File size: 3,689 Bytes
5ed1794 bb73706 5ed1794 bb73706 5ed1794 bb73706 5ed1794 bb73706 5ed1794 bb73706 5ed1794 e884d5e 5ed1794 bb73706 5ed1794 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.1784121320249777,
"eval_steps": 10,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003568242640499554,
"eval_loss": 7.846585750579834,
"eval_runtime": 58.1489,
"eval_samples_per_second": 2.029,
"eval_steps_per_second": 1.015,
"step": 1
},
{
"epoch": 0.01784121320249777,
"grad_norm": 41.419822692871094,
"learning_rate": 5e-05,
"loss": 30.7878,
"step": 5
},
{
"epoch": 0.03568242640499554,
"grad_norm": 59.32698059082031,
"learning_rate": 0.0001,
"loss": 27.0405,
"step": 10
},
{
"epoch": 0.03568242640499554,
"eval_loss": 3.822364568710327,
"eval_runtime": 56.4726,
"eval_samples_per_second": 2.09,
"eval_steps_per_second": 1.045,
"step": 10
},
{
"epoch": 0.05352363960749331,
"grad_norm": 22.128131866455078,
"learning_rate": 9.619397662556435e-05,
"loss": 9.0197,
"step": 15
},
{
"epoch": 0.07136485280999108,
"grad_norm": 18.33565902709961,
"learning_rate": 8.535533905932738e-05,
"loss": 3.4617,
"step": 20
},
{
"epoch": 0.07136485280999108,
"eval_loss": 0.7452569603919983,
"eval_runtime": 79.1279,
"eval_samples_per_second": 1.491,
"eval_steps_per_second": 0.746,
"step": 20
},
{
"epoch": 0.08920606601248884,
"grad_norm": 5.567965030670166,
"learning_rate": 6.91341716182545e-05,
"loss": 2.9074,
"step": 25
},
{
"epoch": 0.10704727921498662,
"grad_norm": 13.315966606140137,
"learning_rate": 5e-05,
"loss": 2.7719,
"step": 30
},
{
"epoch": 0.10704727921498662,
"eval_loss": 0.7875707745552063,
"eval_runtime": 25.4368,
"eval_samples_per_second": 4.639,
"eval_steps_per_second": 2.319,
"step": 30
},
{
"epoch": 0.12488849241748438,
"grad_norm": 6.743807792663574,
"learning_rate": 3.086582838174551e-05,
"loss": 2.9019,
"step": 35
},
{
"epoch": 0.14272970561998216,
"grad_norm": 8.351219177246094,
"learning_rate": 1.4644660940672627e-05,
"loss": 2.6862,
"step": 40
},
{
"epoch": 0.14272970561998216,
"eval_loss": 0.709270715713501,
"eval_runtime": 25.8895,
"eval_samples_per_second": 4.558,
"eval_steps_per_second": 2.279,
"step": 40
},
{
"epoch": 0.16057091882247992,
"grad_norm": 14.457117080688477,
"learning_rate": 3.8060233744356633e-06,
"loss": 2.9802,
"step": 45
},
{
"epoch": 0.1784121320249777,
"grad_norm": 9.18240737915039,
"learning_rate": 0.0,
"loss": 2.8617,
"step": 50
},
{
"epoch": 0.1784121320249777,
"eval_loss": 0.7003238201141357,
"eval_runtime": 7.8711,
"eval_samples_per_second": 14.992,
"eval_steps_per_second": 7.496,
"step": 50
}
],
"logging_steps": 5,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 13,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8143665679564800.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|