| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005741260525644297, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.379178361826996e-05, | |
| "grad_norm": 0.4255746006965637, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2181, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.379178361826996e-05, | |
| "eval_loss": 0.3880921006202698, | |
| "eval_runtime": 136.531, | |
| "eval_samples_per_second": 48.348, | |
| "eval_steps_per_second": 24.178, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012758356723653993, | |
| "grad_norm": 0.5769761800765991, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2823, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001913753508548099, | |
| "grad_norm": 0.5068990588188171, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3933, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001913753508548099, | |
| "eval_loss": 0.38571253418922424, | |
| "eval_runtime": 133.3112, | |
| "eval_samples_per_second": 49.516, | |
| "eval_steps_per_second": 24.762, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025516713447307985, | |
| "grad_norm": 0.48077139258384705, | |
| "learning_rate": 8e-05, | |
| "loss": 0.4101, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00031895891809134984, | |
| "grad_norm": 0.465503454208374, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3471, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003827507017096198, | |
| "grad_norm": 0.43067553639411926, | |
| "learning_rate": 0.00012, | |
| "loss": 0.3989, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003827507017096198, | |
| "eval_loss": 0.3666381239891052, | |
| "eval_runtime": 129.8858, | |
| "eval_samples_per_second": 50.822, | |
| "eval_steps_per_second": 25.415, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00044654248532788977, | |
| "grad_norm": 0.36294376850128174, | |
| "learning_rate": 0.00014, | |
| "loss": 0.3252, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005103342689461597, | |
| "grad_norm": 0.3532055914402008, | |
| "learning_rate": 0.00016, | |
| "loss": 0.3688, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005741260525644297, | |
| "grad_norm": 0.2975287437438965, | |
| "learning_rate": 0.00018, | |
| "loss": 0.2587, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005741260525644297, | |
| "eval_loss": 0.3496640622615814, | |
| "eval_runtime": 131.9733, | |
| "eval_samples_per_second": 50.018, | |
| "eval_steps_per_second": 25.013, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 158042740752384.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |