Commit
·
8abe706
1
Parent(s):
983c796
End of training
Browse files- last-checkpoint/added_tokens.json +0 -4
- last-checkpoint/config.json +0 -39
- last-checkpoint/generation_config.json +0 -6
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/special_tokens_map.json +0 -6
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +0 -10
- last-checkpoint/trainer_state.json +0 -636
- last-checkpoint/training_args.bin +0 -3
- last-checkpoint/vocab.json +0 -0
last-checkpoint/added_tokens.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<|pad|>": 50258,
|
| 3 |
-
"<|startoftext|>": 50257
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/config.json
DELETED
|
@@ -1,39 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "augustocsc/gpt-m-large",
|
| 3 |
-
"activation_function": "gelu_new",
|
| 4 |
-
"architectures": [
|
| 5 |
-
"GPT2LMHeadModel"
|
| 6 |
-
],
|
| 7 |
-
"attn_pdrop": 0.1,
|
| 8 |
-
"bos_token_id": 50256,
|
| 9 |
-
"embd_pdrop": 0.1,
|
| 10 |
-
"eos_token_id": 50256,
|
| 11 |
-
"initializer_range": 0.02,
|
| 12 |
-
"layer_norm_epsilon": 1e-05,
|
| 13 |
-
"model_type": "gpt2",
|
| 14 |
-
"n_ctx": 1024,
|
| 15 |
-
"n_embd": 768,
|
| 16 |
-
"n_head": 12,
|
| 17 |
-
"n_inner": null,
|
| 18 |
-
"n_layer": 12,
|
| 19 |
-
"n_positions": 1024,
|
| 20 |
-
"reorder_and_upcast_attn": false,
|
| 21 |
-
"resid_pdrop": 0.1,
|
| 22 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
-
"scale_attn_weights": true,
|
| 24 |
-
"summary_activation": null,
|
| 25 |
-
"summary_first_dropout": 0.1,
|
| 26 |
-
"summary_proj_to_labels": true,
|
| 27 |
-
"summary_type": "cls_index",
|
| 28 |
-
"summary_use_proj": true,
|
| 29 |
-
"task_specific_params": {
|
| 30 |
-
"text-generation": {
|
| 31 |
-
"do_sample": true,
|
| 32 |
-
"max_length": 50
|
| 33 |
-
}
|
| 34 |
-
},
|
| 35 |
-
"torch_dtype": "float32",
|
| 36 |
-
"transformers_version": "4.27.3",
|
| 37 |
-
"use_cache": true,
|
| 38 |
-
"vocab_size": 50259
|
| 39 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/generation_config.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 50256,
|
| 4 |
-
"eos_token_id": 50256,
|
| 5 |
-
"transformers_version": "4.27.3"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0941c2c0912ed1fa30a9d7cf23a269cf0b470601b299679e02592ec7ec6e8f8f
|
| 3 |
-
size 995617477
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1297ce69d908f6522240d239df7d516fd83a4304f843ca1dc99a5404b0828f30
|
| 3 |
-
size 510404157
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:576ddc1c3ff51d63d5d91b97e907ce6f6a05a1f64623f09c19161200665c54ff
|
| 3 |
-
size 14575
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4700ed25c9ddf06aa39c5954eb81d53f025ad6d606e5311b9eef31815b913fb7
|
| 3 |
-
size 627
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/special_tokens_map.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<|startoftext|>",
|
| 3 |
-
"eos_token": "<|endoftext|>",
|
| 4 |
-
"pad_token": "<|pad|>",
|
| 5 |
-
"unk_token": "<|endoftext|>"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
DELETED
|
@@ -1,10 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": "<|startoftext|>",
|
| 4 |
-
"eos_token": "<|endoftext|>",
|
| 5 |
-
"model_max_length": 1024,
|
| 6 |
-
"pad_token": "<|pad|>",
|
| 7 |
-
"special_tokens_map_file": null,
|
| 8 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
-
"unk_token": "<|endoftext|>"
|
| 10 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
|
@@ -1,636 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.9738321867244684,
|
| 5 |
-
"global_step": 31000,
|
| 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": 4.8426210969403785e-05,
|
| 13 |
-
"loss": 0.0344,
|
| 14 |
-
"step": 500
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.03,
|
| 18 |
-
"learning_rate": 4.685556323427782e-05,
|
| 19 |
-
"loss": 0.0343,
|
| 20 |
-
"step": 1000
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.03,
|
| 24 |
-
"eval_loss": 0.034323398023843765,
|
| 25 |
-
"eval_runtime": 1135.0793,
|
| 26 |
-
"eval_samples_per_second": 99.715,
|
| 27 |
-
"eval_steps_per_second": 1.558,
|
| 28 |
-
"step": 1000
|
| 29 |
-
},
|
| 30 |
-
{
|
| 31 |
-
"epoch": 0.05,
|
| 32 |
-
"learning_rate": 4.528491549915185e-05,
|
| 33 |
-
"loss": 0.0348,
|
| 34 |
-
"step": 1500
|
| 35 |
-
},
|
| 36 |
-
{
|
| 37 |
-
"epoch": 0.06,
|
| 38 |
-
"learning_rate": 4.3714267764025886e-05,
|
| 39 |
-
"loss": 0.0337,
|
| 40 |
-
"step": 2000
|
| 41 |
-
},
|
| 42 |
-
{
|
| 43 |
-
"epoch": 0.06,
|
| 44 |
-
"eval_loss": 0.034191686660051346,
|
| 45 |
-
"eval_runtime": 1134.7063,
|
| 46 |
-
"eval_samples_per_second": 99.747,
|
| 47 |
-
"eval_steps_per_second": 1.559,
|
| 48 |
-
"step": 2000
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 0.08,
|
| 52 |
-
"learning_rate": 4.214362002889992e-05,
|
| 53 |
-
"loss": 0.0343,
|
| 54 |
-
"step": 2500
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 0.09,
|
| 58 |
-
"learning_rate": 4.057297229377395e-05,
|
| 59 |
-
"loss": 0.0338,
|
| 60 |
-
"step": 3000
|
| 61 |
-
},
|
| 62 |
-
{
|
| 63 |
-
"epoch": 0.09,
|
| 64 |
-
"eval_loss": 0.033833108842372894,
|
| 65 |
-
"eval_runtime": 1134.9992,
|
| 66 |
-
"eval_samples_per_second": 99.722,
|
| 67 |
-
"eval_steps_per_second": 1.559,
|
| 68 |
-
"step": 3000
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 0.11,
|
| 72 |
-
"learning_rate": 3.900232455864799e-05,
|
| 73 |
-
"loss": 0.0343,
|
| 74 |
-
"step": 3500
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.13,
|
| 78 |
-
"learning_rate": 3.743167682352202e-05,
|
| 79 |
-
"loss": 0.0349,
|
| 80 |
-
"step": 4000
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.13,
|
| 84 |
-
"eval_loss": 0.03366178646683693,
|
| 85 |
-
"eval_runtime": 1134.8456,
|
| 86 |
-
"eval_samples_per_second": 99.735,
|
| 87 |
-
"eval_steps_per_second": 1.559,
|
| 88 |
-
"step": 4000
|
| 89 |
-
},
|
| 90 |
-
{
|
| 91 |
-
"epoch": 0.14,
|
| 92 |
-
"learning_rate": 3.586102908839606e-05,
|
| 93 |
-
"loss": 0.0341,
|
| 94 |
-
"step": 4500
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 0.16,
|
| 98 |
-
"learning_rate": 3.429038135327009e-05,
|
| 99 |
-
"loss": 0.034,
|
| 100 |
-
"step": 5000
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.16,
|
| 104 |
-
"eval_loss": 0.033504586666822433,
|
| 105 |
-
"eval_runtime": 1134.9555,
|
| 106 |
-
"eval_samples_per_second": 99.725,
|
| 107 |
-
"eval_steps_per_second": 1.559,
|
| 108 |
-
"step": 5000
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 0.17,
|
| 112 |
-
"learning_rate": 3.271973361814412e-05,
|
| 113 |
-
"loss": 0.0348,
|
| 114 |
-
"step": 5500
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.19,
|
| 118 |
-
"learning_rate": 3.114908588301816e-05,
|
| 119 |
-
"loss": 0.0342,
|
| 120 |
-
"step": 6000
|
| 121 |
-
},
|
| 122 |
-
{
|
| 123 |
-
"epoch": 0.19,
|
| 124 |
-
"eval_loss": 0.03340180218219757,
|
| 125 |
-
"eval_runtime": 1135.0508,
|
| 126 |
-
"eval_samples_per_second": 99.717,
|
| 127 |
-
"eval_steps_per_second": 1.559,
|
| 128 |
-
"step": 6000
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.2,
|
| 132 |
-
"learning_rate": 2.957843814789219e-05,
|
| 133 |
-
"loss": 0.0346,
|
| 134 |
-
"step": 6500
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 0.22,
|
| 138 |
-
"learning_rate": 2.800779041276623e-05,
|
| 139 |
-
"loss": 0.0341,
|
| 140 |
-
"step": 7000
|
| 141 |
-
},
|
| 142 |
-
{
|
| 143 |
-
"epoch": 0.22,
|
| 144 |
-
"eval_loss": 0.03326037526130676,
|
| 145 |
-
"eval_runtime": 1134.9126,
|
| 146 |
-
"eval_samples_per_second": 99.729,
|
| 147 |
-
"eval_steps_per_second": 1.559,
|
| 148 |
-
"step": 7000
|
| 149 |
-
},
|
| 150 |
-
{
|
| 151 |
-
"epoch": 0.24,
|
| 152 |
-
"learning_rate": 2.643714267764026e-05,
|
| 153 |
-
"loss": 0.0337,
|
| 154 |
-
"step": 7500
|
| 155 |
-
},
|
| 156 |
-
{
|
| 157 |
-
"epoch": 0.25,
|
| 158 |
-
"learning_rate": 2.4866494942514292e-05,
|
| 159 |
-
"loss": 0.0339,
|
| 160 |
-
"step": 8000
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"epoch": 0.25,
|
| 164 |
-
"eval_loss": 0.03328871726989746,
|
| 165 |
-
"eval_runtime": 1135.1422,
|
| 166 |
-
"eval_samples_per_second": 99.709,
|
| 167 |
-
"eval_steps_per_second": 1.558,
|
| 168 |
-
"step": 8000
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 0.27,
|
| 172 |
-
"learning_rate": 2.3295847207388326e-05,
|
| 173 |
-
"loss": 0.0335,
|
| 174 |
-
"step": 8500
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 0.28,
|
| 178 |
-
"learning_rate": 2.172519947226236e-05,
|
| 179 |
-
"loss": 0.0336,
|
| 180 |
-
"step": 9000
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"epoch": 0.28,
|
| 184 |
-
"eval_loss": 0.03310398384928703,
|
| 185 |
-
"eval_runtime": 1135.1192,
|
| 186 |
-
"eval_samples_per_second": 99.711,
|
| 187 |
-
"eval_steps_per_second": 1.558,
|
| 188 |
-
"step": 9000
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 0.3,
|
| 192 |
-
"learning_rate": 2.0154551737136397e-05,
|
| 193 |
-
"loss": 0.0334,
|
| 194 |
-
"step": 9500
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 0.31,
|
| 198 |
-
"learning_rate": 1.858390400201043e-05,
|
| 199 |
-
"loss": 0.0335,
|
| 200 |
-
"step": 10000
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 0.31,
|
| 204 |
-
"eval_loss": 0.033003877848386765,
|
| 205 |
-
"eval_runtime": 1135.3796,
|
| 206 |
-
"eval_samples_per_second": 99.688,
|
| 207 |
-
"eval_steps_per_second": 1.558,
|
| 208 |
-
"step": 10000
|
| 209 |
-
},
|
| 210 |
-
{
|
| 211 |
-
"epoch": 0.33,
|
| 212 |
-
"learning_rate": 1.7013256266884464e-05,
|
| 213 |
-
"loss": 0.0332,
|
| 214 |
-
"step": 10500
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 0.35,
|
| 218 |
-
"learning_rate": 1.5442608531758498e-05,
|
| 219 |
-
"loss": 0.0334,
|
| 220 |
-
"step": 11000
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 0.35,
|
| 224 |
-
"eval_loss": 0.03297252207994461,
|
| 225 |
-
"eval_runtime": 1135.6348,
|
| 226 |
-
"eval_samples_per_second": 99.666,
|
| 227 |
-
"eval_steps_per_second": 1.558,
|
| 228 |
-
"step": 11000
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"epoch": 0.36,
|
| 232 |
-
"learning_rate": 1.3871960796632533e-05,
|
| 233 |
-
"loss": 0.0336,
|
| 234 |
-
"step": 11500
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 0.38,
|
| 238 |
-
"learning_rate": 1.2301313061506565e-05,
|
| 239 |
-
"loss": 0.0331,
|
| 240 |
-
"step": 12000
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 0.38,
|
| 244 |
-
"eval_loss": 0.03283138945698738,
|
| 245 |
-
"eval_runtime": 1135.6255,
|
| 246 |
-
"eval_samples_per_second": 99.667,
|
| 247 |
-
"eval_steps_per_second": 1.558,
|
| 248 |
-
"step": 12000
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 0.39,
|
| 252 |
-
"learning_rate": 1.07306653263806e-05,
|
| 253 |
-
"loss": 0.0337,
|
| 254 |
-
"step": 12500
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 0.41,
|
| 258 |
-
"learning_rate": 9.160017591254634e-06,
|
| 259 |
-
"loss": 0.0332,
|
| 260 |
-
"step": 13000
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 0.41,
|
| 264 |
-
"eval_loss": 0.03279568627476692,
|
| 265 |
-
"eval_runtime": 1135.354,
|
| 266 |
-
"eval_samples_per_second": 99.69,
|
| 267 |
-
"eval_steps_per_second": 1.558,
|
| 268 |
-
"step": 13000
|
| 269 |
-
},
|
| 270 |
-
{
|
| 271 |
-
"epoch": 0.42,
|
| 272 |
-
"learning_rate": 7.589369856128668e-06,
|
| 273 |
-
"loss": 0.033,
|
| 274 |
-
"step": 13500
|
| 275 |
-
},
|
| 276 |
-
{
|
| 277 |
-
"epoch": 0.44,
|
| 278 |
-
"learning_rate": 6.018722121002702e-06,
|
| 279 |
-
"loss": 0.0327,
|
| 280 |
-
"step": 14000
|
| 281 |
-
},
|
| 282 |
-
{
|
| 283 |
-
"epoch": 0.44,
|
| 284 |
-
"eval_loss": 0.032747525721788406,
|
| 285 |
-
"eval_runtime": 1135.7244,
|
| 286 |
-
"eval_samples_per_second": 99.658,
|
| 287 |
-
"eval_steps_per_second": 1.558,
|
| 288 |
-
"step": 14000
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 0.46,
|
| 292 |
-
"learning_rate": 4.448074385876736e-06,
|
| 293 |
-
"loss": 0.0337,
|
| 294 |
-
"step": 14500
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 0.47,
|
| 298 |
-
"learning_rate": 2.87742665075077e-06,
|
| 299 |
-
"loss": 0.0331,
|
| 300 |
-
"step": 15000
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"epoch": 0.47,
|
| 304 |
-
"eval_loss": 0.032706450670957565,
|
| 305 |
-
"eval_runtime": 1135.4436,
|
| 306 |
-
"eval_samples_per_second": 99.683,
|
| 307 |
-
"eval_steps_per_second": 1.558,
|
| 308 |
-
"step": 15000
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 0.49,
|
| 312 |
-
