| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.016214025131738953, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016214025131738954, | |
| "grad_norm": 0.02850140817463398, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9402, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016214025131738954, | |
| "eval_loss": 11.933202743530273, | |
| "eval_runtime": 31.8847, | |
| "eval_samples_per_second": 32.586, | |
| "eval_steps_per_second": 16.309, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032428050263477908, | |
| "grad_norm": 0.02187924087047577, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9408, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004864207539521687, | |
| "grad_norm": 0.024799637496471405, | |
| "learning_rate": 3e-05, | |
| "loss": 11.937, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0064856100526955816, | |
| "grad_norm": 0.016412202268838882, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9389, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008107012565869477, | |
| "grad_norm": 0.01911051943898201, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9388, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008107012565869477, | |
| "eval_loss": 11.933172225952148, | |
| "eval_runtime": 1.5488, | |
| "eval_samples_per_second": 670.837, | |
| "eval_steps_per_second": 335.741, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009728415079043373, | |
| "grad_norm": 0.016399100422859192, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9391, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011349817592217268, | |
| "grad_norm": 0.024656867608428, | |
| "learning_rate": 7e-05, | |
| "loss": 11.9368, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012971220105391163, | |
| "grad_norm": 0.019521178677678108, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9401, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014592622618565058, | |
| "grad_norm": 0.02017282322049141, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9355, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016214025131738953, | |
| "grad_norm": 0.017548207193613052, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9381, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016214025131738953, | |
| "eval_loss": 11.933080673217773, | |
| "eval_runtime": 1.6739, | |
| "eval_samples_per_second": 620.723, | |
| "eval_steps_per_second": 310.66, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4844617728.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |