| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014349775784753362, | |
| "eval_steps": 3, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002391629297458894, | |
| "grad_norm": 1.3112263679504395, | |
| "learning_rate": 2e-05, | |
| "loss": 44.3552, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002391629297458894, | |
| "eval_loss": 11.093308448791504, | |
| "eval_runtime": 4.3579, | |
| "eval_samples_per_second": 404.093, | |
| "eval_steps_per_second": 202.161, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004783258594917788, | |
| "grad_norm": 1.4681154489517212, | |
| "learning_rate": 4e-05, | |
| "loss": 44.3894, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007174887892376681, | |
| "grad_norm": 1.4816144704818726, | |
| "learning_rate": 6e-05, | |
| "loss": 44.4248, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007174887892376681, | |
| "eval_loss": 11.09327220916748, | |
| "eval_runtime": 3.5525, | |
| "eval_samples_per_second": 495.713, | |
| "eval_steps_per_second": 247.997, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009566517189835576, | |
| "grad_norm": 1.2345036268234253, | |
| "learning_rate": 8e-05, | |
| "loss": 44.4011, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001195814648729447, | |
| "grad_norm": 1.3504621982574463, | |
| "learning_rate": 0.0001, | |
| "loss": 44.4088, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014349775784753362, | |
| "grad_norm": 1.2888625860214233, | |
| "learning_rate": 0.00012, | |
| "loss": 44.4101, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014349775784753362, | |
| "eval_loss": 11.092960357666016, | |
| "eval_runtime": 3.5971, | |
| "eval_samples_per_second": 489.567, | |
| "eval_steps_per_second": 244.923, | |
| "step": 6 | |
| } | |
| ], | |
| "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": 4482662400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |