| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 1000, | |
| "global_step": 2537, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00039416633819471815, | |
| "grad_norm": 6.560182094573975, | |
| "learning_rate": 0.0, | |
| "loss": 3.906, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3941663381947182, | |
| "grad_norm": 4.686622619628906, | |
| "learning_rate": 1.3118844386080105e-05, | |
| "loss": 3.3873, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3941663381947182, | |
| "eval_cosine_accuracy": 0.9577242732048035, | |
| "eval_loss": 1.444562554359436, | |
| "eval_runtime": 24.0999, | |
| "eval_samples_per_second": 394.567, | |
| "eval_steps_per_second": 1.577, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7883326763894364, | |
| "grad_norm": 4.804063320159912, | |
| "learning_rate": 1.9305058763413388e-05, | |
| "loss": 2.6104, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7883326763894364, | |
| "eval_cosine_accuracy": 0.9649805426597595, | |
| "eval_loss": 1.3182923793792725, | |
| "eval_runtime": 24.3741, | |
| "eval_samples_per_second": 390.127, | |
| "eval_steps_per_second": 1.559, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 15222, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |