| { |
| "best_metric": 11.929627418518066, |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", |
| "epoch": 0.030503304524656837, |
| "eval_steps": 5, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0010167768174885613, |
| "eval_loss": 11.931282997131348, |
| "eval_runtime": 12.1282, |
| "eval_samples_per_second": 34.218, |
| "eval_steps_per_second": 17.15, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.003050330452465684, |
| "grad_norm": 0.034024111926555634, |
| "learning_rate": 6e-05, |
| "loss": 11.9303, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.005083884087442806, |
| "eval_loss": 11.931171417236328, |
| "eval_runtime": 12.2651, |
| "eval_samples_per_second": 33.836, |
| "eval_steps_per_second": 16.959, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.006100660904931368, |
| "grad_norm": 0.03859293833374977, |
| "learning_rate": 0.00012, |
| "loss": 11.9311, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.009150991357397052, |
| "grad_norm": 0.028728436678647995, |
| "learning_rate": 0.00018, |
| "loss": 11.9335, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.010167768174885612, |
| "eval_loss": 11.93080997467041, |
| "eval_runtime": 12.0381, |
| "eval_samples_per_second": 34.474, |
| "eval_steps_per_second": 17.278, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.012201321809862735, |
| "grad_norm": 0.03001631423830986, |
| "learning_rate": 0.00019510565162951537, |
| "loss": 11.9301, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.015251652262328419, |
| "grad_norm": 0.05156728997826576, |
| "learning_rate": 0.00017071067811865476, |
| "loss": 11.9283, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.015251652262328419, |
| "eval_loss": 11.930292129516602, |
| "eval_runtime": 12.0367, |
| "eval_samples_per_second": 34.478, |
| "eval_steps_per_second": 17.28, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.018301982714794104, |
| "grad_norm": 0.04535188153386116, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 11.9301, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.020335536349771224, |
| "eval_loss": 11.929884910583496, |
| "eval_runtime": 12.3097, |
| "eval_samples_per_second": 33.713, |
| "eval_steps_per_second": 16.897, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.021352313167259787, |
| "grad_norm": 0.03429163247346878, |
| "learning_rate": 8.435655349597689e-05, |
| "loss": 11.9307, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.02440264361972547, |
| "grad_norm": 0.02444632537662983, |
| "learning_rate": 4.12214747707527e-05, |
| "loss": 11.9311, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.02541942043721403, |
| "eval_loss": 11.929669380187988, |
| "eval_runtime": 12.3353, |
| "eval_samples_per_second": 33.643, |
| "eval_steps_per_second": 16.862, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.027452974072191154, |
| "grad_norm": 0.03801164776086807, |
| "learning_rate": 1.0899347581163221e-05, |
| "loss": 11.9294, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.030503304524656837, |
| "grad_norm": 0.027243835851550102, |
| "learning_rate": 0.0, |
| "loss": 11.9301, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.030503304524656837, |
| "eval_loss": 11.929627418518066, |
| "eval_runtime": 12.1453, |
| "eval_samples_per_second": 34.17, |
| "eval_steps_per_second": 17.126, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 10, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 16956751872.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
