| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.4814814814814814, |
| "eval_steps": 500, |
| "global_step": 80, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.4490234375, |
| "epoch": 0.18518518518518517, |
| "grad_norm": 1.605711817741394, |
| "learning_rate": 0.00019997919281892067, |
| "loss": 2.744666862487793, |
| "mean_token_accuracy": 0.4455879807472229, |
| "num_tokens": 35176.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 2.14208984375, |
| "epoch": 0.37037037037037035, |
| "grad_norm": 1.9346004724502563, |
| "learning_rate": 0.00019749279121818235, |
| "loss": 1.9460367202758788, |
| "mean_token_accuracy": 0.5691858988255263, |
| "num_tokens": 70631.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.50927734375, |
| "epoch": 0.5555555555555556, |
| "grad_norm": 0.859683096408844, |
| "learning_rate": 0.00019096319953545185, |
| "loss": 1.5292683601379395, |
| "mean_token_accuracy": 0.6657284118235112, |
| "num_tokens": 106615.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.45556640625, |
| "epoch": 0.7407407407407407, |
| "grad_norm": 0.7568148970603943, |
| "learning_rate": 0.000180661210923753, |
| "loss": 1.4439837455749511, |
| "mean_token_accuracy": 0.6813905350863934, |
| "num_tokens": 142274.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.4376953125, |
| "epoch": 0.9259259259259259, |
| "grad_norm": 0.7695605158805847, |
| "learning_rate": 0.00016701406618375596, |
| "loss": 1.434541606903076, |
| "mean_token_accuracy": 0.6835584975779057, |
| "num_tokens": 177779.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.4240234375, |
| "epoch": 1.1111111111111112, |
| "grad_norm": 0.7485360503196716, |
| "learning_rate": 0.00015058773536894685, |
| "loss": 1.398463821411133, |
| "mean_token_accuracy": 0.6880027234554291, |
| "num_tokens": 213250.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.3787109375, |
| "epoch": 1.2962962962962963, |
| "grad_norm": 0.8382265567779541, |
| "learning_rate": 0.00013206344605527355, |
| "loss": 1.3820528030395507, |
| "mean_token_accuracy": 0.6910028986632824, |
| "num_tokens": 249008.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.39111328125, |
| "epoch": 1.4814814814814814, |
| "grad_norm": 0.8756011128425598, |
| "learning_rate": 0.000112209431687416, |
| "loss": 1.3737930297851562, |
| "mean_token_accuracy": 0.6952961266040802, |
| "num_tokens": 284762.0, |
| "step": 80 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 162, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 888450731472384.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
