|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 290, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.724137931034483e-06, |
|
"loss": 13.6499, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 3.448275862068966e-06, |
|
"loss": 12.8629, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.999083215558211e-06, |
|
"loss": 10.3507, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 4.88988035667903e-06, |
|
"loss": 8.248, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 4.606455184041623e-06, |
|
"loss": 7.2653, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 4.169469396971739e-06, |
|
"loss": 7.0064, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 3.6107792658847597e-06, |
|
"loss": 6.6082, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 2.971113309695796e-06, |
|
"loss": 6.5262, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 2.2971031861814225e-06, |
|
"loss": 6.1328, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.6378842434300746e-06, |
|
"loss": 6.1506, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 1.041513552231265e-06, |
|
"loss": 5.8993, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 5.51466544896021e-07, |
|
"loss": 6.1471, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 2.0346765559094566e-07, |
|
"loss": 6.2593, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 2.2886008552983064e-08, |
|
"loss": 6.0709, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 290, |
|
"total_flos": 8536543131303936.0, |
|
"train_loss": 7.7484286078091325, |
|
"train_runtime": 226.3779, |
|
"train_samples_per_second": 2.558, |
|
"train_steps_per_second": 1.281 |
|
} |
|
], |
|
"logging_steps": 20, |
|
"max_steps": 290, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"total_flos": 8536543131303936.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|