Retrained by Merry
Browse files- all_results.json +8 -0
- eval_results.json +10 -0
- pytorch_model.bin +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- train_results.json +8 -0
- trainer_state.json +289 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 2.470616279322582,
|
| 4 |
+
"train_runtime": 9527.188,
|
| 5 |
+
"train_samples": 7471,
|
| 6 |
+
"train_samples_per_second": 2.353,
|
| 7 |
+
"train_steps_per_second": 2.353
|
| 8 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.5256540343090056,
|
| 4 |
+
"eval_loss": 2.18223237991333,
|
| 5 |
+
"eval_runtime": 905.1248,
|
| 6 |
+
"eval_samples": 7471,
|
| 7 |
+
"eval_samples_per_second": 8.254,
|
| 8 |
+
"eval_steps_per_second": 8.254,
|
| 9 |
+
"perplexity": 8.86607663440429
|
| 10 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7d5c78ae4019df9388605203e941f0ebb6d5a62dd27ea4f9472b12c0d3e567e
|
| 3 |
+
size 551185105
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-125M"}
|
|
|
|
| 1 |
+
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-125M", "tokenizer_class": "GPT2Tokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 2.470616279322582,
|
| 4 |
+
"train_runtime": 9527.188,
|
| 5 |
+
"train_samples": 7471,
|
| 6 |
+
"train_samples_per_second": 2.353,
|
| 7 |
+
"train_steps_per_second": 2.353
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,289 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 22413,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 4.8884575915763174e-05,
|
| 13 |
+
"loss": 2.9446,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.13,
|
| 18 |
+
"learning_rate": 4.776915183152635e-05,
|
| 19 |
+
"loss": 2.844,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.2,
|
| 24 |
+
"learning_rate": 4.665372774728952e-05,
|
| 25 |
+
"loss": 2.8468,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.27,
|
| 30 |
+
"learning_rate": 4.5538303663052694e-05,
|
| 31 |
+
"loss": 2.7941,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.33,
|
| 36 |
+
"learning_rate": 4.4422879578815865e-05,
|
| 37 |
+
"loss": 2.7849,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.4,
|
| 42 |
+
"learning_rate": 4.330745549457904e-05,
|
| 43 |
+
"loss": 2.7557,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.47,
|
| 48 |
+
"learning_rate": 4.2192031410342214e-05,
|
| 49 |
+
"loss": 2.7485,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.54,
|
| 54 |
+
"learning_rate": 4.1076607326105386e-05,
|
| 55 |
+
"loss": 2.7153,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.6,
|
| 60 |
+
"learning_rate": 3.9961183241868564e-05,
|
| 61 |
+
"loss": 2.7089,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.67,
|
| 66 |
+
"learning_rate": 3.8845759157631735e-05,
|
| 67 |
+
"loss": 2.6941,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.74,
|
| 72 |
+
"learning_rate": 3.7730335073394906e-05,
|
| 73 |
+
"loss": 2.6581,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.8,
|
| 78 |
+
"learning_rate": 3.661491098915808e-05,
|
| 79 |
+
"loss": 2.6449,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.87,
|
| 84 |
+
"learning_rate": 3.5499486904921255e-05,
|
| 85 |
+
"loss": 2.6534,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.94,
|
| 90 |
+
"learning_rate": 3.4384062820684427e-05,
|
| 91 |
+
"loss": 2.6297,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.0,
|
| 96 |
+
"learning_rate": 3.32686387364476e-05,
|
| 97 |
+
"loss": 2.6267,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.07,
|
| 102 |
+
"learning_rate": 3.2153214652210776e-05,
|
| 103 |
+
"loss": 2.4631,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.14,
|
| 108 |
+
"learning_rate": 3.103779056797395e-05,
|
| 109 |
+
"loss": 2.4614,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.2,
|
| 114 |
+
"learning_rate": 2.9922366483737118e-05,
|
| 115 |
+
"loss": 2.4762,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.27,
|
| 120 |
+
"learning_rate": 2.8806942399500293e-05,
|
| 121 |
+
"loss": 2.4324,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.34,
|
| 126 |
+
"learning_rate": 2.7691518315263464e-05,
|
| 127 |
+
"loss": 2.4394,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.41,
|
| 132 |
+
"learning_rate": 2.657609423102664e-05,
|
| 133 |
+
"loss": 2.4331,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.47,
|
| 138 |
+
"learning_rate": 2.546067014678981e-05,
|
| 139 |
+
"loss": 2.4087,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.54,
|
| 144 |
+
"learning_rate": 2.4345246062552984e-05,
|
| 145 |
+
"loss": 2.4048,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.61,
|
| 150 |
+
"learning_rate": 2.322982197831616e-05,
|
| 151 |
+
"loss": 2.4241,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.67,
|
| 156 |
+
"learning_rate": 2.211439789407933e-05,
|
| 157 |
+
"loss": 2.4255,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.74,
|
| 162 |
+
"learning_rate": 2.0998973809842505e-05,
|
| 163 |
+
"loss": 2.3951,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.81,
|
| 168 |
+
"learning_rate": 1.9883549725605676e-05,
|
| 169 |
+
"loss": 2.4398,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.87,
|
| 174 |
+
"learning_rate": 1.876812564136885e-05,
|
| 175 |
+
"loss": 2.395,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.94,
|
| 180 |
+
"learning_rate": 1.7652701557132022e-05,
|
| 181 |
+
"loss": 2.3734,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.01,
|
| 186 |
+
"learning_rate": 1.6537277472895197e-05,
|
| 187 |
+
"loss": 2.37,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.07,
|
| 192 |
+
"learning_rate": 1.5421853388658368e-05,
|
| 193 |
+
"loss": 2.2448,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.14,
|
| 198 |
+
"learning_rate": 1.4306429304421542e-05,
|
| 199 |
+
"loss": 2.2514,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.21,
|
| 204 |
+
"learning_rate": 1.3191005220184715e-05,
|
| 205 |
+
"loss": 2.2704,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.28,
|
| 210 |
+
"learning_rate": 1.2075581135947887e-05,
|
| 211 |
+
"loss": 2.2553,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.34,
|
| 216 |
+
"learning_rate": 1.0960157051711061e-05,
|
| 217 |
+
"loss": 2.2649,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.41,
|
| 222 |
+
"learning_rate": 9.844732967474234e-06,
|
| 223 |
+
"loss": 2.2569,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.48,
|
| 228 |
+
"learning_rate": 8.729308883237407e-06,
|
| 229 |
+
"loss": 2.217,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.54,
|
| 234 |
+
"learning_rate": 7.61388479900058e-06,
|
| 235 |
+
"loss": 2.2623,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.61,
|
| 240 |
+
"learning_rate": 6.498460714763753e-06,
|
| 241 |
+
"loss": 2.2607,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.68,
|
| 246 |
+
"learning_rate": 5.3830366305269266e-06,
|
| 247 |
+
"loss": 2.244,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.74,
|
| 252 |
+
"learning_rate": 4.2676125462901e-06,
|
| 253 |
+
"loss": 2.2591,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.81,
|
| 258 |
+
"learning_rate": 3.1521884620532732e-06,
|
| 259 |
+
"loss": 2.2415,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.88,
|
| 264 |
+
"learning_rate": 2.0367643778164457e-06,
|
| 265 |
+
"loss": 2.2263,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.94,
|
| 270 |
+
"learning_rate": 9.21340293579619e-07,
|
| 271 |
+
"loss": 2.2415,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.0,
|
| 276 |
+
"step": 22413,
|
| 277 |
+
"total_flos": 1.1708869345542144e+16,
|
| 278 |
+
"train_loss": 2.470616279322582,
|
| 279 |
+
"train_runtime": 9527.188,
|
| 280 |
+
"train_samples_per_second": 2.353,
|
| 281 |
+
"train_steps_per_second": 2.353
|
| 282 |
+
}
|
| 283 |
+
],
|
| 284 |
+
"max_steps": 22413,
|
| 285 |
+
"num_train_epochs": 3,
|
| 286 |
+
"total_flos": 1.1708869345542144e+16,
|
| 287 |
+
"trial_name": null,
|
| 288 |
+
"trial_params": null
|
| 289 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f45e97939e98f38775cb8e6926f000b2a542af2cea8b7aaa9466dafb9b67b7f
|
| 3 |
+
size 3119
|