File size: 2,786 Bytes
b25c558 1cc26ec be84b82 1cc26ec b25c558 be84b82 b25c558 be84b82 466b171 1cc26ec b25c558 be84b82 b25c558 be84b82 b25c558 be84b82 b25c558 1cc26ec b25c558 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.06851119894598155,
"eval_steps": 10,
"global_step": 39,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001756697408871322,
"eval_loss": 11.082844734191895,
"eval_runtime": 2.2192,
"eval_samples_per_second": 108.149,
"eval_steps_per_second": 54.075,
"step": 1
},
{
"epoch": 0.00878348704435661,
"grad_norm": 0.4254762828350067,
"learning_rate": 5e-05,
"loss": 44.3315,
"step": 5
},
{
"epoch": 0.01756697408871322,
"grad_norm": 0.4281250834465027,
"learning_rate": 0.0001,
"loss": 44.3285,
"step": 10
},
{
"epoch": 0.01756697408871322,
"eval_loss": 11.08116626739502,
"eval_runtime": 1.4271,
"eval_samples_per_second": 168.168,
"eval_steps_per_second": 84.084,
"step": 10
},
{
"epoch": 0.026350461133069828,
"grad_norm": 0.4372434914112091,
"learning_rate": 9.619397662556435e-05,
"loss": 44.3201,
"step": 15
},
{
"epoch": 0.03513394817742644,
"grad_norm": 0.4354489743709564,
"learning_rate": 8.535533905932738e-05,
"loss": 44.3119,
"step": 20
},
{
"epoch": 0.03513394817742644,
"eval_loss": 11.077805519104004,
"eval_runtime": 1.4987,
"eval_samples_per_second": 160.137,
"eval_steps_per_second": 80.068,
"step": 20
},
{
"epoch": 0.04391743522178305,
"grad_norm": 0.45061734318733215,
"learning_rate": 6.91341716182545e-05,
"loss": 44.3135,
"step": 25
},
{
"epoch": 0.052700922266139656,
"grad_norm": 0.4921723008155823,
"learning_rate": 5e-05,
"loss": 44.2984,
"step": 30
},
{
"epoch": 0.052700922266139656,
"eval_loss": 11.075677871704102,
"eval_runtime": 1.5009,
"eval_samples_per_second": 159.903,
"eval_steps_per_second": 79.951,
"step": 30
},
{
"epoch": 0.061484409310496264,
"grad_norm": 0.43915820121765137,
"learning_rate": 3.086582838174551e-05,
"loss": 44.3019,
"step": 35
}
],
"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": false
},
"attributes": {}
}
},
"total_flos": 34927411200.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|