Commit
·
96c0cbf
1
Parent(s):
2ba18b8
End of training
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- runs/Apr11_19-26-37_relela-04/events.out.tfevents.1681309449.relela-04.1511770.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +279 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_bleu": 0.9098,
|
| 4 |
+
"eval_gen_len": 235.1613,
|
| 5 |
+
"eval_loss": 0.163666233420372,
|
| 6 |
+
"eval_runtime": 7809.6178,
|
| 7 |
+
"eval_samples": 78039,
|
| 8 |
+
"eval_samples_per_second": 9.993,
|
| 9 |
+
"eval_steps_per_second": 0.156,
|
| 10 |
+
"train_loss": 0.21620578862409723,
|
| 11 |
+
"train_runtime": 45769.0844,
|
| 12 |
+
"train_samples": 624312,
|
| 13 |
+
"train_samples_per_second": 27.281,
|
| 14 |
+
"train_steps_per_second": 0.426
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_bleu": 0.9098,
|
| 4 |
+
"eval_gen_len": 235.1613,
|
| 5 |
+
"eval_loss": 0.163666233420372,
|
| 6 |
+
"eval_runtime": 7809.6178,
|
| 7 |
+
"eval_samples": 78039,
|
| 8 |
+
"eval_samples_per_second": 9.993,
|
| 9 |
+
"eval_steps_per_second": 0.156
|
| 10 |
+
}
|
runs/Apr11_19-26-37_relela-04/events.out.tfevents.1681309449.relela-04.1511770.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf60caf8c6b398a12fb5137a76d4b29951f4ad699116a1afd60217c36c996e8b
|
| 3 |
+
size 417
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.21620578862409723,
|
| 4 |
+
"train_runtime": 45769.0844,
|
| 5 |
+
"train_samples": 624312,
|
| 6 |
+
"train_samples_per_second": 27.281,
|
| 7 |
+
"train_steps_per_second": 0.426
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,279 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 19510,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 4.8718605843157357e-05,
|
| 13 |
+
"loss": 0.5024,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 4.743721168631472e-05,
|
| 19 |
+
"loss": 0.3004,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.15,
|
| 24 |
+
"learning_rate": 4.6155817529472065e-05,
|
| 25 |
+
"loss": 0.2771,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.21,
|
| 30 |
+
"learning_rate": 4.487442337262942e-05,
|
| 31 |
+
"loss": 0.2631,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.26,
|
| 36 |
+
"learning_rate": 4.359302921578678e-05,
|
| 37 |
+
"loss": 0.2525,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.31,
|
| 42 |
+
"learning_rate": 4.2311635058944134e-05,
|
| 43 |
+
"loss": 0.246,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.36,
|
| 48 |
+
"learning_rate": 4.103024090210149e-05,
|
| 49 |
+
"loss": 0.2379,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.41,
|
| 54 |
+
"learning_rate": 3.974884674525884e-05,
|
| 55 |
+
"loss": 0.2329,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.46,
|
| 60 |
+
"learning_rate": 3.8467452588416197e-05,
|
| 61 |
+
"loss": 0.2266,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.51,
|
| 66 |
+
"learning_rate": 3.718605843157356e-05,
|
| 67 |
+
"loss": 0.224,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.56,
|
| 72 |
+
"learning_rate": 3.590466427473091e-05,
|
| 73 |
+
"loss": 0.219,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.62,
|
| 78 |
+
"learning_rate": 3.462327011788826e-05,
|
| 79 |
+
"loss": 0.2148,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.67,
|
| 84 |
+
"learning_rate": 3.334187596104562e-05,
|
| 85 |
+
"loss": 0.2128,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.72,
|
| 90 |
+
"learning_rate": 3.2060481804202974e-05,
|
| 91 |
+
"loss": 0.2118,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.77,
|
| 96 |
+
"learning_rate": 3.077908764736033e-05,
|
| 97 |
+
"loss": 0.2088,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.82,
|
| 102 |
+
"learning_rate": 2.9497693490517686e-05,
|
| 103 |
+
"loss": 0.2042,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.87,
|
| 108 |
+
"learning_rate": 2.821629933367504e-05,
|
| 109 |
+
"loss": 0.2031,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.92,
|
| 114 |
+
"learning_rate": 2.693490517683239e-05,
|
| 115 |
+
"loss": 0.2031,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.97,
|
| 120 |
+
"learning_rate": 2.565351101998975e-05,
|
| 121 |
+
"loss": 0.1993,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.0,
|
| 126 |
+
"eval_bleu": 0.0,
|
| 127 |
+
"eval_gen_len": 19.0,
|
| 128 |
+
"eval_loss": 0.17119529843330383,
|
| 129 |
+
"eval_runtime": 1684.1894,
|
| 130 |
+
"eval_samples_per_second": 46.336,
|
| 131 |
+
"eval_steps_per_second": 0.724,
|
| 132 |
+
"step": 9755
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.03,
|
| 136 |
+
"learning_rate": 2.4372116863147106e-05,
|
| 137 |
+
"loss": 0.1977,
|
| 138 |
+
"step": 10000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.08,
|
| 142 |
+
"learning_rate": 2.309072270630446e-05,
|
| 143 |
+
"loss": 0.1966,
|
| 144 |
+
"step": 10500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.13,
|
| 148 |
+
"learning_rate": 2.1809328549461817e-05,
|
| 149 |
+
"loss": 0.1957,
|
| 150 |
+
"step": 11000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.18,
|
| 154 |
+
"learning_rate": 2.052793439261917e-05,
|
| 155 |
+
"loss": 0.1938,
|
| 156 |
+
"step": 11500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.23,
|
| 160 |
+
"learning_rate": 1.9246540235776526e-05,
|
| 161 |
+
"loss": 0.1927,
|
| 162 |
+
"step": 12000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.28,
|
| 166 |
+
"learning_rate": 1.796514607893388e-05,
|
| 167 |
+
"loss": 0.1926,
|
| 168 |
+
"step": 12500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.33,
|
| 172 |
+
"learning_rate": 1.6683751922091237e-05,
|
| 173 |
+
"loss": 0.1908,
|
| 174 |
+
"step": 13000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.38,
|
| 178 |
+
"learning_rate": 1.540235776524859e-05,
|
| 179 |
+
"loss": 0.1901,
|
| 180 |
+
"step": 13500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.44,
|
| 184 |
+
"learning_rate": 1.4120963608405946e-05,
|
| 185 |
+
"loss": 0.1892,
|
| 186 |
+
"step": 14000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.49,
|
| 190 |
+
"learning_rate": 1.2839569451563302e-05,
|
| 191 |
+
"loss": 0.1886,
|
| 192 |
+
"step": 14500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.54,
|
| 196 |
+
"learning_rate": 1.1558175294720656e-05,
|
| 197 |
+
"loss": 0.1893,
|
| 198 |
+
"step": 15000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.59,
|
| 202 |
+
"learning_rate": 1.0276781137878012e-05,
|
| 203 |
+
"loss": 0.1872,
|
| 204 |
+
"step": 15500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.64,
|
| 208 |
+
"learning_rate": 8.995386981035367e-06,
|
| 209 |
+
"loss": 0.1879,
|
| 210 |
+
"step": 16000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.69,
|
| 214 |
+
"learning_rate": 7.713992824192722e-06,
|
| 215 |
+
"loss": 0.1862,
|
| 216 |
+
"step": 16500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.74,
|
| 220 |
+
"learning_rate": 6.432598667350077e-06,
|
| 221 |
+
"loss": 0.1862,
|
| 222 |
+
"step": 17000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.79,
|
| 226 |
+
"learning_rate": 5.151204510507432e-06,
|
| 227 |
+
"loss": 0.1861,
|
| 228 |
+
"step": 17500
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.85,
|
| 232 |
+
"learning_rate": 3.869810353664787e-06,
|
| 233 |
+
"loss": 0.185,
|
| 234 |
+
"step": 18000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.9,
|
| 238 |
+
"learning_rate": 2.588416196822143e-06,
|
| 239 |
+
"loss": 0.1848,
|
| 240 |
+
"step": 18500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.95,
|
| 244 |
+
"learning_rate": 1.3070220399794978e-06,
|
| 245 |
+
"loss": 0.186,
|
| 246 |
+
"step": 19000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.0,
|
| 250 |
+
"learning_rate": 2.5627883136852895e-08,
|
| 251 |
+
"loss": 0.1863,
|
| 252 |
+
"step": 19500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.0,
|
| 256 |
+
"eval_bleu": 0.0,
|
| 257 |
+
"eval_gen_len": 19.0,
|
| 258 |
+
"eval_loss": 0.163666233420372,
|
| 259 |
+
"eval_runtime": 1684.6721,
|
| 260 |
+
"eval_samples_per_second": 46.323,
|
| 261 |
+
"eval_steps_per_second": 0.724,
|
| 262 |
+
"step": 19510
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.0,
|
| 266 |
+
"step": 19510,
|
| 267 |
+
"total_flos": 3.801797311667896e+17,
|
| 268 |
+
"train_loss": 0.21620578862409723,
|
| 269 |
+
"train_runtime": 45769.0844,
|
| 270 |
+
"train_samples_per_second": 27.281,
|
| 271 |
+
"train_steps_per_second": 0.426
|
| 272 |
+
}
|
| 273 |
+
],
|
| 274 |
+
"max_steps": 19510,
|
| 275 |
+
"num_train_epochs": 2,
|
| 276 |
+
"total_flos": 3.801797311667896e+17,
|
| 277 |
+
"trial_name": null,
|
| 278 |
+
"trial_params": null
|
| 279 |
+
}
|