| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00017630543152958184, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.7630543152958186e-05, | |
| "grad_norm": 4.367908477783203, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4166, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7630543152958186e-05, | |
| "eval_loss": 2.4869089126586914, | |
| "eval_runtime": 2092.2381, | |
| "eval_samples_per_second": 11.415, | |
| "eval_steps_per_second": 5.707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.526108630591637e-05, | |
| "grad_norm": 4.961367130279541, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4042, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.2891629458874556e-05, | |
| "grad_norm": 3.3946964740753174, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0628, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.2891629458874556e-05, | |
| "eval_loss": 2.404568672180176, | |
| "eval_runtime": 2091.7971, | |
| "eval_samples_per_second": 11.417, | |
| "eval_steps_per_second": 5.708, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.052217261183275e-05, | |
| "grad_norm": 4.000314235687256, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3275, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.815271576479092e-05, | |
| "grad_norm": 3.29634165763855, | |
| "learning_rate": 0.0001, | |
| "loss": 1.715, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00010578325891774911, | |
| "grad_norm": 4.525784969329834, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1373, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00010578325891774911, | |
| "eval_loss": 1.5161494016647339, | |
| "eval_runtime": 2092.5858, | |
| "eval_samples_per_second": 11.413, | |
| "eval_steps_per_second": 5.706, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001234138020707073, | |
| "grad_norm": 3.471802234649658, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5849, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001410443452236655, | |
| "grad_norm": 3.929349184036255, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2535, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015867488837662365, | |
| "grad_norm": 3.6003997325897217, | |
| "learning_rate": 0.00018, | |
| "loss": 1.4288, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00015867488837662365, | |
| "eval_loss": 0.9702233076095581, | |
| "eval_runtime": 2093.3335, | |
| "eval_samples_per_second": 11.409, | |
| "eval_steps_per_second": 5.704, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00017630543152958184, | |
| "grad_norm": 4.7204108238220215, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0242, | |
| "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": 4053477394219008.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |