| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000865909573063285, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.73181914612657e-05, | |
| "eval_loss": 2.1214678287506104, | |
| "eval_runtime": 1102.6932, | |
| "eval_samples_per_second": 22.049, | |
| "eval_steps_per_second": 11.025, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000173181914612657, | |
| "grad_norm": 2.4697346687316895, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 8.3142, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002251364889964541, | |
| "eval_loss": 1.672813892364502, | |
| "eval_runtime": 1102.7354, | |
| "eval_samples_per_second": 22.048, | |
| "eval_steps_per_second": 11.024, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000346363829225314, | |
| "grad_norm": 2.826448678970337, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.3914, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004502729779929082, | |
| "eval_loss": 1.5376884937286377, | |
| "eval_runtime": 1102.0089, | |
| "eval_samples_per_second": 22.062, | |
| "eval_steps_per_second": 11.032, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.000519545743837971, | |
| "grad_norm": 2.897918939590454, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 5.9956, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006754094669893623, | |
| "eval_loss": 1.502578616142273, | |
| "eval_runtime": 1102.0929, | |
| "eval_samples_per_second": 22.061, | |
| "eval_steps_per_second": 11.031, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.000692727658450628, | |
| "grad_norm": 5.3965325355529785, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 5.587, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.000865909573063285, | |
| "grad_norm": 3.153414011001587, | |
| "learning_rate": 0.0, | |
| "loss": 5.9974, | |
| "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": 1.0334801139984384e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |