File size: 3,134 Bytes
c2819f4 1fcdc5c c2819f4 1fcdc5c c2819f4 6f8c61e c2819f4 6f8c61e c2819f4 6f8c61e c2819f4 6f8c61e c2819f4 6f8c61e c2819f4 6f8c61e c2819f4 6f8c61e c2819f4 7a5fd47 6f8c61e 7a5fd47 6f8c61e 7a5fd47 6f8c61e 7a5fd47 6f8c61e 7a5fd47 6f8c61e 7a5fd47 6f8c61e 7a5fd47 6f8c61e 7a5fd47 f7dfe7d 6f8c61e f7dfe7d 6f8c61e f7dfe7d 6f8c61e f7dfe7d 6f8c61e f7dfe7d 6f8c61e f7dfe7d 1fcdc5c c2819f4 1fcdc5c c2819f4 1fcdc5c c2819f4 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.008442380751371888,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008442380751371887,
"grad_norm": NaN,
"learning_rate": 0.0,
"loss": 6.2949,
"step": 1
},
{
"epoch": 0.0008442380751371887,
"eval_loss": 7.167040824890137,
"eval_runtime": 33.9503,
"eval_samples_per_second": 14.698,
"eval_steps_per_second": 7.364,
"step": 1
},
{
"epoch": 0.0016884761502743773,
"grad_norm": NaN,
"learning_rate": 0.0,
"loss": 7.5932,
"step": 2
},
{
"epoch": 0.002532714225411566,
"grad_norm": 4.345782279968262,
"learning_rate": 2e-05,
"loss": 6.3083,
"step": 3
},
{
"epoch": 0.002532714225411566,
"eval_loss": 7.167040824890137,
"eval_runtime": 33.7762,
"eval_samples_per_second": 14.774,
"eval_steps_per_second": 7.402,
"step": 3
},
{
"epoch": 0.0033769523005487546,
"grad_norm": 4.228282451629639,
"learning_rate": 4e-05,
"loss": 6.5425,
"step": 4
},
{
"epoch": 0.004221190375685944,
"grad_norm": 5.7301530838012695,
"learning_rate": 6e-05,
"loss": 7.4106,
"step": 5
},
{
"epoch": 0.005065428450823132,
"grad_norm": 4.481907367706299,
"learning_rate": 8e-05,
"loss": 6.8524,
"step": 6
},
{
"epoch": 0.005065428450823132,
"eval_loss": 6.865447521209717,
"eval_runtime": 33.823,
"eval_samples_per_second": 14.753,
"eval_steps_per_second": 7.391,
"step": 6
},
{
"epoch": 0.0059096665259603205,
"grad_norm": 3.831299066543579,
"learning_rate": 0.0001,
"loss": 5.5514,
"step": 7
},
{
"epoch": 0.006753904601097509,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 6.6829,
"step": 8
},
{
"epoch": 0.007598142676234698,
"grad_norm": 5.293268203735352,
"learning_rate": 0.00012,
"loss": 6.0991,
"step": 9
},
{
"epoch": 0.007598142676234698,
"eval_loss": 6.2211456298828125,
"eval_runtime": 33.8008,
"eval_samples_per_second": 14.763,
"eval_steps_per_second": 7.396,
"step": 9
},
{
"epoch": 0.008442380751371888,
"grad_norm": 4.914198875427246,
"learning_rate": 0.00014,
"loss": 5.7317,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3699128496291840.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|