End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.15,
|
| 3 |
+
"eval_accuracy": 0.5974110480409802,
|
| 4 |
+
"eval_loss": 2.3658390045166016,
|
| 5 |
+
"eval_runtime": 159.8962,
|
| 6 |
+
"eval_samples": 2330,
|
| 7 |
+
"eval_samples_per_second": 14.572,
|
| 8 |
+
"eval_steps_per_second": 14.572,
|
| 9 |
+
"perplexity": 10.652972961522288,
|
| 10 |
+
"train_loss": 2.5314815139770506,
|
| 11 |
+
"train_runtime": 879.4243,
|
| 12 |
+
"train_samples": 20691,
|
| 13 |
+
"train_samples_per_second": 3.639,
|
| 14 |
+
"train_steps_per_second": 0.455
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.15,
|
| 3 |
+
"eval_accuracy": 0.5974110480409802,
|
| 4 |
+
"eval_loss": 2.3658390045166016,
|
| 5 |
+
"eval_runtime": 159.8962,
|
| 6 |
+
"eval_samples": 2330,
|
| 7 |
+
"eval_samples_per_second": 14.572,
|
| 8 |
+
"eval_steps_per_second": 14.572,
|
| 9 |
+
"perplexity": 10.652972961522288
|
| 10 |
+
}
|
runs/Apr16_21-21-21_359ea6c74d92/events.out.tfevents.1681681402.359ea6c74d92.15015.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d26606b9876503a971bafe90d7fd0f72e0198a7ff0f807d35d0c46c0d109e4b2
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.15,
|
| 3 |
+
"train_loss": 2.5314815139770506,
|
| 4 |
+
"train_runtime": 879.4243,
|
| 5 |
+
"train_samples": 20691,
|
| 6 |
+
"train_samples_per_second": 3.639,
|
| 7 |
+
"train_steps_per_second": 0.455
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.15465661398675754,
|
| 5 |
+
"global_step": 400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 9.775e-06,
|
| 13 |
+
"loss": 3.3176,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 9.525000000000001e-06,
|
| 19 |
+
"loss": 2.8977,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"learning_rate": 9.275e-06,
|
| 25 |
+
"loss": 2.7035,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.02,
|
| 30 |
+
"learning_rate": 9.025e-06,
|
| 31 |
+
"loss": 2.7184,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.02,
|
| 36 |
+
"learning_rate": 8.775e-06,
|
| 37 |
+
"loss": 2.594,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02,
|
| 42 |
+
"learning_rate": 8.525e-06,
|
| 43 |
+
"loss": 2.6345,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03,
|
| 48 |
+
"learning_rate": 8.275000000000001e-06,
|
| 49 |
+
"loss": 2.7017,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.03,
|
| 54 |
+
"learning_rate": 8.025e-06,
|
| 55 |
+
"loss": 2.4358,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.03,
|
| 60 |
+
"learning_rate": 7.775000000000001e-06,
|
| 61 |
+
"loss": 2.5228,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.04,
|
| 66 |
+
"learning_rate": 7.525e-06,
|
| 67 |
+
"loss": 2.6187,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.04,
|
| 72 |
+
"learning_rate": 7.275000000000001e-06,
|
| 73 |
+
"loss": 2.4855,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.05,
|
| 78 |
+
"learning_rate": 7.0250000000000005e-06,
|
| 79 |
+
"loss": 2.4278,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.05,
|
| 84 |
+
"learning_rate": 6.775e-06,
|
| 85 |
+
"loss": 2.4997,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05,
|
| 90 |
+
"learning_rate": 6.525e-06,
|
| 91 |
+
"loss": 2.5494,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.06,
|
| 96 |
+
"learning_rate": 6.275e-06,
|
| 97 |
+
"loss": 2.5052,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.06,
|
| 102 |
+
"learning_rate": 6.025000000000001e-06,
|
| 103 |
+
"loss": 2.5652,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.07,
|
| 108 |
+
"learning_rate": 5.775000000000001e-06,
|
| 109 |
+
"loss": 2.5257,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.07,
|
| 114 |
+
"learning_rate": 5.5250000000000005e-06,
|
| 115 |
+
"loss": 2.5405,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.07,
|
| 120 |
+
"learning_rate": 5.275e-06,
|
| 121 |
+
"loss": 2.485,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.08,
|
| 126 |
+
"learning_rate": 5.025e-06,
|
| 127 |
+
"loss": 2.6217,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08,
|
| 132 |
+
"learning_rate": 4.775e-06,
|
| 133 |
+
"loss": 2.4446,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.09,
|
| 138 |
+
"learning_rate": 4.525000000000001e-06,
|
| 139 |
+
"loss": 2.4229,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.09,
|
| 144 |
+
"learning_rate": 4.2750000000000006e-06,
|
| 145 |
+
"loss": 2.5445,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.09,
|
| 150 |
+
"learning_rate": 4.0250000000000004e-06,
|
| 151 |
+
"loss": 2.4543,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.1,
|
| 156 |
+
"learning_rate": 3.7750000000000003e-06,
|
| 157 |
+
"loss": 2.5161,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.1,
|
| 162 |
+
"learning_rate": 3.525e-06,
|
| 163 |
+
"loss": 2.4905,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.1,
|
| 168 |
+
"learning_rate": 3.2750000000000004e-06,
|
| 169 |
+
"loss": 2.433,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11,
|
| 174 |
+
"learning_rate": 3.0250000000000003e-06,
|
| 175 |
+
"loss": 2.4915,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.11,
|
| 180 |
+
"learning_rate": 2.7750000000000005e-06,
|
| 181 |
+
"loss": 2.388,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.12,
|
| 186 |
+
"learning_rate": 2.5250000000000004e-06,
|
| 187 |
+
"loss": 2.4379,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.12,
|
| 192 |
+
"eval_accuracy": 0.5969701165049358,
|
| 193 |
+
"eval_loss": 2.3698670864105225,
|
| 194 |
+
"eval_runtime": 163.1025,
|
| 195 |
+
"eval_samples_per_second": 14.285,
|
| 196 |
+
"eval_steps_per_second": 14.285,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.12,
|
| 201 |
+
"learning_rate": 2.2750000000000002e-06,
|
| 202 |
+
"loss": 2.3871,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.12,
|
| 207 |
+
"learning_rate": 2.025e-06,
|
| 208 |
+
"loss": 2.476,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.13,
|
| 213 |
+
"learning_rate": 1.7750000000000002e-06,
|
| 214 |
+
"loss": 2.4082,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.13,
|
| 219 |
+
"learning_rate": 1.525e-06,
|
| 220 |
+
"loss": 2.354,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.14,
|
| 225 |
+
"learning_rate": 1.275e-06,
|
| 226 |
+
"loss": 2.404,
|
| 227 |
+
"step": 350
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.14,
|
| 231 |
+
"learning_rate": 1.025e-06,
|
| 232 |
+
"loss": 2.3877,
|
| 233 |
+
"step": 360
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.14,
|
| 237 |
+
"learning_rate": 7.750000000000001e-07,
|
| 238 |
+
"loss": 2.4133,
|
| 239 |
+
"step": 370
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.15,
|
| 243 |
+
"learning_rate": 5.250000000000001e-07,
|
| 244 |
+
"loss": 2.4382,
|
| 245 |
+
"step": 380
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.15,
|
| 249 |
+
"learning_rate": 2.75e-07,
|
| 250 |
+
"loss": 2.4238,
|
| 251 |
+
"step": 390
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.15,
|
| 255 |
+
"learning_rate": 2.5000000000000002e-08,
|
| 256 |
+
"loss": 2.5933,
|
| 257 |
+
"step": 400
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.15,
|
| 261 |
+
"step": 400,
|
| 262 |
+
"total_flos": 1672269004800000.0,
|
| 263 |
+
"train_loss": 2.5314815139770506,
|
| 264 |
+
"train_runtime": 879.4243,
|
| 265 |
+
"train_samples_per_second": 3.639,
|
| 266 |
+
"train_steps_per_second": 0.455
|
| 267 |
+
}
|
| 268 |
+
],
|
| 269 |
+
"max_steps": 400,
|
| 270 |
+
"num_train_epochs": 1,
|
| 271 |
+
"total_flos": 1672269004800000.0,
|
| 272 |
+
"trial_name": null,
|
| 273 |
+
"trial_params": null
|
| 274 |
+
}
|