| { | |
| "best_metric": 0.6528732180595398, | |
| "best_model_checkpoint": "output/checkpoint-200", | |
| "epoch": 0.32086633911561213, | |
| "eval_steps": 50, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.3333333333333332e-06, | |
| "loss": 0.785, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.6547, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.6626865671641791, | |
| "eval_loss": 0.8300915956497192, | |
| "eval_runtime": 61.5689, | |
| "eval_samples_per_second": 5.441, | |
| "eval_steps_per_second": 1.364, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00012666666666666666, | |
| "loss": 0.6654, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.6895522388059702, | |
| "eval_loss": 0.6663276553153992, | |
| "eval_runtime": 56.4633, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 1.488, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019333333333333333, | |
| "loss": 0.6491, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.6537313432835821, | |
| "eval_loss": 0.9172552824020386, | |
| "eval_runtime": 56.4705, | |
| "eval_samples_per_second": 5.932, | |
| "eval_steps_per_second": 1.488, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00026, | |
| "loss": 0.641, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.6865671641791045, | |
| "eval_loss": 0.6528732180595398, | |
| "eval_runtime": 56.4485, | |
| "eval_samples_per_second": 5.935, | |
| "eval_steps_per_second": 1.488, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002941234084231146, | |
| "loss": 0.6521, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.6835820895522388, | |
| "eval_loss": 0.8197052478790283, | |
| "eval_runtime": 56.4577, | |
| "eval_samples_per_second": 5.934, | |
| "eval_steps_per_second": 1.488, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027943192948090106, | |
| "loss": 0.638, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.6835820895522388, | |
| "eval_loss": 0.6961421370506287, | |
| "eval_runtime": 56.4506, | |
| "eval_samples_per_second": 5.934, | |
| "eval_steps_per_second": 1.488, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00026474045053868754, | |
| "loss": 0.6857, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.6835820895522388, | |
| "eval_loss": 0.7876304388046265, | |
| "eval_runtime": 56.4651, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 1.488, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.000250048971596474, | |
| "loss": 0.6469, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.6626865671641791, | |
| "eval_loss": 0.7487305402755737, | |
| "eval_runtime": 56.4489, | |
| "eval_samples_per_second": 5.935, | |
| "eval_steps_per_second": 1.488, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1246, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1.4970050098348032e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |