|
{ |
|
"best_metric": 3.883234739303589, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.1443001443001443, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.005772005772005772, |
|
"grad_norm": 9.749709129333496, |
|
"learning_rate": 0.0001, |
|
"loss": 3.7589, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.005772005772005772, |
|
"eval_loss": 10.803024291992188, |
|
"eval_runtime": 29.4154, |
|
"eval_samples_per_second": 2.482, |
|
"eval_steps_per_second": 1.258, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.011544011544011544, |
|
"grad_norm": 7.1808881759643555, |
|
"learning_rate": 0.0002, |
|
"loss": 5.5834, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.017316017316017316, |
|
"grad_norm": 7.575276851654053, |
|
"learning_rate": 0.00019978589232386035, |
|
"loss": 5.2038, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.023088023088023088, |
|
"grad_norm": 5.419090747833252, |
|
"learning_rate": 0.00019914448613738106, |
|
"loss": 5.0399, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.02886002886002886, |
|
"grad_norm": 8.910318374633789, |
|
"learning_rate": 0.00019807852804032305, |
|
"loss": 3.9669, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.03463203463203463, |
|
"grad_norm": 45.46010971069336, |
|
"learning_rate": 0.00019659258262890683, |
|
"loss": 4.2862, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.04040404040404041, |
|
"grad_norm": 43.968482971191406, |
|
"learning_rate": 0.0001946930129495106, |
|
"loss": 4.4392, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.046176046176046176, |
|
"grad_norm": 9.73154354095459, |
|
"learning_rate": 0.0001923879532511287, |
|
"loss": 3.3899, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.05194805194805195, |
|
"grad_norm": 5.469523906707764, |
|
"learning_rate": 0.00018968727415326884, |
|
"loss": 3.064, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.05772005772005772, |
|
"grad_norm": 6.917726516723633, |
|
"learning_rate": 0.00018660254037844388, |
|
"loss": 3.4218, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.06349206349206349, |
|
"grad_norm": 5.250333309173584, |
|
"learning_rate": 0.00018314696123025454, |
|
"loss": 2.7711, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.06926406926406926, |
|
"grad_norm": 5.692388534545898, |
|
"learning_rate": 0.00017933533402912354, |
|
"loss": 2.8573, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.07503607503607504, |
|
"grad_norm": 5.600759983062744, |
|
"learning_rate": 0.00017518398074789775, |
|
"loss": 3.238, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.08080808080808081, |
|
"grad_norm": 8.384806632995605, |
|
"learning_rate": 0.00017071067811865476, |
|
"loss": 2.9453, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.08658008658008658, |
|
"grad_norm": 5.953359127044678, |
|
"learning_rate": 0.00016593458151000688, |
|
"loss": 2.8733, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.09235209235209235, |
|
"grad_norm": 5.461154937744141, |
|
"learning_rate": 0.00016087614290087208, |
|
"loss": 2.4783, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.09812409812409813, |
|
"grad_norm": 5.699024677276611, |
|
"learning_rate": 0.00015555702330196023, |
|
"loss": 2.7727, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.1038961038961039, |
|
"grad_norm": 5.159974098205566, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 2.9109, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.10966810966810966, |
|
"grad_norm": 4.561604022979736, |
|
"learning_rate": 0.00014422886902190014, |
|
"loss": 3.1012, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.11544011544011544, |
|
"grad_norm": 5.195240497589111, |
|
"learning_rate": 0.000138268343236509, |
|
"loss": 2.935, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.12121212121212122, |
|
"grad_norm": 4.813465595245361, |
|
"learning_rate": 0.00013214394653031616, |
|
"loss": 3.4641, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.12698412698412698, |
|
"grad_norm": 5.874507904052734, |
|
"learning_rate": 0.00012588190451025207, |
|
"loss": 3.3369, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.13275613275613277, |
|
"grad_norm": 4.917274475097656, |
|
"learning_rate": 0.00011950903220161285, |
|
"loss": 3.3583, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.13852813852813853, |
|
"grad_norm": 3.70969820022583, |
|
"learning_rate": 0.00011305261922200519, |
|
"loss": 2.5707, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.1443001443001443, |
|
"grad_norm": 6.91110372543335, |
|
"learning_rate": 0.00010654031292301432, |
|
"loss": 3.474, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.1443001443001443, |
|
"eval_loss": 3.883234739303589, |
|
"eval_runtime": 29.8984, |
|
"eval_samples_per_second": 2.442, |
|
"eval_steps_per_second": 1.238, |
|
"step": 25 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 1, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.11806271012864e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|