File size: 4,684 Bytes
a3db559 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.0,
"eval_steps": 500,
"global_step": 1125,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5333333333333333,
"grad_norm": 0.9283596873283386,
"learning_rate": 3e-05,
"loss": 1.963,
"step": 100
},
{
"epoch": 0.9973333333333333,
"eval_accuracy": 0.5695384615384615,
"eval_loss": 1.6438876390457153,
"eval_runtime": 5.0534,
"eval_samples_per_second": 98.943,
"eval_steps_per_second": 12.467,
"step": 187
},
{
"epoch": 0.9973333333333333,
"eval_exact_match": 16.2,
"eval_f1": 25.888571428571442,
"step": 187
},
{
"epoch": 1.0666666666666667,
"grad_norm": 1.0407154560089111,
"learning_rate": 3e-05,
"loss": 1.6668,
"step": 200
},
{
"epoch": 1.6,
"grad_norm": 1.1281720399856567,
"learning_rate": 3e-05,
"loss": 1.6099,
"step": 300
},
{
"epoch": 2.0,
"eval_accuracy": 0.5733333333333334,
"eval_loss": 1.618270754814148,
"eval_runtime": 5.1983,
"eval_samples_per_second": 96.186,
"eval_steps_per_second": 12.119,
"step": 375
},
{
"epoch": 2.0,
"eval_exact_match": 16.6,
"eval_f1": 26.287619047619057,
"step": 375
},
{
"epoch": 2.1333333333333333,
"grad_norm": 1.2508225440979004,
"learning_rate": 3e-05,
"loss": 1.5866,
"step": 400
},
{
"epoch": 2.6666666666666665,
"grad_norm": 1.3197834491729736,
"learning_rate": 3e-05,
"loss": 1.524,
"step": 500
},
{
"epoch": 2.997333333333333,
"eval_accuracy": 0.5743589743589743,
"eval_loss": 1.6164497137069702,
"eval_runtime": 5.0495,
"eval_samples_per_second": 99.019,
"eval_steps_per_second": 12.476,
"step": 562
},
{
"epoch": 2.997333333333333,
"eval_exact_match": 17.8,
"eval_f1": 27.35428571428571,
"step": 562
},
{
"epoch": 3.2,
"grad_norm": 1.6320394277572632,
"learning_rate": 3e-05,
"loss": 1.4752,
"step": 600
},
{
"epoch": 3.7333333333333334,
"grad_norm": 1.7101725339889526,
"learning_rate": 3e-05,
"loss": 1.3938,
"step": 700
},
{
"epoch": 4.0,
"eval_accuracy": 0.5728717948717948,
"eval_loss": 1.6376241445541382,
"eval_runtime": 4.9662,
"eval_samples_per_second": 100.68,
"eval_steps_per_second": 12.686,
"step": 750
},
{
"epoch": 4.0,
"eval_exact_match": 18.0,
"eval_f1": 27.498571428571427,
"step": 750
},
{
"epoch": 4.266666666666667,
"grad_norm": 2.1727664470672607,
"learning_rate": 3e-05,
"loss": 1.342,
"step": 800
},
{
"epoch": 4.8,
"grad_norm": 2.341384172439575,
"learning_rate": 3e-05,
"loss": 1.2685,
"step": 900
},
{
"epoch": 4.997333333333334,
"eval_accuracy": 0.5699487179487179,
"eval_loss": 1.684618353843689,
"eval_runtime": 5.5457,
"eval_samples_per_second": 90.16,
"eval_steps_per_second": 11.36,
"step": 937
},
{
"epoch": 4.997333333333334,
"eval_exact_match": 19.2,
"eval_f1": 28.190952380952375,
"step": 937
},
{
"epoch": 5.333333333333333,
"grad_norm": 2.5624172687530518,
"learning_rate": 3e-05,
"loss": 1.1847,
"step": 1000
},
{
"epoch": 5.866666666666667,
"grad_norm": 2.8159019947052,
"learning_rate": 3e-05,
"loss": 1.1591,
"step": 1100
},
{
"epoch": 6.0,
"eval_accuracy": 0.5672820512820513,
"eval_loss": 1.7546838521957397,
"eval_runtime": 5.0186,
"eval_samples_per_second": 99.629,
"eval_steps_per_second": 12.553,
"step": 1125
},
{
"epoch": 6.0,
"eval_exact_match": 16.6,
"eval_f1": 25.054761904761914,
"step": 1125
}
],
"logging_steps": 100,
"max_steps": 9350,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.059723965517005e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|