| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00027728098268380263, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.7728098268380262e-05, | |
| "grad_norm": 9.117630958557129, | |
| "learning_rate": 2e-05, | |
| "loss": 12.6889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.7728098268380262e-05, | |
| "eval_loss": 12.221525192260742, | |
| "eval_runtime": 727.815, | |
| "eval_samples_per_second": 20.864, | |
| "eval_steps_per_second": 10.433, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.5456196536760525e-05, | |
| "grad_norm": 9.838047981262207, | |
| "learning_rate": 4e-05, | |
| "loss": 13.4563, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 8.318429480514078e-05, | |
| "grad_norm": 10.068131446838379, | |
| "learning_rate": 6e-05, | |
| "loss": 12.1282, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.318429480514078e-05, | |
| "eval_loss": 12.13474178314209, | |
| "eval_runtime": 726.2499, | |
| "eval_samples_per_second": 20.909, | |
| "eval_steps_per_second": 10.455, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00011091239307352105, | |
| "grad_norm": 9.659515380859375, | |
| "learning_rate": 8e-05, | |
| "loss": 11.7016, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00013864049134190132, | |
| "grad_norm": 10.803753852844238, | |
| "learning_rate": 0.0001, | |
| "loss": 12.0853, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00016636858961028157, | |
| "grad_norm": 13.15717887878418, | |
| "learning_rate": 0.00012, | |
| "loss": 11.5983, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016636858961028157, | |
| "eval_loss": 9.911439895629883, | |
| "eval_runtime": 726.4933, | |
| "eval_samples_per_second": 20.902, | |
| "eval_steps_per_second": 10.452, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019409668787866185, | |
| "grad_norm": 15.02273178100586, | |
| "learning_rate": 0.00014, | |
| "loss": 9.7374, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002218247861470421, | |
| "grad_norm": 14.003586769104004, | |
| "learning_rate": 0.00016, | |
| "loss": 7.1773, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00024955288441542235, | |
| "grad_norm": 12.71288013458252, | |
| "learning_rate": 0.00018, | |
| "loss": 6.932, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00024955288441542235, | |
| "eval_loss": 6.153598785400391, | |
| "eval_runtime": 726.5907, | |
| "eval_samples_per_second": 20.899, | |
| "eval_steps_per_second": 10.45, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00027728098268380263, | |
| "grad_norm": 10.181532859802246, | |
| "learning_rate": 0.0002, | |
| "loss": 6.2723, | |
| "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": 3190498328051712.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |