File size: 4,875 Bytes
7d40537 |
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 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 1000,
"global_step": 9466,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00021128248468201986,
"grad_norm": 7.594412803649902,
"learning_rate": 0.0,
"loss": 2.6278,
"step": 1
},
{
"epoch": 0.21128248468201985,
"grad_norm": 6.050217628479004,
"learning_rate": 8.441064638783271e-06,
"loss": 2.7281,
"step": 1000
},
{
"epoch": 0.21128248468201985,
"eval_cosine_accuracy": 0.9345883131027222,
"eval_loss": 0.6125919222831726,
"eval_runtime": 34.2392,
"eval_samples_per_second": 277.723,
"eval_steps_per_second": 2.19,
"step": 1000
},
{
"epoch": 0.4225649693640397,
"grad_norm": 6.340444087982178,
"learning_rate": 1.6890578791719477e-05,
"loss": 1.999,
"step": 2000
},
{
"epoch": 0.4225649693640397,
"eval_cosine_accuracy": 0.9388999938964844,
"eval_loss": 0.5676162838935852,
"eval_runtime": 34.1182,
"eval_samples_per_second": 278.708,
"eval_steps_per_second": 2.198,
"step": 2000
},
{
"epoch": 0.6338474540460596,
"grad_norm": 8.218648910522461,
"learning_rate": 1.940745609916424e-05,
"loss": 1.5073,
"step": 3000
},
{
"epoch": 0.6338474540460596,
"eval_cosine_accuracy": 0.9328005313873291,
"eval_loss": 0.5519113540649414,
"eval_runtime": 34.1651,
"eval_samples_per_second": 278.325,
"eval_steps_per_second": 2.195,
"step": 3000
},
{
"epoch": 0.8451299387280794,
"grad_norm": 9.030098915100098,
"learning_rate": 1.846933984411682e-05,
"loss": 0.9687,
"step": 4000
},
{
"epoch": 0.8451299387280794,
"eval_cosine_accuracy": 0.9312230348587036,
"eval_loss": 0.5424668788909912,
"eval_runtime": 34.165,
"eval_samples_per_second": 278.326,
"eval_steps_per_second": 2.195,
"step": 4000
},
{
"epoch": 1.0564124234100993,
"grad_norm": 5.368319511413574,
"learning_rate": 1.7530284533759038e-05,
"loss": 0.9492,
"step": 5000
},
{
"epoch": 1.0564124234100993,
"eval_cosine_accuracy": 0.944158136844635,
"eval_loss": 0.5103689432144165,
"eval_runtime": 33.9293,
"eval_samples_per_second": 280.259,
"eval_steps_per_second": 2.21,
"step": 5000
},
{
"epoch": 1.2676949080921192,
"grad_norm": 6.123900890350342,
"learning_rate": 1.6592168278711617e-05,
"loss": 1.3563,
"step": 6000
},
{
"epoch": 1.2676949080921192,
"eval_cosine_accuracy": 0.9431065320968628,
"eval_loss": 0.516655445098877,
"eval_runtime": 34.739,
"eval_samples_per_second": 273.727,
"eval_steps_per_second": 2.159,
"step": 6000
},
{
"epoch": 1.478977392774139,
"grad_norm": 5.849966526031494,
"learning_rate": 1.5653112968353836e-05,
"loss": 1.253,
"step": 7000
},
{
"epoch": 1.478977392774139,
"eval_cosine_accuracy": 0.9433168768882751,
"eval_loss": 0.5244542956352234,
"eval_runtime": 33.8791,
"eval_samples_per_second": 280.674,
"eval_steps_per_second": 2.214,
"step": 7000
},
{
"epoch": 1.690259877456159,
"grad_norm": 8.606755256652832,
"learning_rate": 1.4714057657996057e-05,
"loss": 0.9613,
"step": 8000
},
{
"epoch": 1.690259877456159,
"eval_cosine_accuracy": 0.9373225569725037,
"eval_loss": 0.5143805742263794,
"eval_runtime": 34.3167,
"eval_samples_per_second": 277.096,
"eval_steps_per_second": 2.186,
"step": 8000
},
{
"epoch": 1.9015423621381786,
"grad_norm": 7.499396800994873,
"learning_rate": 1.3775002347638278e-05,
"loss": 0.6725,
"step": 9000
},
{
"epoch": 1.9015423621381786,
"eval_cosine_accuracy": 0.9387948513031006,
"eval_loss": 0.5081201791763306,
"eval_runtime": 33.8383,
"eval_samples_per_second": 281.013,
"eval_steps_per_second": 2.216,
"step": 9000
}
],
"logging_steps": 1000,
"max_steps": 23665,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 0.0,
"train_batch_size": 128,
"trial_name": null,
"trial_params": null
}
|