| { | |
| "best_metric": 4.549448013305664, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.00048110461619879245, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6036820539959746e-05, | |
| "eval_loss": 5.815370559692383, | |
| "eval_runtime": 893.8373, | |
| "eval_samples_per_second": 29.374, | |
| "eval_steps_per_second": 14.687, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.811046161987924e-05, | |
| "grad_norm": 13.024637222290039, | |
| "learning_rate": 6e-05, | |
| "loss": 23.9765, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.018410269979874e-05, | |
| "eval_loss": 5.52920389175415, | |
| "eval_runtime": 897.299, | |
| "eval_samples_per_second": 29.261, | |
| "eval_steps_per_second": 14.631, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 9.622092323975848e-05, | |
| "grad_norm": 11.284300804138184, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 22.9837, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014433138485963774, | |
| "grad_norm": 10.9056396484375, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 20.9837, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00016036820539959748, | |
| "eval_loss": 4.929401397705078, | |
| "eval_runtime": 894.1386, | |
| "eval_samples_per_second": 29.365, | |
| "eval_steps_per_second": 14.682, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00019244184647951697, | |
| "grad_norm": 8.726426124572754, | |
| "learning_rate": 8.18711994874345e-05, | |
| "loss": 19.5447, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00024055230809939623, | |
| "grad_norm": 9.420560836791992, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 20.2183, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00024055230809939623, | |
| "eval_loss": 4.678121566772461, | |
| "eval_runtime": 890.1762, | |
| "eval_samples_per_second": 29.495, | |
| "eval_steps_per_second": 14.748, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002886627697192755, | |
| "grad_norm": 7.593912124633789, | |
| "learning_rate": 4.6860474023534335e-05, | |
| "loss": 19.6809, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00032073641079919497, | |
| "eval_loss": 4.605849742889404, | |
| "eval_runtime": 894.7504, | |
| "eval_samples_per_second": 29.344, | |
| "eval_steps_per_second": 14.672, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003367732313391547, | |
| "grad_norm": 9.476841926574707, | |
| "learning_rate": 2.8711035421746367e-05, | |
| "loss": 18.1777, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00038488369295903394, | |
| "grad_norm": 12.611469268798828, | |
| "learning_rate": 1.3551568628929434e-05, | |
| "loss": 19.379, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0004009205134989937, | |
| "eval_loss": 4.5646562576293945, | |
| "eval_runtime": 893.5971, | |
| "eval_samples_per_second": 29.382, | |
| "eval_steps_per_second": 14.691, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00043299415457891317, | |
| "grad_norm": 8.356888771057129, | |
| "learning_rate": 3.511175705587433e-06, | |
| "loss": 18.3493, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00048110461619879245, | |
| "grad_norm": 9.053627014160156, | |
| "learning_rate": 0.0, | |
| "loss": 18.3131, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00048110461619879245, | |
| "eval_loss": 4.549448013305664, | |
| "eval_runtime": 891.0399, | |
| "eval_samples_per_second": 29.467, | |
| "eval_steps_per_second": 14.733, | |
| "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": 455056482631680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |