End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +241 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.44,
|
| 3 |
+
"eval_accuracy": 0.2328767123287671,
|
| 4 |
+
"eval_loss": 1.693766474723816,
|
| 5 |
+
"eval_runtime": 22.6545,
|
| 6 |
+
"eval_samples_per_second": 3.222,
|
| 7 |
+
"eval_steps_per_second": 1.633
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.44,
|
| 3 |
+
"eval_accuracy": 0.2328767123287671,
|
| 4 |
+
"eval_loss": 1.693766474723816,
|
| 5 |
+
"eval_runtime": 22.6545,
|
| 6 |
+
"eval_samples_per_second": 3.222,
|
| 7 |
+
"eval_steps_per_second": 1.633
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.26666666666666666,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-caer-subset-5-classes-base-model\\checkpoint-139",
|
| 4 |
+
"epoch": 1.444,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 11.07775592803955,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 1.6854,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 16.159523010253906,
|
| 21 |
+
"learning_rate": 4e-05,
|
| 22 |
+
"loss": 1.6475,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 15.219178199768066,
|
| 28 |
+
"learning_rate": 4.888888888888889e-05,
|
| 29 |
+
"loss": 1.6296,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 12.341416358947754,
|
| 35 |
+
"learning_rate": 4.666666666666667e-05,
|
| 36 |
+
"loss": 1.7157,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 14.330547332763672,
|
| 42 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 43 |
+
"loss": 1.652,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 12.243963241577148,
|
| 49 |
+
"learning_rate": 4.222222222222222e-05,
|
| 50 |
+
"loss": 1.6353,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.28,
|
| 55 |
+
"grad_norm": 12.711626052856445,
|
| 56 |
+
"learning_rate": 4e-05,
|
| 57 |
+
"loss": 1.6923,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.32,
|
| 62 |
+
"grad_norm": 16.082073211669922,
|
| 63 |
+
"learning_rate": 3.777777777777778e-05,
|
| 64 |
+
"loss": 1.5922,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.36,
|
| 69 |
+
"grad_norm": 16.63982582092285,
|
| 70 |
+
"learning_rate": 3.555555555555556e-05,
|
| 71 |
+
"loss": 1.7151,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4,
|
| 76 |
+
"grad_norm": 8.993603706359863,
|
| 77 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 78 |
+
"loss": 1.718,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.44,
|
| 83 |
+
"grad_norm": 11.654336929321289,
|
| 84 |
+
"learning_rate": 3.111111111111111e-05,
|
| 85 |
+
"loss": 1.6497,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48,
|
| 90 |
+
"grad_norm": 10.800435066223145,
|
| 91 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 92 |
+
"loss": 1.6542,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.52,
|
| 97 |
+
"grad_norm": 9.841632843017578,
|
| 98 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 99 |
+
"loss": 1.5763,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.56,
|
| 104 |
+
"eval_accuracy": 0.26666666666666666,
|
| 105 |
+
"eval_loss": 1.641332983970642,
|
| 106 |
+
"eval_runtime": 9.3839,
|
| 107 |
+
"eval_samples_per_second": 3.197,
|
| 108 |
+
"eval_steps_per_second": 1.598,
|
| 109 |
+
"step": 139
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.0,
|
| 113 |
+
"grad_norm": 13.519031524658203,
|
| 114 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 115 |
+
"loss": 1.5659,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.04,
|
| 120 |
+
"grad_norm": 9.212859153747559,
|
| 121 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 122 |
+
"loss": 1.6481,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.08,
|
| 127 |
+
"grad_norm": 10.454906463623047,
|
| 128 |
+
"learning_rate": 2e-05,
|
| 129 |
+
"loss": 1.7381,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.12,
|
| 134 |
+
"grad_norm": 11.107510566711426,
|
| 135 |
+
"learning_rate": 1.777777777777778e-05,
|
| 136 |
+
"loss": 1.6243,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.16,
|
| 141 |
+
"grad_norm": 9.847452163696289,
|
| 142 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 143 |
+
"loss": 1.5956,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.2,
|
| 148 |
+
"grad_norm": 11.35783576965332,
|
| 149 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 150 |
+
"loss": 1.6769,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.24,
|
| 155 |
+
"grad_norm": 8.935040473937988,
|
| 156 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 157 |
+
"loss": 1.5996,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.28,
|
| 162 |
+
"grad_norm": 10.564764976501465,
|
| 163 |
+
"learning_rate": 8.88888888888889e-06,
|
| 164 |
+
"loss": 1.7105,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.32,
|
| 169 |
+
"grad_norm": 9.259597778320312,
|
| 170 |
+
"learning_rate": 6.666666666666667e-06,
|
| 171 |
+
"loss": 1.6253,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.36,
|
| 176 |
+
"grad_norm": 15.238162994384766,
|
| 177 |
+
"learning_rate": 4.444444444444445e-06,
|
| 178 |
+
"loss": 1.5752,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.4,
|
| 183 |
+
"grad_norm": 9.198563575744629,
|
| 184 |
+
"learning_rate": 2.2222222222222225e-06,
|
| 185 |
+
"loss": 1.5624,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.44,
|
| 190 |
+
"grad_norm": 9.007689476013184,
|
| 191 |
+
"learning_rate": 0.0,
|
| 192 |
+
"loss": 1.5825,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.44,
|
| 197 |
+
"eval_accuracy": 0.2,
|
| 198 |
+
"eval_loss": 1.615497350692749,
|
| 199 |
+
"eval_runtime": 9.657,
|
| 200 |
+
"eval_samples_per_second": 3.107,
|
| 201 |
+
"eval_steps_per_second": 1.553,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.44,
|
| 206 |
+
"step": 250,
|
| 207 |
+
"total_flos": 6.2304896360448e+17,
|
| 208 |
+
"train_loss": 1.6427093963623047,
|
| 209 |
+
"train_runtime": 248.4449,
|
| 210 |
+
"train_samples_per_second": 2.013,
|
| 211 |
+
"train_steps_per_second": 1.006
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.44,
|
| 215 |
+
"eval_accuracy": 0.2328767123287671,
|
| 216 |
+
"eval_loss": 1.6937663555145264,
|
| 217 |
+
"eval_runtime": 21.9862,
|
| 218 |
+
"eval_samples_per_second": 3.32,
|
| 219 |
+
"eval_steps_per_second": 1.683,
|
| 220 |
+
"step": 250
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.44,
|
| 224 |
+
"eval_accuracy": 0.2328767123287671,
|
| 225 |
+
"eval_loss": 1.693766474723816,
|
| 226 |
+
"eval_runtime": 22.6545,
|
| 227 |
+
"eval_samples_per_second": 3.222,
|
| 228 |
+
"eval_steps_per_second": 1.633,
|
| 229 |
+
"step": 250
|
| 230 |
+
}
|
| 231 |
+
],
|
| 232 |
+
"logging_steps": 10,
|
| 233 |
+
"max_steps": 250,
|
| 234 |
+
"num_input_tokens_seen": 0,
|
| 235 |
+
"num_train_epochs": 9223372036854775807,
|
| 236 |
+
"save_steps": 500,
|
| 237 |
+
"total_flos": 6.2304896360448e+17,
|
| 238 |
+
"train_batch_size": 2,
|
| 239 |
+
"trial_name": null,
|
| 240 |
+
"trial_params": null
|
| 241 |
+
}
|