|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0005283736658564937, |
|
"eval_steps": 3, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 5.283736658564937e-05, |
|
"grad_norm": 15.33159351348877, |
|
"learning_rate": 2e-05, |
|
"loss": 7.6823, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 5.283736658564937e-05, |
|
"eval_loss": 7.635408878326416, |
|
"eval_runtime": 151.6456, |
|
"eval_samples_per_second": 52.55, |
|
"eval_steps_per_second": 26.278, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00010567473317129874, |
|
"grad_norm": 15.896822929382324, |
|
"learning_rate": 4e-05, |
|
"loss": 7.3373, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00015851209975694812, |
|
"grad_norm": 15.872105598449707, |
|
"learning_rate": 6e-05, |
|
"loss": 7.3625, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00015851209975694812, |
|
"eval_loss": 7.4907331466674805, |
|
"eval_runtime": 150.6864, |
|
"eval_samples_per_second": 52.885, |
|
"eval_steps_per_second": 26.446, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00021134946634259749, |
|
"grad_norm": 18.81482696533203, |
|
"learning_rate": 8e-05, |
|
"loss": 7.4719, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.00026418683292824685, |
|
"grad_norm": 14.488409042358398, |
|
"learning_rate": 0.0001, |
|
"loss": 7.0073, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.00031702419951389624, |
|
"grad_norm": 16.42768096923828, |
|
"learning_rate": 0.00012, |
|
"loss": 6.3756, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.00031702419951389624, |
|
"eval_loss": 5.868957996368408, |
|
"eval_runtime": 151.4984, |
|
"eval_samples_per_second": 52.601, |
|
"eval_steps_per_second": 26.304, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0003698615660995456, |
|
"grad_norm": 15.76357650756836, |
|
"learning_rate": 0.00014, |
|
"loss": 6.056, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.00042269893268519497, |
|
"grad_norm": 13.875348091125488, |
|
"learning_rate": 0.00016, |
|
"loss": 4.9629, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.00047553629927084436, |
|
"grad_norm": 15.756418228149414, |
|
"learning_rate": 0.00018, |
|
"loss": 3.7258, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.00047553629927084436, |
|
"eval_loss": 3.4606802463531494, |
|
"eval_runtime": 151.5311, |
|
"eval_samples_per_second": 52.59, |
|
"eval_steps_per_second": 26.298, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0005283736658564937, |
|
"grad_norm": 16.484500885009766, |
|
"learning_rate": 0.0002, |
|
"loss": 3.0488, |
|
"step": 10 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 89038163804160.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|