"learning_rate": 1.3067789156248037e-06,
|
| 313 |
-
"loss": 0.0333,
|
| 314 |
-
"step": 15500
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 0.5,
|
| 318 |
-
"learning_rate": 0.0,
|
| 319 |
-
"loss": 0.0335,
|
| 320 |
-
"step": 16000
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 0.5,
|
| 324 |
-
"eval_loss": 0.032679423689842224,
|
| 325 |
-
"eval_runtime": 1135.5297,
|
| 326 |
-
"eval_samples_per_second": 99.675,
|
| 327 |
-
"eval_steps_per_second": 1.558,
|
| 328 |
-
"step": 16000
|
| 329 |
-
},
|
| 330 |
-
{
|
| 331 |
-
"epoch": 0.52,
|
| 332 |
-
"learning_rate": 0.0,
|
| 333 |
-
"loss": 0.033,
|
| 334 |
-
"step": 16500
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 0.53,
|
| 338 |
-
"learning_rate": 0.0,
|
| 339 |
-
"loss": 0.0333,
|
| 340 |
-
"step": 17000
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"epoch": 0.53,
|
| 344 |
-
"eval_loss": 0.032679423689842224,
|
| 345 |
-
"eval_runtime": 1135.609,
|
| 346 |
-
"eval_samples_per_second": 99.668,
|
| 347 |
-
"eval_steps_per_second": 1.558,
|
| 348 |
-
"step": 17000
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 0.55,
|
| 352 |
-
"learning_rate": 0.0,
|
| 353 |
-
"loss": 0.0336,
|
| 354 |
-
"step": 17500
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 0.57,
|
| 358 |
-
"learning_rate": 0.0,
|
| 359 |
-
"loss": 0.0333,
|
| 360 |
-
"step": 18000
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 0.57,
|
| 364 |
-
"eval_loss": 0.032679423689842224,
|
| 365 |
-
"eval_runtime": 1135.7019,
|
| 366 |
-
"eval_samples_per_second": 99.66,
|
| 367 |
-
"eval_steps_per_second": 1.558,
|
| 368 |
-
"step": 18000
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 0.58,
|
| 372 |
-
"learning_rate": 0.0,
|
| 373 |
-
"loss": 0.0333,
|
| 374 |
-
"step": 18500
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 0.6,
|
| 378 |
-
"learning_rate": 0.0,
|
| 379 |
-
"loss": 0.0333,
|
| 380 |
-
"step": 19000
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 0.6,
|
| 384 |
-
"eval_loss": 0.032679423689842224,
|
| 385 |
-
"eval_runtime": 1135.7897,
|
| 386 |
-
"eval_samples_per_second": 99.652,
|
| 387 |
-
"eval_steps_per_second": 1.558,
|
| 388 |
-
"step": 19000
|
| 389 |
-
},
|
| 390 |
-
{
|
| 391 |
-
"epoch": 0.61,
|
| 392 |
-
"learning_rate": 0.0,
|
| 393 |
-
"loss": 0.0336,
|
| 394 |
-
"step": 19500
|
| 395 |
-
},
|
| 396 |
-
{
|
| 397 |
-
"epoch": 0.63,
|
| 398 |
-
"learning_rate": 0.0,
|
| 399 |
-
"loss": 0.0332,
|
| 400 |
-
"step": 20000
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"epoch": 0.63,
|
| 404 |
-
"eval_loss": 0.032679423689842224,
|
| 405 |
-
"eval_runtime": 1135.728,
|
| 406 |
-
"eval_samples_per_second": 99.658,
|
| 407 |
-
"eval_steps_per_second": 1.558,
|
| 408 |
-
"step": 20000
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"epoch": 0.64,
|
| 412 |
-
"learning_rate": 0.0,
|
| 413 |
-
"loss": 0.0329,
|
| 414 |
-
"step": 20500
|
| 415 |
-
},
|
| 416 |
-
{
|
| 417 |
-
"epoch": 0.66,
|
| 418 |
-
"learning_rate": 0.0,
|
| 419 |
-
"loss": 0.0331,
|
| 420 |
-
"step": 21000
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"epoch": 0.66,
|
| 424 |
-
"eval_loss": 0.032679423689842224,
|
| 425 |
-
"eval_runtime": 1135.6128,
|
| 426 |
-
"eval_samples_per_second": 99.668,
|
| 427 |
-
"eval_steps_per_second": 1.558,
|
| 428 |
-
"step": 21000
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 0.68,
|
| 432 |
-
"learning_rate": 0.0,
|
| 433 |
-
"loss": 0.0332,
|
| 434 |
-
"step": 21500
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 0.69,
|
| 438 |
-
"learning_rate": 0.0,
|
| 439 |
-
"loss": 0.0328,
|
| 440 |
-
"step": 22000
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 0.69,
|
| 444 |
-
"eval_loss": 0.032679423689842224,
|
| 445 |
-
"eval_runtime": 1135.5304,
|
| 446 |
-
"eval_samples_per_second": 99.675,
|
| 447 |
-
"eval_steps_per_second": 1.558,
|
| 448 |
-
"step": 22000
|
| 449 |
-
},
|
| 450 |
-
{
|
| 451 |
-
"epoch": 0.71,
|
| 452 |
-
"learning_rate": 0.0,
|
| 453 |
-
"loss": 0.0325,
|
| 454 |
-
"step": 22500
|
| 455 |
-
},
|
| 456 |
-
{
|
| 457 |
-
"epoch": 0.72,
|
| 458 |
-
"learning_rate": 0.0,
|
| 459 |
-
"loss": 0.033,
|
| 460 |
-
"step": 23000
|
| 461 |
-
},
|
| 462 |
-
{
|
| 463 |
-
"epoch": 0.72,
|
| 464 |
-
"eval_loss": 0.032679423689842224,
|
| 465 |
-
"eval_runtime": 1135.4821,
|
| 466 |
-
"eval_samples_per_second": 99.679,
|
| 467 |
-
"eval_steps_per_second": 1.558,
|
| 468 |
-
"step": 23000
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"epoch": 0.74,
|
| 472 |
-
"learning_rate": 0.0,
|
| 473 |
-
"loss": 0.0328,
|
| 474 |
-
"step": 23500
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"epoch": 0.75,
|
| 478 |
-
"learning_rate": 0.0,
|
| 479 |
-
"loss": 0.0334,
|
| 480 |
-
"step": 24000
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"epoch": 0.75,
|
| 484 |
-
"eval_loss": 0.032679423689842224,
|
| 485 |
-
"eval_runtime": 1135.3823,
|
| 486 |
-
"eval_samples_per_second": 99.688,
|
| 487 |
-
"eval_steps_per_second": 1.558,
|
| 488 |
-
"step": 24000
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 0.77,
|
| 492 |
-
"learning_rate": 0.0,
|
| 493 |
-
"loss": 0.0334,
|
| 494 |
-
"step": 24500
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 0.79,
|
| 498 |
-
"learning_rate": 0.0,
|
| 499 |
-
"loss": 0.0334,
|
| 500 |
-
"step": 25000
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 0.79,
|
| 504 |
-
"eval_loss": 0.032679423689842224,
|
| 505 |
-
"eval_runtime": 1135.246,
|
| 506 |
-
"eval_samples_per_second": 99.7,
|
| 507 |
-
"eval_steps_per_second": 1.558,
|
| 508 |
-
"step": 25000
|
| 509 |
-
},
|
| 510 |
-
{
|
| 511 |
-
"epoch": 0.8,
|
| 512 |
-
"learning_rate": 0.0,
|
| 513 |
-
"loss": 0.0331,
|
| 514 |
-
"step": 25500
|
| 515 |
-
},
|
| 516 |
-
{
|
| 517 |
-
"epoch": 0.82,
|
| 518 |
-
"learning_rate": 0.0,
|
| 519 |
-
"loss": 0.0333,
|
| 520 |
-
"step": 26000
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"epoch": 0.82,
|
| 524 |
-
"eval_loss": 0.032679423689842224,
|
| 525 |
-
"eval_runtime": 1135.5369,
|
| 526 |
-
"eval_samples_per_second": 99.674,
|
| 527 |
-
"eval_steps_per_second": 1.558,
|
| 528 |
-
"step": 26000
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 0.83,
|
| 532 |
-
"learning_rate": 0.0,
|
| 533 |
-
"loss": 0.0332,
|
| 534 |
-
"step": 26500
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"epoch": 0.85,
|
| 538 |
-
"learning_rate": 0.0,
|
| 539 |
-
"loss": 0.0332,
|
| 540 |
-
"step": 27000
|
| 541 |
-
},
|
| 542 |
-
{
|
| 543 |
-
"epoch": 0.85,
|
| 544 |
-
"eval_loss": 0.032679423689842224,
|
| 545 |
-
"eval_runtime": 1135.3961,
|
| 546 |
-
"eval_samples_per_second": 99.687,
|
| 547 |
-
"eval_steps_per_second": 1.558,
|
| 548 |
-
"step": 27000
|
| 549 |
-
},
|
| 550 |
-
{
|
| 551 |
-
"epoch": 0.86,
|
| 552 |
-
"learning_rate": 0.0,
|
| 553 |
-
"loss": 0.0332,
|
| 554 |
-
"step": 27500
|
| 555 |
-
},
|
| 556 |
-
{
|
| 557 |
-
"epoch": 0.88,
|
| 558 |
-
"learning_rate": 0.0,
|
| 559 |
-
"loss": 0.033,
|
| 560 |
-
"step": 28000
|
| 561 |
-
},
|
| 562 |
-
{
|
| 563 |
-
"epoch": 0.88,
|
| 564 |
-
"eval_loss": 0.032679423689842224,
|
| 565 |
-
"eval_runtime": 1135.3972,
|
| 566 |
-
"eval_samples_per_second": 99.687,
|
| 567 |
-
"eval_steps_per_second": 1.558,
|
| 568 |
-
"step": 28000
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 0.9,
|
| 572 |
-
"learning_rate": 0.0,
|
| 573 |
-
"loss": 0.0326,
|
| 574 |
-
"step": 28500
|
| 575 |
-
},
|
| 576 |
-
{
|
| 577 |
-
"epoch": 0.91,
|
| 578 |
-
"learning_rate": 0.0,
|
| 579 |
-
"loss": 0.033,
|
| 580 |
-
"step": 29000
|
| 581 |
-
},
|
| 582 |
-
{
|
| 583 |
-
"epoch": 0.91,
|
| 584 |
-
"eval_loss": 0.032679423689842224,
|
| 585 |
-
"eval_runtime": 1135.0499,
|
| 586 |
-
"eval_samples_per_second": 99.717,
|
| 587 |
-
"eval_steps_per_second": 1.559,
|
| 588 |
-
"step": 29000
|
| 589 |
-
},
|
| 590 |
-
{
|
| 591 |
-
"epoch": 0.93,
|
| 592 |
-
"learning_rate": 0.0,
|
| 593 |
-
"loss": 0.0334,
|
| 594 |
-
"step": 29500
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 0.94,
|
| 598 |
-
"learning_rate": 0.0,
|
| 599 |
-
"loss": 0.0331,
|
| 600 |
-
"step": 30000
|
| 601 |
-
},
|
| 602 |
-
{
|
| 603 |
-
"epoch": 0.94,
|
| 604 |
-
"eval_loss": 0.032679423689842224,
|
| 605 |
-
"eval_runtime": 1135.1874,
|
| 606 |
-
"eval_samples_per_second": 99.705,
|
| 607 |
-
"eval_steps_per_second": 1.558,
|
| 608 |
-
"step": 30000
|
| 609 |
-
},
|
| 610 |
-
{
|
| 611 |
-
"epoch": 0.96,
|
| 612 |
-
"learning_rate": 0.0,
|
| 613 |
-
"loss": 0.0331,
|
| 614 |
-
"step": 30500
|
| 615 |
-
},
|
| 616 |
-
{
|
| 617 |
-
"epoch": 0.97,
|
| 618 |
-
"learning_rate": 0.0,
|
| 619 |
-
"loss": 0.0335,
|
| 620 |
-
"step": 31000
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 0.97,
|
| 624 |
-
"eval_loss": 0.032679423689842224,
|
| 625 |
-
"eval_runtime": 1134.9563,
|
| 626 |
-
"eval_samples_per_second": 99.725,
|
| 627 |
-
"eval_steps_per_second": 1.559,
|
| 628 |
-
"step": 31000
|
| 629 |
-
}
|
| 630 |
-
],
|
| 631 |
-
"max_steps": 31833,
|
| 632 |
-
"num_train_epochs": 1,
|
| 633 |
-
"total_flos": 2.59218418434048e+17,
|
| 634 |
-
"trial_name": null,
|
| 635 |
-
"trial_params": null
|
| 636 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c3fe204f53109334a6df3947eed7b4984e791cb8af86fdaf81ee04cec6a0a8c8
|
| 3 |
-
size 3515
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|