File size: 5,156 Bytes
d7d3c7e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 10510,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.9514747859181731,
"grad_norm": 12745.587890625,
"learning_rate": 0.0005993999999999999,
"loss": 1.2234,
"step": 1000
},
{
"epoch": 1.0,
"eval_accuracy": 0.22268764859051285,
"eval_loss": 4.631209373474121,
"eval_runtime": 6.498,
"eval_samples_per_second": 37.242,
"eval_steps_per_second": 1.231,
"step": 1051
},
{
"epoch": 1.9029495718363463,
"grad_norm": 11723.8271484375,
"learning_rate": 0.0005369716088328075,
"loss": 1.015,
"step": 2000
},
{
"epoch": 2.0,
"eval_accuracy": 0.26512590771619415,
"eval_loss": 4.201041221618652,
"eval_runtime": 5.77,
"eval_samples_per_second": 41.941,
"eval_steps_per_second": 1.386,
"step": 2102
},
{
"epoch": 2.8544243577545196,
"grad_norm": 10506.5712890625,
"learning_rate": 0.00047388012618296526,
"loss": 0.9468,
"step": 3000
},
{
"epoch": 3.0,
"eval_accuracy": 0.28578706474098753,
"eval_loss": 4.014913558959961,
"eval_runtime": 5.9155,
"eval_samples_per_second": 40.91,
"eval_steps_per_second": 1.352,
"step": 3153
},
{
"epoch": 3.8058991436726926,
"grad_norm": 9833.72265625,
"learning_rate": 0.000410788643533123,
"loss": 0.9083,
"step": 4000
},
{
"epoch": 4.0,
"eval_accuracy": 0.30322977147385616,
"eval_loss": 3.8843796253204346,
"eval_runtime": 5.9819,
"eval_samples_per_second": 40.455,
"eval_steps_per_second": 1.337,
"step": 4204
},
{
"epoch": 4.757373929590866,
"grad_norm": 9816.0380859375,
"learning_rate": 0.0003476971608832807,
"loss": 0.8769,
"step": 5000
},
{
"epoch": 5.0,
"eval_accuracy": 0.3162653038120037,
"eval_loss": 3.772235870361328,
"eval_runtime": 5.9202,
"eval_samples_per_second": 40.877,
"eval_steps_per_second": 1.351,
"step": 5255
},
{
"epoch": 5.708848715509039,
"grad_norm": 9225.9716796875,
"learning_rate": 0.00028460567823343844,
"loss": 0.8502,
"step": 6000
},
{
"epoch": 6.0,
"eval_accuracy": 0.32605003962413676,
"eval_loss": 3.6949210166931152,
"eval_runtime": 5.9591,
"eval_samples_per_second": 40.61,
"eval_steps_per_second": 1.342,
"step": 6306
},
{
"epoch": 6.660323501427213,
"grad_norm": 9708.4267578125,
"learning_rate": 0.00022151419558359621,
"loss": 0.8276,
"step": 7000
},
{
"epoch": 7.0,
"eval_accuracy": 0.33672429687373645,
"eval_loss": 3.613666296005249,
"eval_runtime": 5.9886,
"eval_samples_per_second": 40.41,
"eval_steps_per_second": 1.336,
"step": 7357
},
{
"epoch": 7.611798287345385,
"grad_norm": 9902.1474609375,
"learning_rate": 0.00015842271293375394,
"loss": 0.8078,
"step": 8000
},
{
"epoch": 8.0,
"eval_accuracy": 0.3435170060325727,
"eval_loss": 3.560777425765991,
"eval_runtime": 5.8919,
"eval_samples_per_second": 41.073,
"eval_steps_per_second": 1.358,
"step": 8408
},
{
"epoch": 8.56327307326356,
"grad_norm": 9983.5361328125,
"learning_rate": 9.533123028391166e-05,
"loss": 0.7895,
"step": 9000
},
{
"epoch": 9.0,
"eval_accuracy": 0.3506978700004852,
"eval_loss": 3.5129082202911377,
"eval_runtime": 6.0614,
"eval_samples_per_second": 39.925,
"eval_steps_per_second": 1.32,
"step": 9459
},
{
"epoch": 9.514747859181732,
"grad_norm": 10257.3037109375,
"learning_rate": 3.22397476340694e-05,
"loss": 0.7746,
"step": 10000
},
{
"epoch": 10.0,
"eval_accuracy": 0.35421552295773967,
"eval_loss": 3.491698741912842,
"eval_runtime": 5.9119,
"eval_samples_per_second": 40.935,
"eval_steps_per_second": 1.353,
"step": 10510
},
{
"epoch": 10.0,
"step": 10510,
"total_flos": 8.78333165568e+16,
"train_loss": 0.8954192244133191,
"train_runtime": 9693.5758,
"train_samples_per_second": 34.678,
"train_steps_per_second": 1.084
}
],
"logging_steps": 1000,
"max_steps": 10510,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8.78333165568e+16,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|