File size: 2,960 Bytes
8859889 59c831b 8859889 59c831b 8859889 59c831b 8859889 59c831b 8859889 59c831b 8859889 59c831b 8859889 59c831b 8859889 59c831b 8859889 59c831b 8859889 59c831b 8859889 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500.0,
"global_step": 5380,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 10.252312660217285,
"learning_rate": 1.8008368200836822e-05,
"loss": 1.484,
"step": 1076
},
{
"epoch": 1.0,
"eval_f1": 0.7462822532277763,
"eval_loss": 0.8799635171890259,
"eval_runtime": 683.415,
"eval_samples_per_second": 12.591,
"eval_steps_per_second": 0.394,
"step": 1076
},
{
"epoch": 2.0,
"grad_norm": 11.723691940307617,
"learning_rate": 1.3506276150627616e-05,
"loss": 0.7957,
"step": 2152
},
{
"epoch": 2.0,
"eval_f1": 0.773518075222442,
"eval_loss": 0.7795748710632324,
"eval_runtime": 678.1252,
"eval_samples_per_second": 12.689,
"eval_steps_per_second": 0.397,
"step": 2152
},
{
"epoch": 3.0,
"grad_norm": 9.515564918518066,
"learning_rate": 9.004184100418411e-06,
"loss": 0.612,
"step": 3228
},
{
"epoch": 3.0,
"eval_f1": 0.790370571641359,
"eval_loss": 0.7352398037910461,
"eval_runtime": 672.8155,
"eval_samples_per_second": 12.79,
"eval_steps_per_second": 0.4,
"step": 3228
},
{
"epoch": 4.0,
"grad_norm": 22.87370491027832,
"learning_rate": 4.5020920502092055e-06,
"loss": 0.4784,
"step": 4304
},
{
"epoch": 4.0,
"eval_f1": 0.7948184348707309,
"eval_loss": 0.7243198156356812,
"eval_runtime": 678.247,
"eval_samples_per_second": 12.687,
"eval_steps_per_second": 0.397,
"step": 4304
},
{
"epoch": 5.0,
"grad_norm": 5.2252960205078125,
"learning_rate": 0.0,
"loss": 0.3959,
"step": 5380
},
{
"epoch": 5.0,
"eval_f1": 0.7954325175529264,
"eval_loss": 0.734076738357544,
"eval_runtime": 676.4727,
"eval_samples_per_second": 12.72,
"eval_steps_per_second": 0.398,
"step": 5380
},
{
"epoch": 5.0,
"step": 5380,
"total_flos": 2.28033311981568e+16,
"train_loss": 0.7531972722049982,
"train_runtime": 49725.5381,
"train_samples_per_second": 3.461,
"train_steps_per_second": 0.108
}
],
"logging_steps": 500,
"max_steps": 5380,
"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": true
},
"attributes": {}
}
},
"total_flos": 2.28033311981568e+16,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|