End of training
Browse files- all_results.json +11 -0
- eval_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +431 -0
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.0708099901676178,
|
| 4 |
+
"eval_runtime": 220.4842,
|
| 5 |
+
"eval_samples_per_second": 35.15,
|
| 6 |
+
"eval_steps_per_second": 8.79,
|
| 7 |
+
"train_loss": 0.07038866728798608,
|
| 8 |
+
"train_runtime": 25445.4127,
|
| 9 |
+
"train_samples_per_second": 4.604,
|
| 10 |
+
"train_steps_per_second": 1.151
|
| 11 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.0708099901676178,
|
| 4 |
+
"eval_runtime": 220.4842,
|
| 5 |
+
"eval_samples_per_second": 35.15,
|
| 6 |
+
"eval_steps_per_second": 8.79
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.07038866728798608,
|
| 4 |
+
"train_runtime": 25445.4127,
|
| 5 |
+
"train_samples_per_second": 4.604,
|
| 6 |
+
"train_steps_per_second": 1.151
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,431 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0708099901676178,
|
| 3 |
+
"best_model_checkpoint": "/nasty/data/tpid/vizwiz/ViTGPT2I2A/checkpoint-17000",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 29290,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.17,
|
| 12 |
+
"learning_rate": 1.9320587231136908e-05,
|
| 13 |
+
"loss": 0.1528,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"eval_loss": 0.08688350766897202,
|
| 19 |
+
"eval_runtime": 552.3255,
|
| 20 |
+
"eval_samples_per_second": 14.032,
|
| 21 |
+
"eval_steps_per_second": 3.509,
|
| 22 |
+
"step": 1000
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.34,
|
| 26 |
+
"learning_rate": 1.8637760327756916e-05,
|
| 27 |
+
"loss": 0.0899,
|
| 28 |
+
"step": 2000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.34,
|
| 32 |
+
"eval_loss": 0.08172640949487686,
|
| 33 |
+
"eval_runtime": 437.9983,
|
| 34 |
+
"eval_samples_per_second": 17.694,
|
| 35 |
+
"eval_steps_per_second": 4.425,
|
| 36 |
+
"step": 2000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.51,
|
| 40 |
+
"learning_rate": 1.795493342437692e-05,
|
| 41 |
+
"loss": 0.084,
|
| 42 |
+
"step": 3000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.51,
|
| 46 |
+
"eval_loss": 0.07901930063962936,
|
| 47 |
+
"eval_runtime": 217.4661,
|
| 48 |
+
"eval_samples_per_second": 35.638,
|
| 49 |
+
"eval_steps_per_second": 8.912,
|
| 50 |
+
"step": 3000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.68,
|
| 54 |
+
"learning_rate": 1.7272106520996928e-05,
|
| 55 |
+
"loss": 0.0814,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.68,
|
| 60 |
+
"eval_loss": 0.07728389650583267,
|
| 61 |
+
"eval_runtime": 218.3505,
|
| 62 |
+
"eval_samples_per_second": 35.493,
|
| 63 |
+
"eval_steps_per_second": 8.876,
|
| 64 |
+
"step": 4000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.85,
|
| 68 |
+
"learning_rate": 1.6589279617616936e-05,
|
| 69 |
+
"loss": 0.0803,
|
| 70 |
+
"step": 5000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.85,
|
| 74 |
+
"eval_loss": 0.07569148391485214,
|
| 75 |
+
"eval_runtime": 218.1796,
|
| 76 |
+
"eval_samples_per_second": 35.521,
|
| 77 |
+
"eval_steps_per_second": 8.883,
|
| 78 |
+
"step": 5000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.02,
|
| 82 |
+
"learning_rate": 1.590645271423694e-05,
|
| 83 |
+
"loss": 0.077,
|
| 84 |
+
"step": 6000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.02,
|
| 88 |
+
"eval_loss": 0.07452211529016495,
|
| 89 |
+
"eval_runtime": 220.2685,
|
| 90 |
+
"eval_samples_per_second": 35.184,
|
| 91 |
+
"eval_steps_per_second": 8.798,
|
| 92 |
+
"step": 6000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.19,
|
| 96 |
+
"learning_rate": 1.5223625810856947e-05,
|
| 97 |
+
"loss": 0.0739,
|
| 98 |
+
"step": 7000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.19,
|
| 102 |
+
"eval_loss": 0.0739876851439476,
|
| 103 |
+
"eval_runtime": 205.9033,
|
| 104 |
+
"eval_samples_per_second": 37.639,
|
| 105 |
+
"eval_steps_per_second": 9.412,
|
| 106 |
+
"step": 7000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.37,
|
| 110 |
+
"learning_rate": 1.4540798907476957e-05,
|
| 111 |
+
"loss": 0.0719,
|
| 112 |
+
"step": 8000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.37,
|
| 116 |
+
"eval_loss": 0.07368426769971848,
|
| 117 |
+
"eval_runtime": 217.9815,
|
| 118 |
+
"eval_samples_per_second": 35.553,
|
| 119 |
+
"eval_steps_per_second": 8.891,
|
| 120 |
+
"step": 8000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.54,
|
| 124 |
+
"learning_rate": 1.3857972004096963e-05,
|
| 125 |
+
"loss": 0.0717,
|
| 126 |
+
"step": 9000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.54,
|
| 130 |
+
"eval_loss": 0.07300957292318344,
|
| 131 |
+
"eval_runtime": 219.2086,
|
| 132 |
+
"eval_samples_per_second": 35.354,
|
| 133 |
+
"eval_steps_per_second": 8.841,
|
| 134 |
+
"step": 9000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.71,
|
| 138 |
+
"learning_rate": 1.3175145100716968e-05,
|
| 139 |
+
"loss": 0.0731,
|
| 140 |
+
"step": 10000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.71,
|
| 144 |
+
"eval_loss": 0.0726846307516098,
|
| 145 |
+
"eval_runtime": 219.3614,
|
| 146 |
+
"eval_samples_per_second": 35.33,
|
| 147 |
+
"eval_steps_per_second": 8.835,
|
| 148 |
+
"step": 10000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.88,
|
| 152 |
+
"learning_rate": 1.2492318197336977e-05,
|
| 153 |
+
"loss": 0.0708,
|
| 154 |
+
"step": 11000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.88,
|
| 158 |
+
"eval_loss": 0.07204297184944153,
|
| 159 |
+
"eval_runtime": 217.9036,
|
| 160 |
+
"eval_samples_per_second": 35.566,
|
| 161 |
+
"eval_steps_per_second": 8.894,
|
| 162 |
+
"step": 11000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.05,
|
| 166 |
+
"learning_rate": 1.1809491293956984e-05,
|
| 167 |
+
"loss": 0.0697,
|
| 168 |
+
"step": 12000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.05,
|
| 172 |
+
"eval_loss": 0.07171137630939484,
|
| 173 |
+
"eval_runtime": 219.7173,
|
| 174 |
+
"eval_samples_per_second": 35.273,
|
| 175 |
+
"eval_steps_per_second": 8.82,
|
| 176 |
+
"step": 12000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.22,
|
| 180 |
+
"learning_rate": 1.1126664390576988e-05,
|
| 181 |
+
"loss": 0.0655,
|
| 182 |
+
"step": 13000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.22,
|
| 186 |
+
"eval_loss": 0.07193101197481155,
|
| 187 |
+
"eval_runtime": 218.2496,
|
| 188 |
+
"eval_samples_per_second": 35.51,
|
| 189 |
+
"eval_steps_per_second": 8.88,
|
| 190 |
+
"step": 13000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.39,
|
| 194 |
+
"learning_rate": 1.0443837487196998e-05,
|
| 195 |
+
"loss": 0.0653,
|
| 196 |
+
"step": 14000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.39,
|
| 200 |
+
"eval_loss": 0.07193595170974731,
|
| 201 |
+
"eval_runtime": 218.5083,
|
| 202 |
+
"eval_samples_per_second": 35.468,
|
| 203 |
+
"eval_steps_per_second": 8.869,
|
| 204 |
+
"step": 14000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.56,
|
| 208 |
+
"learning_rate": 9.761693410720383e-06,
|
| 209 |
+
"loss": 0.0657,
|
| 210 |
+
"step": 15000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.56,
|
| 214 |
+
"eval_loss": 0.07120098173618317,
|
| 215 |
+
"eval_runtime": 219.0492,
|
| 216 |
+
"eval_samples_per_second": 35.38,
|
| 217 |
+
"eval_steps_per_second": 8.847,
|
| 218 |
+
"step": 15000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.73,
|
| 222 |
+
"learning_rate": 9.07886650734039e-06,
|
| 223 |
+
"loss": 0.0663,
|
| 224 |
+
"step": 16000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.73,
|
| 228 |
+
"eval_loss": 0.07102101296186447,
|
| 229 |
+
"eval_runtime": 218.7347,
|
| 230 |
+
"eval_samples_per_second": 35.431,
|
| 231 |
+
"eval_steps_per_second": 8.86,
|
| 232 |
+
"step": 16000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.9,
|
| 236 |
+
"learning_rate": 8.396722430863777e-06,
|
| 237 |
+
"loss": 0.0654,
|
| 238 |
+
"step": 17000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 2.9,
|
| 242 |
+
"eval_loss": 0.0708099901676178,
|
| 243 |
+
"eval_runtime": 218.8513,
|
| 244 |
+
"eval_samples_per_second": 35.412,
|
| 245 |
+
"eval_steps_per_second": 8.855,
|
| 246 |
+
"step": 17000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.07,
|
| 250 |
+
"learning_rate": 7.713895527483783e-06,
|
| 251 |
+
"loss": 0.0645,
|
| 252 |
+
"step": 18000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.07,
|
| 256 |
+
"eval_loss": 0.07163063436746597,
|
| 257 |
+
"eval_runtime": 219.9493,
|
| 258 |
+
"eval_samples_per_second": 35.235,
|
| 259 |
+
"eval_steps_per_second": 8.811,
|
| 260 |
+
"step": 18000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.24,
|
| 264 |
+
"learning_rate": 7.0317514510071705e-06,
|
| 265 |
+
"loss": 0.0616,
|
| 266 |
+
"step": 19000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.24,
|
| 270 |
+
"eval_loss": 0.07119180262088776,
|
| 271 |
+
"eval_runtime": 219.2713,
|
| 272 |
+
"eval_samples_per_second": 35.344,
|
| 273 |
+
"eval_steps_per_second": 8.838,
|
| 274 |
+
"step": 19000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.41,
|
| 278 |
+
"learning_rate": 6.348924547627177e-06,
|
| 279 |
+
"loss": 0.0607,
|
| 280 |
+
"step": 20000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 3.41,
|
| 284 |
+
"eval_loss": 0.07116228342056274,
|
| 285 |
+
"eval_runtime": 219.1634,
|
| 286 |
+
"eval_samples_per_second": 35.362,
|
| 287 |
+
"eval_steps_per_second": 8.843,
|
| 288 |
+
"step": 20000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.58,
|
| 292 |
+
"learning_rate": 5.666097644247184e-06,
|
| 293 |
+
"loss": 0.0611,
|
| 294 |
+
"step": 21000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 3.58,
|
| 298 |
+
"eval_loss": 0.07110943645238876,
|
| 299 |
+
"eval_runtime": 219.7957,
|
| 300 |
+
"eval_samples_per_second": 35.26,
|
| 301 |
+
"eval_steps_per_second": 8.817,
|
| 302 |
+
"step": 21000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.76,
|
| 306 |
+
"learning_rate": 4.98327074086719e-06,
|
| 307 |
+
"loss": 0.0615,
|
| 308 |
+
"step": 22000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.76,
|
| 312 |
+
"eval_loss": 0.07111015915870667,
|
| 313 |
+
"eval_runtime": 220.0979,
|
| 314 |
+
"eval_samples_per_second": 35.212,
|
| 315 |
+
"eval_steps_per_second": 8.805,
|
| 316 |
+
"step": 22000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.93,
|
| 320 |
+
"learning_rate": 4.3018094912939576e-06,
|
| 321 |
+
"loss": 0.0614,
|
| 322 |
+
"step": 23000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 3.93,
|
| 326 |
+
"eval_loss": 0.0710098147392273,
|
| 327 |
+
"eval_runtime": 223.1322,
|
| 328 |
+
"eval_samples_per_second": 34.733,
|
| 329 |
+
"eval_steps_per_second": 8.685,
|
| 330 |
+
"step": 23000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 4.1,
|
| 334 |
+
"learning_rate": 3.618982587913964e-06,
|
| 335 |
+
"loss": 0.0594,
|
| 336 |
+
"step": 24000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.1,
|
| 340 |
+
"eval_loss": 0.07158154249191284,
|
| 341 |
+
"eval_runtime": 220.2761,
|
| 342 |
+
"eval_samples_per_second": 35.183,
|
| 343 |
+
"eval_steps_per_second": 8.798,
|
| 344 |
+
"step": 24000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.27,
|
| 348 |
+
"learning_rate": 2.936155684533971e-06,
|
| 349 |
+
"loss": 0.0587,
|
| 350 |
+
"step": 25000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.27,
|
| 354 |
+
"eval_loss": 0.07150966674089432,
|
| 355 |
+
"eval_runtime": 223.8011,
|
| 356 |
+
"eval_samples_per_second": 34.629,
|
| 357 |
+
"eval_steps_per_second": 8.659,
|
| 358 |
+
"step": 25000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 4.44,
|
| 362 |
+
"learning_rate": 2.2533287811539777e-06,
|
| 363 |
+
"loss": 0.0574,
|
| 364 |
+
"step": 26000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.44,
|
| 368 |
+
"eval_loss": 0.07154253125190735,
|
| 369 |
+
"eval_runtime": 216.2215,
|
| 370 |
+
"eval_samples_per_second": 35.843,
|
| 371 |
+
"eval_steps_per_second": 8.963,
|
| 372 |
+
"step": 26000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 4.61,
|
| 376 |
+
"learning_rate": 1.5711847046773643e-06,
|
| 377 |
+
"loss": 0.0579,
|
| 378 |
+
"step": 27000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 4.61,
|
| 382 |
+
"eval_loss": 0.07154078036546707,
|
| 383 |
+
"eval_runtime": 219.6549,
|
| 384 |
+
"eval_samples_per_second": 35.283,
|
| 385 |
+
"eval_steps_per_second": 8.823,
|
| 386 |
+
"step": 27000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.78,
|
| 390 |
+
"learning_rate": 8.883578012973712e-07,
|
| 391 |
+
"loss": 0.0581,
|
| 392 |
+
"step": 28000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.78,
|
| 396 |
+
"eval_loss": 0.07147673517465591,
|
| 397 |
+
"eval_runtime": 218.889,
|
| 398 |
+
"eval_samples_per_second": 35.406,
|
| 399 |
+
"eval_steps_per_second": 8.854,
|
| 400 |
+
"step": 28000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 4.95,
|
| 404 |
+
"learning_rate": 2.0553089791737796e-07,
|
| 405 |
+
"loss": 0.0579,
|
| 406 |
+
"step": 29000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 4.95,
|
| 410 |
+
"eval_loss": 0.07150830328464508,
|
| 411 |
+
"eval_runtime": 219.8431,
|
| 412 |
+
"eval_samples_per_second": 35.252,
|
| 413 |
+
"eval_steps_per_second": 8.815,
|
| 414 |
+
"step": 29000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 5.0,
|
| 418 |
+
"step": 29290,
|
| 419 |
+
"total_flos": 2.1143149521668145e+19,
|
| 420 |
+
"train_loss": 0.07038866728798608,
|
| 421 |
+
"train_runtime": 25445.4127,
|
| 422 |
+
"train_samples_per_second": 4.604,
|
| 423 |
+
"train_steps_per_second": 1.151
|
| 424 |
+
}
|
| 425 |
+
],
|
| 426 |
+
"max_steps": 29290,
|
| 427 |
+
"num_train_epochs": 5,
|
| 428 |
+
"total_flos": 2.1143149521668145e+19,
|
| 429 |
+
"trial_name": null,
|
| 430 |
+
"trial_params": null
|
| 431 |
+
}
|