| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.030927835051546393, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003436426116838488, | |
| "eval_loss": 1.0753878355026245, | |
| "eval_runtime": 70.8712, | |
| "eval_samples_per_second": 6.914, | |
| "eval_steps_per_second": 0.875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010309278350515464, | |
| "grad_norm": 9.508790016174316, | |
| "learning_rate": 3e-05, | |
| "loss": 4.2728, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020618556701030927, | |
| "grad_norm": 4.23081111907959, | |
| "learning_rate": 6e-05, | |
| "loss": 4.2308, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.030927835051546393, | |
| "grad_norm": 2.994974136352539, | |
| "learning_rate": 9e-05, | |
| "loss": 4.0505, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.030927835051546393, | |
| "eval_loss": 0.9270894527435303, | |
| "eval_runtime": 72.0129, | |
| "eval_samples_per_second": 6.804, | |
| "eval_steps_per_second": 0.861, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.14501064818688e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |