| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.16822429906542055, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 1.2704600095748901, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "eval_loss": 2.2257795333862305, | |
| "eval_runtime": 0.9227, | |
| "eval_samples_per_second": 98.625, | |
| "eval_steps_per_second": 13.005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 1.3961941003799438, | |
| "learning_rate": 4e-05, | |
| "loss": 2.262, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 1.301194429397583, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2203, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "eval_loss": 2.207164764404297, | |
| "eval_runtime": 0.9897, | |
| "eval_samples_per_second": 91.95, | |
| "eval_steps_per_second": 12.125, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 1.3056365251541138, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1908, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 1.2624163627624512, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1388, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 1.3537291288375854, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1188, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "eval_loss": 1.8779184818267822, | |
| "eval_runtime": 0.9893, | |
| "eval_samples_per_second": 91.989, | |
| "eval_steps_per_second": 12.13, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 1.3764944076538086, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8747, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 1.407188892364502, | |
| "learning_rate": 0.00016, | |
| "loss": 1.637, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 1.341946005821228, | |
| "learning_rate": 0.00018, | |
| "loss": 1.718, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "eval_loss": 1.5427663326263428, | |
| "eval_runtime": 0.987, | |
| "eval_samples_per_second": 92.195, | |
| "eval_steps_per_second": 12.158, | |
| "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": 6658431293325312.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |