File size: 1,801 Bytes
08be33a |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.7745664739884393,
"eval_steps": 500,
"global_step": 15,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.9248554913294798,
"eval_loss": 0.948443591594696,
"eval_runtime": 17.2335,
"eval_samples_per_second": 8.472,
"eval_steps_per_second": 0.174,
"step": 5
},
{
"epoch": 1.8497109826589595,
"grad_norm": 2.0815279543947365,
"learning_rate": 5e-06,
"loss": 0.9953,
"step": 10
},
{
"epoch": 1.8497109826589595,
"eval_loss": 0.8798985481262207,
"eval_runtime": 17.4079,
"eval_samples_per_second": 8.387,
"eval_steps_per_second": 0.172,
"step": 10
},
{
"epoch": 2.7745664739884393,
"eval_loss": 0.8367447257041931,
"eval_runtime": 17.0323,
"eval_samples_per_second": 8.572,
"eval_steps_per_second": 0.176,
"step": 15
},
{
"epoch": 2.7745664739884393,
"step": 15,
"total_flos": 25073213767680.0,
"train_loss": 0.936284065246582,
"train_runtime": 4393.8745,
"train_samples_per_second": 1.887,
"train_steps_per_second": 0.003
}
],
"logging_steps": 10,
"max_steps": 15,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 25073213767680.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|