|
{ |
|
"best_metric": 8.5859375, |
|
"best_model_checkpoint": "model_bloomz_7b_fa_v2/checkpoint-24000", |
|
"epoch": 1.25, |
|
"eval_steps": 6000, |
|
"global_step": 30000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.95e-05, |
|
"loss": 8.659, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"eval_loss": 8.6171875, |
|
"eval_runtime": 6400.1737, |
|
"eval_samples_per_second": 0.937, |
|
"eval_steps_per_second": 0.937, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.9e-05, |
|
"loss": 8.5668, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"eval_loss": 8.59375, |
|
"eval_runtime": 4301.219, |
|
"eval_samples_per_second": 1.395, |
|
"eval_steps_per_second": 1.395, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.8500000000000002e-05, |
|
"loss": 8.6004, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"eval_loss": 8.59375, |
|
"eval_runtime": 4302.1725, |
|
"eval_samples_per_second": 1.395, |
|
"eval_steps_per_second": 1.395, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.8e-05, |
|
"loss": 8.5774, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 8.5859375, |
|
"eval_runtime": 4302.2132, |
|
"eval_samples_per_second": 1.395, |
|
"eval_steps_per_second": 1.395, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.7500000000000002e-05, |
|
"loss": 8.559, |
|
"step": 30000 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"eval_loss": 8.5859375, |
|
"eval_runtime": 6350.3496, |
|
"eval_samples_per_second": 0.945, |
|
"eval_steps_per_second": 0.945, |
|
"step": 30000 |
|
} |
|
], |
|
"logging_steps": 6000, |
|
"max_steps": 240000, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 6000, |
|
"total_flos": 2.22710596632576e+18, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|