| { | |
| "best_metric": 1.351155400276184, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.005567928730512249, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001855976243504083, | |
| "eval_loss": 1.4602763652801514, | |
| "eval_runtime": 374.0894, | |
| "eval_samples_per_second": 6.065, | |
| "eval_steps_per_second": 3.034, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005567928730512249, | |
| "grad_norm": 0.14660656452178955, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0201, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009279881217520415, | |
| "eval_loss": 1.4547374248504639, | |
| "eval_runtime": 376.6111, | |
| "eval_samples_per_second": 6.025, | |
| "eval_steps_per_second": 3.014, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011135857461024498, | |
| "grad_norm": 0.15634022653102875, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 1.2386, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016703786191536749, | |
| "grad_norm": 0.22342237830162048, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 1.4359, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001855976243504083, | |
| "eval_loss": 1.416305422782898, | |
| "eval_runtime": 376.6421, | |
| "eval_samples_per_second": 6.024, | |
| "eval_steps_per_second": 3.013, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022271714922048997, | |
| "grad_norm": 0.3038925230503082, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.1451, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0027839643652561247, | |
| "grad_norm": 0.3491500914096832, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.2388, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027839643652561247, | |
| "eval_loss": 1.3749524354934692, | |
| "eval_runtime": 376.5474, | |
| "eval_samples_per_second": 6.026, | |
| "eval_steps_per_second": 3.014, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033407572383073497, | |
| "grad_norm": 0.28735220432281494, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 1.2865, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003711952487008166, | |
| "eval_loss": 1.35789155960083, | |
| "eval_runtime": 376.4943, | |
| "eval_samples_per_second": 6.027, | |
| "eval_steps_per_second": 3.015, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0038975501113585748, | |
| "grad_norm": 0.41736310720443726, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 1.0301, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004454342984409799, | |
| "grad_norm": 0.3389260768890381, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 1.1751, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0046399406087602076, | |
| "eval_loss": 1.3520481586456299, | |
| "eval_runtime": 376.6032, | |
| "eval_samples_per_second": 6.025, | |
| "eval_steps_per_second": 3.014, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005011135857461025, | |
| "grad_norm": 0.27419382333755493, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 1.2334, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005567928730512249, | |
| "grad_norm": 0.2178027182817459, | |
| "learning_rate": 0.0, | |
| "loss": 0.9741, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005567928730512249, | |
| "eval_loss": 1.351155400276184, | |
| "eval_runtime": 376.4603, | |
| "eval_samples_per_second": 6.027, | |
| "eval_steps_per_second": 3.015, | |
| "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": 1.4941952069861376e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |