Delete folder last-checkpoint with huggingface_hub
Browse files- last-checkpoint/config.json +0 -41
- last-checkpoint/generation_config.json +0 -6
- last-checkpoint/model.safetensors +0 -3
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scaler.pt +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +0 -12
- last-checkpoint/trainer_state.json +0 -736
- last-checkpoint/training_args.bin +0 -3
last-checkpoint/config.json
DELETED
|
@@ -1,41 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"activation_function": "gelu_new",
|
| 3 |
-
"add_cross_attention": false,
|
| 4 |
-
"architectures": [
|
| 5 |
-
"GPT2LMHeadModel"
|
| 6 |
-
],
|
| 7 |
-
"attn_pdrop": 0.1,
|
| 8 |
-
"bos_token_id": 0,
|
| 9 |
-
"dtype": "float32",
|
| 10 |
-
"embd_pdrop": 0.1,
|
| 11 |
-
"eos_token_id": 0,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"layer_norm_epsilon": 1e-05,
|
| 14 |
-
"model_type": "gpt2",
|
| 15 |
-
"n_ctx": 1024,
|
| 16 |
-
"n_embd": 768,
|
| 17 |
-
"n_head": 12,
|
| 18 |
-
"n_inner": null,
|
| 19 |
-
"n_layer": 12,
|
| 20 |
-
"n_positions": 1024,
|
| 21 |
-
"pad_token_id": 0,
|
| 22 |
-
"reorder_and_upcast_attn": false,
|
| 23 |
-
"resid_pdrop": 0.1,
|
| 24 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
-
"scale_attn_weights": true,
|
| 26 |
-
"summary_activation": null,
|
| 27 |
-
"summary_first_dropout": 0.1,
|
| 28 |
-
"summary_proj_to_labels": true,
|
| 29 |
-
"summary_type": "cls_index",
|
| 30 |
-
"summary_use_proj": true,
|
| 31 |
-
"task_specific_params": {
|
| 32 |
-
"text-generation": {
|
| 33 |
-
"do_sample": true,
|
| 34 |
-
"max_length": 50
|
| 35 |
-
}
|
| 36 |
-
},
|
| 37 |
-
"tie_word_embeddings": true,
|
| 38 |
-
"transformers_version": "5.0.0",
|
| 39 |
-
"use_cache": false,
|
| 40 |
-
"vocab_size": 32000
|
| 41 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "5.0.0"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:cfd224ac4f13bb08781434397b33248f9893d360b8636d996957410f8289aae2
|
| 3 |
-
size 441688704
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:23ff7b66d3c3b540fcbef896a735182e8d431fff31c994d58ecafc7bdeb449f4
|
| 3 |
-
size 883473803
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9449910befbd8e82c9f7eebd9e032fd8d60e664bc2408c9df91eccb93185118e
|
| 3 |
-
size 14645
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/scaler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b62db0ba9861d9ab63380744e79a287faa461a1bf55700140a411fe1e976f1cd
|
| 3 |
-
size 1383
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6b115c78407cd8a402fe92c02d25a01a03ac04d9159fdfdaf5de4d8b081df935
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
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 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": "<|endoftext|>",
|
| 5 |
-
"eos_token": "<|endoftext|>",
|
| 6 |
-
"errors": "replace",
|
| 7 |
-
"is_local": false,
|
| 8 |
-
"model_max_length": 1024,
|
| 9 |
-
"pad_token": "<|endoftext|>",
|
| 10 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 11 |
-
"unk_token": "<|endoftext|>"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
|
@@ -1,736 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.5,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 4500,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.005555555555555556,
|
| 14 |
-
"grad_norm": 0.35775071382522583,
|
| 15 |
-
"learning_rate": 0.0001989111111111111,
|
| 16 |
-
"loss": 3.360899658203125,
|
| 17 |
-
"step": 50
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.011111111111111112,
|
| 21 |
-
"grad_norm": 0.3325912356376648,
|
| 22 |
-
"learning_rate": 0.0001978,
|
| 23 |
-
"loss": 3.377425537109375,
|
| 24 |
-
"step": 100
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.016666666666666666,
|
| 28 |
-
"grad_norm": 0.35807931423187256,
|
| 29 |
-
"learning_rate": 0.0001966888888888889,
|
| 30 |
-
"loss": 3.375316467285156,
|
| 31 |
-
"step": 150
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.022222222222222223,
|
| 35 |
-
"grad_norm": 0.3500971794128418,
|
| 36 |
-
"learning_rate": 0.00019557777777777779,
|
| 37 |
-
"loss": 3.3736077880859376,
|
| 38 |
-
"step": 200
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.027777777777777776,
|
| 42 |
-
"grad_norm": 0.3371691107749939,
|
| 43 |
-
"learning_rate": 0.00019446666666666669,
|
| 44 |
-
"loss": 3.371192626953125,
|
| 45 |
-
"step": 250
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.03333333333333333,
|
| 49 |
-
"grad_norm": 0.3565760552883148,
|
| 50 |
-
"learning_rate": 0.00019335555555555556,
|
| 51 |
-
"loss": 3.3762380981445315,
|
| 52 |
-
"step": 300
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.03888888888888889,
|
| 56 |
-
"grad_norm": 0.338236540555954,
|
| 57 |
-
"learning_rate": 0.00019224444444444446,
|
| 58 |
-
"loss": 3.2787982177734376,
|
| 59 |
-
"step": 350
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 0.044444444444444446,
|
| 63 |
-
"grad_norm": 0.3267105221748352,
|
| 64 |
-
"learning_rate": 0.00019113333333333334,
|
| 65 |
-
"loss": 3.1427099609375,
|
| 66 |
-
"step": 400
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 0.05,
|
| 70 |
-
"grad_norm": 0.351743221282959,
|
| 71 |
-
"learning_rate": 0.00019002222222222224,
|
| 72 |
-
"loss": 3.177709655761719,
|
| 73 |
-
"step": 450
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 0.05555555555555555,
|
| 77 |
-
"grad_norm": 0.3772064745426178,
|
| 78 |
-
"learning_rate": 0.00018891111111111114,
|
| 79 |
-
"loss": 3.3302297973632813,
|
| 80 |
-
"step": 500
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.05555555555555555,
|
| 84 |
-
"eval_loss": 3.2087979316711426,
|
| 85 |
-
"eval_runtime": 166.477,
|
| 86 |
-
"eval_samples_per_second": 52.187,
|
| 87 |
-
"eval_steps_per_second": 1.634,
|
| 88 |
-
"step": 500
|
| 89 |
-
},
|
| 90 |
-
{
|
| 91 |
-
"epoch": 0.06111111111111111,
|
| 92 |
-
"grad_norm": 0.3273681402206421,
|
| 93 |
-
"learning_rate": 0.0001878,
|
| 94 |
-
"loss": 3.3618435668945312,
|
| 95 |
-
"step": 550
|
| 96 |
-
},
|
| 97 |
-
{
|
| 98 |
-
"epoch": 0.06666666666666667,
|
| 99 |
-
"grad_norm": 0.32075268030166626,
|
| 100 |
-
"learning_rate": 0.00018668888888888889,
|
| 101 |
-
"loss": 3.3656939697265624,
|
| 102 |
-
"step": 600
|
| 103 |
-
},
|
| 104 |
-
{
|
| 105 |
-
"epoch": 0.07222222222222222,
|
| 106 |
-
"grad_norm": 0.3335159122943878,
|
| 107 |
-
"learning_rate": 0.00018557777777777779,
|
| 108 |
-
"loss": 3.3647976684570313,
|
| 109 |
-
"step": 650
|
| 110 |
-
},
|
| 111 |
-
{
|
| 112 |
-
"epoch": 0.07777777777777778,
|
| 113 |
-
"grad_norm": 0.3546631336212158,
|
| 114 |
-
"learning_rate": 0.0001844666666666667,
|
| 115 |
-
"loss": 3.3779290771484374,
|
| 116 |
-
"step": 700
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 0.08333333333333333,
|
| 120 |
-
"grad_norm": 0.3615032732486725,
|
| 121 |
-
"learning_rate": 0.00018335555555555556,
|
| 122 |
-
"loss": 3.373221435546875,
|
| 123 |
-
"step": 750
|
| 124 |
-
},
|
| 125 |
-
{
|
| 126 |
-
"epoch": 0.08888888888888889,
|
| 127 |
-
"grad_norm": 0.3439997434616089,
|
| 128 |
-
"learning_rate": 0.00018224444444444446,
|
| 129 |
-
"loss": 3.3516156005859377,
|
| 130 |
-
"step": 800
|
| 131 |
-
},
|
| 132 |
-
{
|
| 133 |
-
"epoch": 0.09444444444444444,
|
| 134 |
-
"grad_norm": 0.3357887268066406,
|
| 135 |
-
"learning_rate": 0.00018113333333333334,
|
| 136 |
-
"loss": 3.3828070068359377,
|
| 137 |
-
"step": 850
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 0.1,
|
| 141 |
-
"grad_norm": 0.3612283170223236,
|
| 142 |
-
"learning_rate": 0.00018002222222222224,
|
| 143 |
-
"loss": 3.3401724243164064,
|
| 144 |
-
"step": 900
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"epoch": 0.10555555555555556,
|
| 148 |
-
"grad_norm": 0.32794448733329773,
|
| 149 |
-
"learning_rate": 0.0001789111111111111,
|
| 150 |
-
"loss": 3.261454772949219,
|
| 151 |
-
"step": 950
|
| 152 |
-
},
|
| 153 |
-
{
|
| 154 |
-
"epoch": 0.1111111111111111,
|
| 155 |
-
"grad_norm": 0.3254797160625458,
|
| 156 |
-
"learning_rate": 0.0001778,
|
| 157 |
-
"loss": 3.1203973388671873,
|
| 158 |
-
"step": 1000
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 0.1111111111111111,
|
| 162 |
-
"eval_loss": 3.1987435817718506,
|
| 163 |
-
"eval_runtime": 165.973,
|
| 164 |
-
"eval_samples_per_second": 52.346,
|
| 165 |
-
"eval_steps_per_second": 1.639,
|
| 166 |
-
"step": 1000
|
| 167 |
-
},
|
| 168 |
-
{
|
| 169 |
-
"epoch": 0.11666666666666667,
|
| 170 |
-
"grad_norm": 0.3622206151485443,
|
| 171 |
-
"learning_rate": 0.0001766888888888889,
|
| 172 |
-
"loss": 3.161617431640625,
|
| 173 |
-
"step": 1050
|
| 174 |
-
},
|
| 175 |
-
{
|
| 176 |
-
"epoch": 0.12222222222222222,
|
| 177 |
-
"grad_norm": 0.381729394197464,
|
| 178 |
-
"learning_rate": 0.0001755777777777778,
|
| 179 |
-
"loss": 3.3174508666992186,
|
| 180 |
-
"step": 1100
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"epoch": 0.12777777777777777,
|
| 184 |
-
"grad_norm": 0.3418969213962555,
|
| 185 |
-
"learning_rate": 0.00017446666666666666,
|
| 186 |
-
"loss": 3.3552154541015624,
|
| 187 |
-
"step": 1150
|
| 188 |
-
},
|
| 189 |
-
{
|
| 190 |
-
"epoch": 0.13333333333333333,
|
| 191 |
-
"grad_norm": 0.32382291555404663,
|
| 192 |
-
"learning_rate": 0.00017335555555555556,
|
| 193 |
-
"loss": 3.3517587280273435,
|
| 194 |
-
"step": 1200
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 0.1388888888888889,
|
| 198 |
-
"grad_norm": 0.33188289403915405,
|
| 199 |
-
"learning_rate": 0.00017224444444444446,
|
| 200 |
-
"loss": 3.3422265625,
|
| 201 |
-
"step": 1250
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 0.14444444444444443,
|
| 205 |
-
"grad_norm": 0.3254759907722473,
|
| 206 |
-
"learning_rate": 0.00017113333333333334,
|
| 207 |
-
"loss": 3.3487127685546874,
|
| 208 |
-
"step": 1300
|
| 209 |
-
},
|
| 210 |
-
{
|
| 211 |
-
"epoch": 0.15,
|
| 212 |
-
"grad_norm": 0.34883055090904236,
|
| 213 |
-
"learning_rate": 0.00017002222222222224,
|
| 214 |
-
"loss": 3.3675653076171876,
|
| 215 |
-
"step": 1350
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 0.15555555555555556,
|
| 219 |
-
"grad_norm": 0.32952237129211426,
|
| 220 |
-
"learning_rate": 0.0001689111111111111,
|
| 221 |
-
"loss": 3.353576354980469,
|
| 222 |
-
"step": 1400
|
| 223 |
-
},
|
| 224 |
-
{
|
| 225 |
-
"epoch": 0.16111111111111112,
|
| 226 |
-
"grad_norm": 0.3523924648761749,
|
| 227 |
-
"learning_rate": 0.0001678,
|
| 228 |
-
"loss": 3.3583038330078123,
|
| 229 |
-
"step": 1450
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"epoch": 0.16666666666666666,
|
| 233 |
-
"grad_norm": 0.33520838618278503,
|
| 234 |
-
"learning_rate": 0.0001666888888888889,
|
| 235 |
-
"loss": 3.337117919921875,
|
| 236 |
-
"step": 1500
|
| 237 |
-
},
|
| 238 |
-
{
|
| 239 |
-
"epoch": 0.16666666666666666,
|
| 240 |
-
"eval_loss": 3.183213710784912,
|
| 241 |
-
"eval_runtime": 166.0918,
|
| 242 |
-
"eval_samples_per_second": 52.308,
|
| 243 |
-
"eval_steps_per_second": 1.638,
|
| 244 |
-
"step": 1500
|
| 245 |
-
},
|
| 246 |
-
{
|
| 247 |
-
"epoch": 0.17222222222222222,
|
| 248 |
-
"grad_norm": 0.33549970388412476,
|
| 249 |
-
"learning_rate": 0.0001655777777777778,
|
| 250 |
-
"loss": 3.272804870605469,
|
| 251 |
-
"step": 1550
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 0.17777777777777778,
|
| 255 |
-
"grad_norm": 0.3457739055156708,
|
| 256 |
-
"learning_rate": 0.0001644666666666667,
|
| 257 |
-
"loss": 3.1095587158203126,
|
| 258 |
-
"step": 1600
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"epoch": 0.18333333333333332,
|
| 262 |
-
"grad_norm": 0.3696184754371643,
|
| 263 |
-
"learning_rate": 0.00016335555555555556,
|
| 264 |
-
"loss": 3.150552978515625,
|
| 265 |
-
"step": 1650
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"epoch": 0.18888888888888888,
|
| 269 |
-
"grad_norm": 0.33659297227859497,
|
| 270 |
-
"learning_rate": 0.00016224444444444444,
|
| 271 |
-
"loss": 3.3054623413085937,
|
| 272 |
-
"step": 1700
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"epoch": 0.19444444444444445,
|
| 276 |
-
"grad_norm": 0.33346593379974365,
|
| 277 |
-
"learning_rate": 0.00016113333333333334,
|
| 278 |
-
"loss": 3.3228750610351563,
|
| 279 |
-
"step": 1750
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 0.2,
|
| 283 |
-
"grad_norm": 0.3283025622367859,
|
| 284 |
-
"learning_rate": 0.00016002222222222224,
|
| 285 |
-
"loss": 3.3500897216796877,
|
| 286 |
-
"step": 1800
|
| 287 |
-
},
|
| 288 |
-
{
|
| 289 |
-
"epoch": 0.20555555555555555,
|
| 290 |
-
"grad_norm": 0.33104243874549866,
|
| 291 |
-
"learning_rate": 0.0001589111111111111,
|
| 292 |
-
"loss": 3.3303262329101564,
|
| 293 |
-
"step": 1850
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"epoch": 0.2111111111111111,
|
| 297 |
-
"grad_norm": 0.341381311416626,
|
| 298 |
-
"learning_rate": 0.00015780000000000001,
|
| 299 |
-
"loss": 3.334217224121094,
|
| 300 |
-
"step": 1900
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"epoch": 0.21666666666666667,
|
| 304 |
-
"grad_norm": 0.35246169567108154,
|
| 305 |
-
"learning_rate": 0.00015668888888888891,
|
| 306 |
-
"loss": 3.3466201782226563,
|
| 307 |
-
"step": 1950
|
| 308 |
-
},
|
| 309 |
-
{
|
| 310 |
-
"epoch": 0.2222222222222222,
|
| 311 |
-
"grad_norm": 0.35079947113990784,
|
| 312 |
-
"learning_rate": 0.0001555777777777778,
|
| 313 |
-
"loss": 3.3411221313476562,
|
| 314 |
-
"step": 2000
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 0.2222222222222222,
|
| 318 |
-
"eval_loss": 3.173346757888794,
|
| 319 |
-
"eval_runtime": 166.0597,
|
| 320 |
-
"eval_samples_per_second": 52.319,
|
| 321 |
-
"eval_steps_per_second": 1.638,
|
| 322 |
-
"step": 2000
|
| 323 |
-
},
|
| 324 |
-
{
|
| 325 |
-
"epoch": 0.22777777777777777,
|
| 326 |
-
"grad_norm": 0.3230424225330353,
|
| 327 |
-
"learning_rate": 0.00015446666666666666,
|
| 328 |
-
"loss": 3.32146484375,
|
| 329 |
-
"step": 2050
|
| 330 |
-
},
|
| 331 |
-
{
|
| 332 |
-
"epoch": 0.23333333333333334,
|
| 333 |
-
"grad_norm": 0.31917229294776917,
|
| 334 |
-
"learning_rate": 0.00015335555555555556,
|
| 335 |
-
"loss": 3.3351910400390623,
|
| 336 |
-
"step": 2100
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"epoch": 0.2388888888888889,
|
| 340 |
-
"grad_norm": 0.3427633047103882,
|
| 341 |
-
"learning_rate": 0.00015224444444444446,
|
| 342 |
-
"loss": 3.281336364746094,
|
| 343 |
-
"step": 2150
|
| 344 |
-
},
|
| 345 |
-
{
|
| 346 |
-
"epoch": 0.24444444444444444,
|
| 347 |
-
"grad_norm": 0.3299531042575836,
|
| 348 |
-
"learning_rate": 0.00015113333333333334,
|
| 349 |
-
"loss": 3.096239013671875,
|
| 350 |
-
"step": 2200
|
| 351 |
-
},
|
| 352 |
-
{
|
| 353 |
-
"epoch": 0.25,
|
| 354 |
-
"grad_norm": 0.35307979583740234,
|
| 355 |
-
"learning_rate": 0.0001500222222222222,
|
| 356 |
-
"loss": 3.131253967285156,
|
| 357 |
-
"step": 2250
|
| 358 |
-
},
|
| 359 |
-
{
|
| 360 |
-
"epoch": 0.25555555555555554,
|
| 361 |
-
"grad_norm": 0.336974561214447,
|
| 362 |
-
"learning_rate": 0.00014891111111111111,
|
| 363 |
-
"loss": 3.286785888671875,
|
| 364 |
-
"step": 2300
|
| 365 |
-
},
|
| 366 |
-
{
|
| 367 |
-
"epoch": 0.2611111111111111,
|
| 368 |
-
"grad_norm": 0.35140281915664673,
|
| 369 |
-
"learning_rate": 0.00014780000000000001,
|
| 370 |
-
"loss": 3.3154971313476564,
|
| 371 |
-
"step": 2350
|
| 372 |
-
},
|
| 373 |
-
{
|
| 374 |
-
"epoch": 0.26666666666666666,
|
| 375 |
-
"grad_norm": 0.33435744047164917,
|
| 376 |
-
"learning_rate": 0.0001466888888888889,
|
| 377 |
-
"loss": 3.3314889526367186,
|
| 378 |
-
"step": 2400
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 0.2722222222222222,
|
| 382 |
-
"grad_norm": 0.32398200035095215,
|
| 383 |
-
"learning_rate": 0.0001455777777777778,
|
| 384 |
-
"loss": 3.3115130615234376,
|
| 385 |
-
"step": 2450
|
| 386 |
-
},
|
| 387 |
-
{
|
| 388 |
-
"epoch": 0.2777777777777778,
|
| 389 |
-
"grad_norm": 0.3433283269405365,
|
| 390 |
-
"learning_rate": 0.0001444666666666667,
|
| 391 |
-
"loss": 3.3148236083984375,
|
| 392 |
-
"step": 2500
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 0.2777777777777778,
|
| 396 |
-
"eval_loss": 3.1662325859069824,
|
| 397 |
-
"eval_runtime": 165.919,
|
| 398 |
-
"eval_samples_per_second": 52.363,
|
| 399 |
-
"eval_steps_per_second": 1.639,
|
| 400 |
-
"step": 2500
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"epoch": 0.2833333333333333,
|
| 404 |
-
"grad_norm": 0.34796038269996643,
|
| 405 |
-
"learning_rate": 0.00014335555555555556,
|
| 406 |
-
"loss": 3.319035949707031,
|
| 407 |
-
"step": 2550
|
| 408 |
-
},
|
| 409 |
-
{
|
| 410 |
-
"epoch": 0.28888888888888886,
|
| 411 |
-
"grad_norm": 0.3492030203342438,
|
| 412 |
-
"learning_rate": 0.00014224444444444444,
|
| 413 |
-
"loss": 3.3430206298828127,
|
| 414 |
-
"step": 2600
|
| 415 |
-
},
|
| 416 |
-
{
|
| 417 |
-
"epoch": 0.29444444444444445,
|
| 418 |
-
"grad_norm": 0.3453795909881592,
|
| 419 |
-
"learning_rate": 0.00014113333333333334,
|
| 420 |
-
"loss": 3.3211288452148438,
|
| 421 |
-
"step": 2650
|
| 422 |
-
},
|
| 423 |
-
{
|
| 424 |
-
"epoch": 0.3,
|
| 425 |
-
"grad_norm": 0.3202071785926819,
|
| 426 |
-
"learning_rate": 0.00014002222222222224,
|
| 427 |
-
"loss": 3.31465087890625,
|
| 428 |
-
"step": 2700
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 0.3055555555555556,
|
| 432 |
-
"grad_norm": 0.3388383984565735,
|
| 433 |
-
"learning_rate": 0.00013891111111111111,
|
| 434 |
-
"loss": 3.3147201538085938,
|
| 435 |
-
"step": 2750
|
| 436 |
-
},
|
| 437 |
-
{
|
| 438 |
-
"epoch": 0.3111111111111111,
|
| 439 |
-
"grad_norm": 0.3404223322868347,
|
| 440 |
-
"learning_rate": 0.0001378,
|
| 441 |
-
"loss": 3.306570739746094,
|
| 442 |
-
"step": 2800
|
| 443 |
-
},
|
| 444 |
-
{
|
| 445 |
-
"epoch": 0.31666666666666665,
|
| 446 |
-
"grad_norm": 0.3333878517150879,
|
| 447 |
-
"learning_rate": 0.0001366888888888889,
|
| 448 |
-
"loss": 3.3179815673828124,
|
| 449 |
-
"step": 2850
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"epoch": 0.32222222222222224,
|
| 453 |
-
"grad_norm": 0.34150388836860657,
|
| 454 |
-
"learning_rate": 0.0001355777777777778,
|
| 455 |
-
"loss": 3.321144714355469,
|
| 456 |
-
"step": 2900
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"epoch": 0.3277777777777778,
|
| 460 |
-
"grad_norm": 0.3324436545372009,
|
| 461 |
-
"learning_rate": 0.00013446666666666666,
|
| 462 |
-
"loss": 3.3187985229492187,
|
| 463 |
-
"step": 2950
|
| 464 |
-
},
|
| 465 |
-
{
|
| 466 |
-
"epoch": 0.3333333333333333,
|
| 467 |
-
"grad_norm": 0.3744795024394989,
|
| 468 |
-
"learning_rate": 0.00013335555555555557,
|
| 469 |
-
"loss": 3.3278173828125,
|
| 470 |
-
"step": 3000
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 0.3333333333333333,
|
| 474 |
-
"eval_loss": 3.1569581031799316,
|
| 475 |
-
"eval_runtime": 166.2587,
|
| 476 |
-
"eval_samples_per_second": 52.256,
|
| 477 |
-
"eval_steps_per_second": 1.636,
|
| 478 |
-
"step": 3000
|
| 479 |
-
},
|
| 480 |
-
{
|
| 481 |
-
"epoch": 0.3388888888888889,
|
| 482 |
-
"grad_norm": 0.3463502526283264,
|
| 483 |
-
"learning_rate": 0.00013224444444444447,
|
| 484 |
-
"loss": 3.174356689453125,
|
| 485 |
-
"step": 3050
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 0.34444444444444444,
|
| 489 |
-
"grad_norm": 0.31703874468803406,
|
| 490 |
-
"learning_rate": 0.00013113333333333334,
|
| 491 |
-
"loss": 3.082904052734375,
|
| 492 |
-
"step": 3100
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"epoch": 0.35,
|
| 496 |
-
"grad_norm": 0.35603103041648865,
|
| 497 |
-
"learning_rate": 0.00013002222222222221,
|
| 498 |
-
"loss": 3.2023150634765627,
|
| 499 |
-
"step": 3150
|
| 500 |
-
},
|
| 501 |
-
{
|
| 502 |
-
"epoch": 0.35555555555555557,
|
| 503 |
-
"grad_norm": 0.33750680088996887,
|
| 504 |
-
"learning_rate": 0.00012891111111111112,
|
| 505 |
-
"loss": 3.2860113525390626,
|
| 506 |
-
"step": 3200
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 0.3611111111111111,
|
| 510 |
-
"grad_norm": 0.33665114641189575,
|
| 511 |
-
"learning_rate": 0.00012780000000000002,
|
| 512 |
-
"loss": 3.2967050170898435,
|
| 513 |
-
"step": 3250
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 0.36666666666666664,
|
| 517 |
-
"grad_norm": 0.3330186605453491,
|
| 518 |
-
"learning_rate": 0.0001266888888888889,
|
| 519 |
-
"loss": 3.337146911621094,
|
| 520 |
-
"step": 3300
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"epoch": 0.37222222222222223,
|
| 524 |
-
"grad_norm": 0.3167618215084076,
|
| 525 |
-
"learning_rate": 0.0001255777777777778,
|
| 526 |
-
"loss": 3.247300109863281,
|
| 527 |
-
"step": 3350
|
| 528 |
-
},
|
| 529 |
-
{
|
| 530 |
-
"epoch": 0.37777777777777777,
|
| 531 |
-
"grad_norm": 0.33100470900535583,
|
| 532 |
-
"learning_rate": 0.00012446666666666667,
|
| 533 |
-
"loss": 3.0897637939453126,
|
| 534 |
-
"step": 3400
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"epoch": 0.38333333333333336,
|
| 538 |
-
"grad_norm": 0.33727842569351196,
|
| 539 |
-
"learning_rate": 0.00012335555555555557,
|
| 540 |
-
"loss": 3.1006646728515626,
|
| 541 |
-
"step": 3450
|
| 542 |
-
},
|
| 543 |
-
{
|
| 544 |
-
"epoch": 0.3888888888888889,
|
| 545 |
-
"grad_norm": 0.339106023311615,
|
| 546 |
-
"learning_rate": 0.00012224444444444444,
|
| 547 |
-
"loss": 3.2851516723632814,
|
| 548 |
-
"step": 3500
|
| 549 |
-
},
|
| 550 |
-
{
|
| 551 |
-
"epoch": 0.3888888888888889,
|
| 552 |
-
"eval_loss": 3.154163360595703,
|
| 553 |
-
"eval_runtime": 167.1636,
|
| 554 |
-
"eval_samples_per_second": 51.973,
|
| 555 |
-
"eval_steps_per_second": 1.627,
|
| 556 |
-
"step": 3500
|
| 557 |
-
},
|
| 558 |
-
{
|
| 559 |
-
"epoch": 0.39444444444444443,
|
| 560 |
-
"grad_norm": 0.3349100649356842,
|
| 561 |
-
"learning_rate": 0.00012113333333333334,
|
| 562 |
-
"loss": 3.2821334838867187,
|
| 563 |
-
"step": 3550
|
| 564 |
-
},
|
| 565 |
-
{
|
| 566 |
-
"epoch": 0.4,
|
| 567 |
-
"grad_norm": 0.3199748396873474,
|
| 568 |
-
"learning_rate": 0.00012002222222222224,
|
| 569 |
-
"loss": 3.3088592529296874,
|
| 570 |
-
"step": 3600
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"epoch": 0.40555555555555556,
|
| 574 |
-
"grad_norm": 0.33304205536842346,
|
| 575 |
-
"learning_rate": 0.0001189111111111111,
|
| 576 |
-
"loss": 3.312510986328125,
|
| 577 |
-
"step": 3650
|
| 578 |
-
},
|
| 579 |
-
{
|
| 580 |
-
"epoch": 0.4111111111111111,
|
| 581 |
-
"grad_norm": 0.3239525854587555,
|
| 582 |
-
"learning_rate": 0.0001178,
|
| 583 |
-
"loss": 3.3061819458007813,
|
| 584 |
-
"step": 3700
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 0.4166666666666667,
|
| 588 |
-
"grad_norm": 0.33456292748451233,
|
| 589 |
-
"learning_rate": 0.00011668888888888889,
|
| 590 |
-
"loss": 3.3097720336914063,
|
| 591 |
-
"step": 3750
|
| 592 |
-
},
|
| 593 |
-
{
|
| 594 |
-
"epoch": 0.4222222222222222,
|
| 595 |
-
"grad_norm": 0.366735577583313,
|
| 596 |
-
"learning_rate": 0.00011557777777777778,
|
| 597 |
-
"loss": 3.304618225097656,
|
| 598 |
-
"step": 3800
|
| 599 |
-
},
|
| 600 |
-
{
|
| 601 |
-
"epoch": 0.42777777777777776,
|
| 602 |
-
"grad_norm": 0.3458787202835083,
|
| 603 |
-
"learning_rate": 0.00011446666666666668,
|
| 604 |
-
"loss": 3.305858154296875,
|
| 605 |
-
"step": 3850
|
| 606 |
-
},
|
| 607 |
-
{
|
| 608 |
-
"epoch": 0.43333333333333335,
|
| 609 |
-
"grad_norm": 0.3511033058166504,
|
| 610 |
-
"learning_rate": 0.00011335555555555557,
|
| 611 |
-
"loss": 3.3072021484375,
|
| 612 |
-
"step": 3900
|
| 613 |
-
},
|
| 614 |
-
{
|
| 615 |
-
"epoch": 0.4388888888888889,
|
| 616 |
-
"grad_norm": 0.32906875014305115,
|
| 617 |
-
"learning_rate": 0.00011224444444444444,
|
| 618 |
-
"loss": 3.261636047363281,
|
| 619 |
-
"step": 3950
|
| 620 |
-
},
|
| 621 |
-
{
|
| 622 |
-
"epoch": 0.4444444444444444,
|
| 623 |
-
"grad_norm": 0.3258017301559448,
|
| 624 |
-
"learning_rate": 0.00011113333333333333,
|
| 625 |
-
"loss": 3.077975158691406,
|
| 626 |
-
"step": 4000
|
| 627 |
-
},
|
| 628 |
-
{
|
| 629 |
-
"epoch": 0.4444444444444444,
|
| 630 |
-
"eval_loss": 3.1473567485809326,
|
| 631 |
-
"eval_runtime": 166.5794,
|
| 632 |
-
"eval_samples_per_second": 52.155,
|
| 633 |
-
"eval_steps_per_second": 1.633,
|
| 634 |
-
"step": 4000
|
| 635 |
-
},
|
| 636 |
-
{
|
| 637 |
-
"epoch": 0.45,
|
| 638 |
-
"grad_norm": 0.3296092450618744,
|
| 639 |
-
"learning_rate": 0.00011002222222222223,
|
| 640 |
-
"loss": 3.096522216796875,
|
| 641 |
-
"step": 4050
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 0.45555555555555555,
|
| 645 |
-
"grad_norm": 0.36984893679618835,
|
| 646 |
-
"learning_rate": 0.00010891111111111112,
|
| 647 |
-
"loss": 3.272289123535156,
|
| 648 |
-
"step": 4100
|
| 649 |
-
},
|
| 650 |
-
{
|
| 651 |
-
"epoch": 0.46111111111111114,
|
| 652 |
-
"grad_norm": 0.3618357479572296,
|
| 653 |
-
"learning_rate": 0.00010780000000000002,
|
| 654 |
-
"loss": 3.2838409423828123,
|
| 655 |
-
"step": 4150
|
| 656 |
-
},
|
| 657 |
-
{
|
| 658 |
-
"epoch": 0.4666666666666667,
|
| 659 |
-
"grad_norm": 0.34125998616218567,
|
| 660 |
-
"learning_rate": 0.0001066888888888889,
|
| 661 |
-
"loss": 3.3192120361328126,
|
| 662 |
-
"step": 4200
|
| 663 |
-
},
|
| 664 |
-
{
|
| 665 |
-
"epoch": 0.4722222222222222,
|
| 666 |
-
"grad_norm": 0.3505809009075165,
|
| 667 |
-
"learning_rate": 0.00010557777777777778,
|
| 668 |
-
"loss": 3.3169589233398438,
|
| 669 |
-
"step": 4250
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 0.4777777777777778,
|
| 673 |
-
"grad_norm": 0.3265681564807892,
|
| 674 |
-
"learning_rate": 0.00010446666666666667,
|
| 675 |
-
"loss": 3.29230224609375,
|
| 676 |
-
"step": 4300
|
| 677 |
-
},
|
| 678 |
-
{
|
| 679 |
-
"epoch": 0.48333333333333334,
|
| 680 |
-
"grad_norm": 0.3397888243198395,
|
| 681 |
-
"learning_rate": 0.00010335555555555555,
|
| 682 |
-
"loss": 3.28514404296875,
|
| 683 |
-
"step": 4350
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 0.4888888888888889,
|
| 687 |
-
"grad_norm": 0.35736849904060364,
|
| 688 |
-
"learning_rate": 0.00010224444444444446,
|
| 689 |
-
"loss": 3.308734130859375,
|
| 690 |
-
"step": 4400
|
| 691 |
-
},
|
| 692 |
-
{
|
| 693 |
-
"epoch": 0.49444444444444446,
|
| 694 |
-
"grad_norm": 0.35276156663894653,
|
| 695 |
-
"learning_rate": 0.00010113333333333334,
|
| 696 |
-
"loss": 3.2899267578125,
|
| 697 |
-
"step": 4450
|
| 698 |
-
},
|
| 699 |
-
{
|
| 700 |
-
"epoch": 0.5,
|
| 701 |
-
"grad_norm": 0.3468235433101654,
|
| 702 |
-
"learning_rate": 0.00010002222222222222,
|
| 703 |
-
"loss": 3.3065914916992187,
|
| 704 |
-
"step": 4500
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 0.5,
|
| 708 |
-
"eval_loss": 3.1372437477111816,
|
| 709 |
-
"eval_runtime": 165.9576,
|
| 710 |
-
"eval_samples_per_second": 52.351,
|
| 711 |
-
"eval_steps_per_second": 1.639,
|
| 712 |
-
"step": 4500
|
| 713 |
-
}
|
| 714 |
-
],
|
| 715 |
-
"logging_steps": 50,
|
| 716 |
-
"max_steps": 9000,
|
| 717 |
-
"num_input_tokens_seen": 0,
|
| 718 |
-
"num_train_epochs": 9223372036854775807,
|
| 719 |
-
"save_steps": 500,
|
| 720 |
-
"stateful_callbacks": {
|
| 721 |
-
"TrainerControl": {
|
| 722 |
-
"args": {
|
| 723 |
-
"should_epoch_stop": false,
|
| 724 |
-
"should_evaluate": false,
|
| 725 |
-
"should_log": false,
|
| 726 |
-
"should_save": true,
|
| 727 |
-
"should_training_stop": false
|
| 728 |
-
},
|
| 729 |
-
"attributes": {}
|
| 730 |
-
}
|
| 731 |
-
},
|
| 732 |
-
"total_flos": 7.5252105216e+16,
|
| 733 |
-
"train_batch_size": 32,
|
| 734 |
-
"trial_name": null,
|
| 735 |
-
"trial_params": null
|
| 736 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:dd37d0c02b2ccb9edd98dd633c884ff4bb66f6f9b90d58062d0802f2813269e2
|
| 3 |
-
size 5265
|
|
|
|
|
|
|
|
|
|
|
|