| { | |
| "best_metric": 3.88244366645813, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.0003900517306107723, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.9502586530538612e-05, | |
| "eval_loss": 4.488034725189209, | |
| "eval_runtime": 736.639, | |
| "eval_samples_per_second": 29.309, | |
| "eval_steps_per_second": 14.654, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.850775959161584e-05, | |
| "grad_norm": 11.912729263305664, | |
| "learning_rate": 6e-05, | |
| "loss": 19.6102, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.751293265269307e-05, | |
| "eval_loss": 4.3603668212890625, | |
| "eval_runtime": 740.5036, | |
| "eval_samples_per_second": 29.156, | |
| "eval_steps_per_second": 14.578, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00011701551918323167, | |
| "grad_norm": 8.767396926879883, | |
| "learning_rate": 0.00012, | |
| "loss": 16.5732, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00017552327877484752, | |
| "grad_norm": 8.869946479797363, | |
| "learning_rate": 0.00018, | |
| "loss": 17.0351, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00019502586530538614, | |
| "eval_loss": 4.058638095855713, | |
| "eval_runtime": 736.3032, | |
| "eval_samples_per_second": 29.322, | |
| "eval_steps_per_second": 14.661, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00023403103836646335, | |
| "grad_norm": 9.496614456176758, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 16.2777, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002925387979580792, | |
| "grad_norm": 9.867759704589844, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 15.7824, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002925387979580792, | |
| "eval_loss": 3.9371206760406494, | |
| "eval_runtime": 734.2275, | |
| "eval_samples_per_second": 29.405, | |
| "eval_steps_per_second": 14.703, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00035104655754969504, | |
| "grad_norm": 9.290112495422363, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 15.3766, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0003900517306107723, | |
| "eval_loss": 3.88244366645813, | |
| "eval_runtime": 735.9882, | |
| "eval_samples_per_second": 29.335, | |
| "eval_steps_per_second": 14.667, | |
| "step": 20 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 303370988421120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |