| { | |
| "best_metric": 11.928269386291504, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05738880918220947, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022955523672883787, | |
| "grad_norm": 0.013528205454349518, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9322, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022955523672883787, | |
| "eval_loss": 11.929409980773926, | |
| "eval_runtime": 0.1769, | |
| "eval_samples_per_second": 282.581, | |
| "eval_steps_per_second": 73.471, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004591104734576757, | |
| "grad_norm": 0.011310913600027561, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9318, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006886657101865136, | |
| "grad_norm": 0.013020253740251064, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.932, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009182209469153515, | |
| "grad_norm": 0.012884683907032013, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9327, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011477761836441894, | |
| "grad_norm": 0.012654552236199379, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.931, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013773314203730272, | |
| "grad_norm": 0.012715470045804977, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9318, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01606886657101865, | |
| "grad_norm": 0.013791879639029503, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9327, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01836441893830703, | |
| "grad_norm": 0.013869657181203365, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9311, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02065997130559541, | |
| "grad_norm": 0.014448965899646282, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9317, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02295552367288379, | |
| "grad_norm": 0.014188776724040508, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9313, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025251076040172165, | |
| "grad_norm": 0.013875615783035755, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9313, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027546628407460545, | |
| "grad_norm": 0.013013684190809727, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.932, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029842180774748924, | |
| "grad_norm": 0.018279287964105606, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9315, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0321377331420373, | |
| "grad_norm": 0.023077277466654778, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9318, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03443328550932568, | |
| "grad_norm": 0.02386321686208248, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.932, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03672883787661406, | |
| "grad_norm": 0.025863660499453545, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9308, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03902439024390244, | |
| "grad_norm": 0.022284619510173798, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9313, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04131994261119082, | |
| "grad_norm": 0.02538789063692093, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9308, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0436154949784792, | |
| "grad_norm": 0.02727440558373928, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9308, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04591104734576758, | |
| "grad_norm": 0.021660292521119118, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9316, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04820659971305596, | |
| "grad_norm": 0.02413346990942955, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.931, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05050215208034433, | |
| "grad_norm": 0.017548860982060432, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9315, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05279770444763271, | |
| "grad_norm": 0.018093083053827286, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9301, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05509325681492109, | |
| "grad_norm": 0.018053309991955757, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9307, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05738880918220947, | |
| "grad_norm": 0.014743311330676079, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9307, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05738880918220947, | |
| "eval_loss": 11.928269386291504, | |
| "eval_runtime": 0.1709, | |
| "eval_samples_per_second": 292.494, | |
| "eval_steps_per_second": 76.049, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "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": 522550247424.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |