 |
-
"learning_rate": 9.446783607398505e-06,
|
| 226 |
-
"loss": 0.6781,
|
| 227 |
-
"step": 32000
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 0.66,
|
| 231 |
-
"learning_rate": 8.538901241148115e-06,
|
| 232 |
-
"loss": 0.7332,
|
| 233 |
-
"step": 33000
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 0.68,
|
| 237 |
-
"learning_rate": 7.659215159142834e-06,
|
| 238 |
-
"loss": 0.8189,
|
| 239 |
-
"step": 34000
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 0.7,
|
| 243 |
-
"learning_rate": 6.810733117141998e-06,
|
| 244 |
-
"loss": 0.8406,
|
| 245 |
-
"step": 35000
|
| 246 |
-
},
|
| 247 |
-
{
|
| 248 |
-
"epoch": 0.72,
|
| 249 |
-
"learning_rate": 5.998060655562913e-06,
|
| 250 |
-
"loss": 0.8554,
|
| 251 |
-
"step": 36000
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 0.74,
|
| 255 |
-
"learning_rate": 5.224751384305667e-06,
|
| 256 |
-
"loss": 0.8401,
|
| 257 |
-
"step": 37000
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 0.76,
|
| 261 |
-
"learning_rate": 4.494186788054548e-06,
|
| 262 |
-
"loss": 0.7826,
|
| 263 |
-
"step": 38000
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 0.78,
|
| 267 |
-
"learning_rate": 3.8095614399059063e-06,
|
| 268 |
-
"loss": 0.7544,
|
| 269 |
-
"step": 39000
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 0.8,
|
| 273 |
-
"learning_rate": 3.1744793390868967e-06,
|
| 274 |
-
"loss": 0.7466,
|
| 275 |
-
"step": 40000
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 0.8,
|
| 279 |
-
"eval_accuracy": 0.8594107078575001,
|
| 280 |
-
"eval_loss": 0.6134777665138245,
|
| 281 |
-
"eval_runtime": 124.9907,
|
| 282 |
-
"eval_samples_per_second": 40.003,
|
| 283 |
-
"eval_steps_per_second": 2.504,
|
| 284 |
-
"step": 40000
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 0.82,
|
| 288 |
-
"learning_rate": 2.5904465663698255e-06,
|
| 289 |
-
"loss": 0.7148,
|
| 290 |
-
"step": 41000
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 0.84,
|
| 294 |
-
"learning_rate": 2.0606776133616594e-06,
|
| 295 |
-
"loss": 0.7148,
|
| 296 |
-
"step": 42000
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 0.86,
|
| 300 |
-
"learning_rate": 1.5874890249007857e-06,
|
| 301 |
-
"loss": 0.8135,
|
| 302 |
-
"step": 43000
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 0.88,
|
| 306 |
-
"learning_rate": 1.1729499342876049e-06,
|
| 307 |
-
"loss": 0.8566,
|
| 308 |
-
"step": 44000
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 0.9,
|
| 312 |
-
"learning_rate": 8.19196353853926e-07,
|
| 313 |
-
"loss": 0.8101,
|
| 314 |
-
"step": 45000
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 0.92,
|
| 318 |
-
"learning_rate": 5.270672010640238e-07,
|
| 319 |
-
"loss": 0.7488,
|
| 320 |
-
"step": 46000
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 0.94,
|
| 324 |
-
"learning_rate": 2.982245009463186e-07,
|
| 325 |
-
"loss": 0.6483,
|
| 326 |
-
"step": 47000
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 0.96,
|
| 330 |
-
"learning_rate": 1.3393335157752762e-07,
|
| 331 |
-
"loss": 0.6717,
|
| 332 |
-
"step": 48000
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 0.98,
|
| 336 |
-
"learning_rate": 3.425391532401623e-08,
|
| 337 |
-
"loss": 0.6661,
|
| 338 |
-
"step": 49000
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 1.0,
|
| 342 |
-
"learning_rate": 1.5878851039041742e-11,
|
| 343 |
-
"loss": 0.7593,
|
| 344 |
-
"step": 50000
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 1.0,
|
| 348 |
-
"eval_accuracy": 0.8603840251781334,
|
| 349 |
-
"eval_loss": 0.6071112155914307,
|
| 350 |
-
"eval_runtime": 157.0885,
|
| 351 |
-
"eval_samples_per_second": 31.829,
|
| 352 |
-
"eval_steps_per_second": 1.993,
|
| 353 |
-
"step": 50000
|
| 354 |
-
}
|
| 355 |
-
],
|
| 356 |
-
"max_steps": 50000,
|
| 357 |
-
"num_train_epochs": 9223372036854775807,
|
| 358 |
-
"total_flos": 3.3671067205632e+19,
|
| 359 |
-
"trial_name": null,
|
| 360 |
-
"trial_params": null
|
| 361 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:cc7a2fca956110fa8feafc0aa6cd21981160f54c916ff419fbc9ee0826ac6859
|
| 3 |
-
size 3771
|
|
|
|
|
|
|
|
|
|
|
|