| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006386613657773307, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.386613657773307e-05, | |
| "grad_norm": 2.683688163757324, | |
| "learning_rate": 2e-05, | |
| "loss": 3.7011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.386613657773307e-05, | |
| "eval_loss": 0.9851329326629639, | |
| "eval_runtime": 314.4511, | |
| "eval_samples_per_second": 20.967, | |
| "eval_steps_per_second": 10.485, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012773227315546613, | |
| "grad_norm": 2.7458348274230957, | |
| "learning_rate": 4e-05, | |
| "loss": 3.728, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001915984097331992, | |
| "grad_norm": 2.825495958328247, | |
| "learning_rate": 6e-05, | |
| "loss": 3.9193, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001915984097331992, | |
| "eval_loss": 0.9755826592445374, | |
| "eval_runtime": 314.6713, | |
| "eval_samples_per_second": 20.952, | |
| "eval_steps_per_second": 10.478, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025546454631093226, | |
| "grad_norm": 2.776876211166382, | |
| "learning_rate": 8e-05, | |
| "loss": 3.7216, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00031933068288866537, | |
| "grad_norm": 3.5824928283691406, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3011, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003831968194663984, | |
| "grad_norm": 3.2902731895446777, | |
| "learning_rate": 0.00012, | |
| "loss": 3.8865, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003831968194663984, | |
| "eval_loss": 0.8573234677314758, | |
| "eval_runtime": 314.8639, | |
| "eval_samples_per_second": 20.939, | |
| "eval_steps_per_second": 10.471, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004470629560441315, | |
| "grad_norm": 2.6606855392456055, | |
| "learning_rate": 0.00014, | |
| "loss": 3.1834, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005109290926218645, | |
| "grad_norm": 2.275407314300537, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8928, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005747952291995977, | |
| "grad_norm": 2.3752694129943848, | |
| "learning_rate": 0.00018, | |
| "loss": 3.0065, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005747952291995977, | |
| "eval_loss": 0.6135407090187073, | |
| "eval_runtime": 314.4663, | |
| "eval_samples_per_second": 20.966, | |
| "eval_steps_per_second": 10.484, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006386613657773307, | |
| "grad_norm": 2.048513412475586, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6492, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1468725404368896.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |