File size: 1,675 Bytes
305ae86 358ef0f c5eba45 358ef0f 305ae86 c5eba45 305ae86 c5eba45 358ef0f 305ae86 c5eba45 305ae86 c5eba45 305ae86 c5eba45 305ae86 358ef0f 305ae86 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.020709911883307612,
"eval_steps": 10,
"global_step": 26,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0007965350724349081,
"eval_loss": NaN,
"eval_runtime": 257.2896,
"eval_samples_per_second": 32.873,
"eval_steps_per_second": 4.112,
"step": 1
},
{
"epoch": 0.007965350724349082,
"grad_norm": NaN,
"learning_rate": 9.330127018922194e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.007965350724349082,
"eval_loss": NaN,
"eval_runtime": 255.6607,
"eval_samples_per_second": 33.083,
"eval_steps_per_second": 4.138,
"step": 10
},
{
"epoch": 0.015930701448698164,
"grad_norm": NaN,
"learning_rate": 6.91341716182545e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.015930701448698164,
"eval_loss": NaN,
"eval_runtime": 255.6473,
"eval_samples_per_second": 33.085,
"eval_steps_per_second": 4.139,
"step": 20
}
],
"logging_steps": 10,
"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": 2.169555349458125e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|