| { | |
| "best_metric": 0.7479696273803711, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.0477326968973747, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002386634844868735, | |
| "grad_norm": 0.8287795186042786, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8038, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002386634844868735, | |
| "eval_loss": 0.8742901682853699, | |
| "eval_runtime": 88.9007, | |
| "eval_samples_per_second": 1.991, | |
| "eval_steps_per_second": 1.001, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00477326968973747, | |
| "grad_norm": 0.2608904540538788, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7002, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007159904534606206, | |
| "grad_norm": 0.3414213955402374, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7874, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00954653937947494, | |
| "grad_norm": 0.3702467978000641, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6293, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011933174224343675, | |
| "grad_norm": 0.3586605191230774, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6539, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011933174224343675, | |
| "eval_loss": 0.8658517003059387, | |
| "eval_runtime": 88.9025, | |
| "eval_samples_per_second": 1.991, | |
| "eval_steps_per_second": 1.001, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014319809069212411, | |
| "grad_norm": 0.42771315574645996, | |
| "learning_rate": 0.00012, | |
| "loss": 0.7592, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016706443914081145, | |
| "grad_norm": 0.5302035808563232, | |
| "learning_rate": 0.00014, | |
| "loss": 0.6993, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01909307875894988, | |
| "grad_norm": 0.418961763381958, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9279, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021479713603818614, | |
| "grad_norm": 0.32545751333236694, | |
| "learning_rate": 0.00018, | |
| "loss": 0.5822, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02386634844868735, | |
| "grad_norm": 0.3017027974128723, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6542, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02386634844868735, | |
| "eval_loss": 0.7966330051422119, | |
| "eval_runtime": 88.9654, | |
| "eval_samples_per_second": 1.99, | |
| "eval_steps_per_second": 1.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026252983293556086, | |
| "grad_norm": 1.3630088567733765, | |
| "learning_rate": 0.0001999979446958366, | |
| "loss": 0.8378, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.028639618138424822, | |
| "grad_norm": 0.4510791301727295, | |
| "learning_rate": 0.00019999177886783194, | |
| "loss": 0.8985, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.031026252983293555, | |
| "grad_norm": 0.5864933729171753, | |
| "learning_rate": 0.00019998150276943902, | |
| "loss": 0.6781, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03341288782816229, | |
| "grad_norm": 0.423950731754303, | |
| "learning_rate": 0.000199967116823068, | |
| "loss": 0.5872, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03579952267303103, | |
| "grad_norm": 0.5833825469017029, | |
| "learning_rate": 0.0001999486216200688, | |
| "loss": 0.7589, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03579952267303103, | |
| "eval_loss": 0.7643417119979858, | |
| "eval_runtime": 88.8878, | |
| "eval_samples_per_second": 1.991, | |
| "eval_steps_per_second": 1.001, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03818615751789976, | |
| "grad_norm": 0.368539035320282, | |
| "learning_rate": 0.00019992601792070679, | |
| "loss": 0.684, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0405727923627685, | |
| "grad_norm": 0.4044187664985657, | |
| "learning_rate": 0.00019989930665413147, | |
| "loss": 0.7617, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04295942720763723, | |
| "grad_norm": 0.590376079082489, | |
| "learning_rate": 0.00019986848891833845, | |
| "loss": 0.7967, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.045346062052505964, | |
| "grad_norm": 0.3635483384132385, | |
| "learning_rate": 0.0001998335659801241, | |
| "loss": 0.5567, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0477326968973747, | |
| "grad_norm": 0.5464037656784058, | |
| "learning_rate": 0.00019979453927503364, | |
| "loss": 0.6186, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0477326968973747, | |
| "eval_loss": 0.7479696273803711, | |
| "eval_runtime": 88.8942, | |
| "eval_samples_per_second": 1.991, | |
| "eval_steps_per_second": 1.001, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.984041808658432e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |