| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.5384615384615383, | |
| "eval_steps": 50, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 23.719074249267578, | |
| "learning_rate": 5e-06, | |
| "loss": 9.5134, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "eval_loss": 9.499454498291016, | |
| "eval_runtime": 0.1078, | |
| "eval_samples_per_second": 603.237, | |
| "eval_steps_per_second": 46.403, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 23.93488121032715, | |
| "learning_rate": 1e-05, | |
| "loss": 9.566, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 24.966135025024414, | |
| "learning_rate": 1.5e-05, | |
| "loss": 9.4636, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 23.337398529052734, | |
| "learning_rate": 2e-05, | |
| "loss": 9.3114, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.1794871794871795, | |
| "grad_norm": 44.995216369628906, | |
| "learning_rate": 2.5e-05, | |
| "loss": 17.3202, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.3846153846153846, | |
| "grad_norm": 22.951753616333008, | |
| "learning_rate": 3e-05, | |
| "loss": 9.0162, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.5897435897435899, | |
| "grad_norm": 23.991498947143555, | |
| "learning_rate": 3.5e-05, | |
| "loss": 8.8952, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.7948717948717947, | |
| "grad_norm": 25.16469955444336, | |
| "learning_rate": 4e-05, | |
| "loss": 8.5841, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 44.421878814697266, | |
| "learning_rate": 4.5e-05, | |
| "loss": 15.2004, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.358974358974359, | |
| "grad_norm": 22.687650680541992, | |
| "learning_rate": 5e-05, | |
| "loss": 7.9599, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 22.766340255737305, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 7.6044, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "grad_norm": 21.284555435180664, | |
| "learning_rate": 6e-05, | |
| "loss": 7.1714, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.128205128205128, | |
| "grad_norm": 38.172462463378906, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 12.8336, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 18.4998722076416, | |
| "learning_rate": 7e-05, | |
| "loss": 6.4072, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.5384615384615383, | |
| "grad_norm": 16.771501541137695, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.0637, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 156989443276800.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |