File size: 1,537 Bytes
3be58fd |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4667989263624694,
"eval_steps": 250,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2333994631812347,
"grad_norm": 0.8913317918777466,
"learning_rate": 8.959847237666421e-05,
"loss": 0.453,
"step": 250
},
{
"epoch": 0.2333994631812347,
"eval_loss": 0.23909452557563782,
"eval_runtime": 15.8602,
"eval_samples_per_second": 5.485,
"eval_steps_per_second": 5.485,
"step": 250
},
{
"epoch": 0.4667989263624694,
"grad_norm": 0.5381897687911987,
"learning_rate": 5.783666949486448e-05,
"loss": 0.1536,
"step": 500
},
{
"epoch": 0.4667989263624694,
"eval_loss": 0.13772033154964447,
"eval_runtime": 15.7869,
"eval_samples_per_second": 5.511,
"eval_steps_per_second": 5.511,
"step": 500
}
],
"logging_steps": 250,
"max_steps": 1071,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 250,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.159485237141504e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|