| { | |
| "best_metric": 1.4530510902404785, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.006438113632705618, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021460378775685392, | |
| "eval_loss": 3.0670204162597656, | |
| "eval_runtime": 316.2885, | |
| "eval_samples_per_second": 12.406, | |
| "eval_steps_per_second": 3.102, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006438113632705617, | |
| "grad_norm": 3.800321340560913, | |
| "learning_rate": 0.00012, | |
| "loss": 9.5117, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010730189387842695, | |
| "eval_loss": 2.6441357135772705, | |
| "eval_runtime": 312.2481, | |
| "eval_samples_per_second": 12.567, | |
| "eval_steps_per_second": 3.142, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012876227265411235, | |
| "grad_norm": 4.350091457366943, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 9.797, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001931434089811685, | |
| "grad_norm": 4.657054424285889, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 8.4985, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002146037877568539, | |
| "eval_loss": 1.8972209692001343, | |
| "eval_runtime": 314.6447, | |
| "eval_samples_per_second": 12.471, | |
| "eval_steps_per_second": 3.118, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002575245453082247, | |
| "grad_norm": 6.100785732269287, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 7.9055, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003219056816352809, | |
| "grad_norm": 7.180042266845703, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 7.0498, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003219056816352809, | |
| "eval_loss": 1.6312284469604492, | |
| "eval_runtime": 312.8834, | |
| "eval_samples_per_second": 12.541, | |
| "eval_steps_per_second": 3.135, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00386286817962337, | |
| "grad_norm": 6.62025260925293, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 6.4382, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004292075755137078, | |
| "eval_loss": 1.5036325454711914, | |
| "eval_runtime": 312.9013, | |
| "eval_samples_per_second": 12.541, | |
| "eval_steps_per_second": 3.135, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0045066795428939325, | |
| "grad_norm": 6.944516658782959, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 6.1814, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005150490906164494, | |
| "grad_norm": 6.075719356536865, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 5.829, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005365094693921347, | |
| "eval_loss": 1.4611380100250244, | |
| "eval_runtime": 312.8644, | |
| "eval_samples_per_second": 12.542, | |
| "eval_steps_per_second": 3.136, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005794302269435055, | |
| "grad_norm": 5.367476940155029, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 5.8356, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006438113632705618, | |
| "grad_norm": 6.34188985824585, | |
| "learning_rate": 0.0, | |
| "loss": 5.9808, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006438113632705618, | |
| "eval_loss": 1.4530510902404785, | |
| "eval_runtime": 313.1667, | |
| "eval_samples_per_second": 12.53, | |
| "eval_steps_per_second": 3.133, | |
| "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": 3582868429209600.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |