|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0010976044782262712, |
|
"eval_steps": 3, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00010976044782262712, |
|
"grad_norm": 3.4242184162139893, |
|
"learning_rate": 2e-05, |
|
"loss": 44.4846, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00010976044782262712, |
|
"eval_loss": 11.109243392944336, |
|
"eval_runtime": 24.632, |
|
"eval_samples_per_second": 622.971, |
|
"eval_steps_per_second": 77.907, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00021952089564525424, |
|
"grad_norm": 3.2589004039764404, |
|
"learning_rate": 4e-05, |
|
"loss": 44.4219, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00032928134346788137, |
|
"grad_norm": 3.1269261837005615, |
|
"learning_rate": 6e-05, |
|
"loss": 44.4614, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00032928134346788137, |
|
"eval_loss": 11.103837966918945, |
|
"eval_runtime": 24.0044, |
|
"eval_samples_per_second": 639.258, |
|
"eval_steps_per_second": 79.944, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00043904179129050847, |
|
"grad_norm": 3.233558177947998, |
|
"learning_rate": 8e-05, |
|
"loss": 44.4412, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0005488022391131356, |
|
"grad_norm": 3.275294303894043, |
|
"learning_rate": 0.0001, |
|
"loss": 44.4168, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0006585626869357627, |
|
"grad_norm": 3.2577297687530518, |
|
"learning_rate": 0.00012, |
|
"loss": 44.4082, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0006585626869357627, |
|
"eval_loss": 11.081639289855957, |
|
"eval_runtime": 24.0515, |
|
"eval_samples_per_second": 638.006, |
|
"eval_steps_per_second": 79.787, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0007683231347583898, |
|
"grad_norm": 3.174706220626831, |
|
"learning_rate": 0.00014, |
|
"loss": 44.3363, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.0008780835825810169, |
|
"grad_norm": 3.3509459495544434, |
|
"learning_rate": 0.00016, |
|
"loss": 44.2819, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.000987844030403644, |
|
"grad_norm": 3.4119491577148438, |
|
"learning_rate": 0.00018, |
|
"loss": 44.2531, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.000987844030403644, |
|
"eval_loss": 11.040336608886719, |
|
"eval_runtime": 24.0508, |
|
"eval_samples_per_second": 638.024, |
|
"eval_steps_per_second": 79.789, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0010976044782262712, |
|
"grad_norm": 3.691930055618286, |
|
"learning_rate": 0.0002, |
|
"loss": 44.1788, |
|
"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": 3327928565760.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|