| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0490075961774075, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00098015192354815, | |
| "eval_loss": 1.1600793600082397, | |
| "eval_runtime": 14.3992, | |
| "eval_samples_per_second": 29.863, | |
| "eval_steps_per_second": 14.931, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0098015192354815, | |
| "grad_norm": 5.415401935577393, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 3.3126, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01274197500612595, | |
| "eval_loss": 0.4898880124092102, | |
| "eval_runtime": 14.4275, | |
| "eval_samples_per_second": 29.804, | |
| "eval_steps_per_second": 14.902, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019603038470963, | |
| "grad_norm": 5.042013645172119, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.9093, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0254839500122519, | |
| "eval_loss": 0.4654274880886078, | |
| "eval_runtime": 14.4631, | |
| "eval_samples_per_second": 29.731, | |
| "eval_steps_per_second": 14.865, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.029404557706444498, | |
| "grad_norm": 3.6320323944091797, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.9185, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03822592501837785, | |
| "eval_loss": 0.45106396079063416, | |
| "eval_runtime": 14.4235, | |
| "eval_samples_per_second": 29.812, | |
| "eval_steps_per_second": 14.906, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.039206076941926, | |
| "grad_norm": 3.356422185897827, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.7877, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0490075961774075, | |
| "grad_norm": 4.639557838439941, | |
| "learning_rate": 0.0, | |
| "loss": 1.6317, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8763348929740800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |