| { | |
| "best_metric": 3.6801536083221436, | |
| "best_model_checkpoint": "/content/drive/MyDrive/models/finetuned/meta-llama_Meta-Llama-3.1-8B-Instruct/checkpoint-100", | |
| "epoch": 10.0, | |
| "eval_steps": 50, | |
| "global_step": 110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 6.6702094078063965, | |
| "learning_rate": 9.900412805461967e-05, | |
| "loss": 11.2023, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 8.338553428649902, | |
| "learning_rate": 9.422164654989072e-05, | |
| "loss": 9.4483, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 18.10846519470215, | |
| "learning_rate": 8.585659023794818e-05, | |
| "loss": 7.6668, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 16.715173721313477, | |
| "learning_rate": 7.45866462322802e-05, | |
| "loss": 6.1567, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 22.686342239379883, | |
| "learning_rate": 6.132483837128823e-05, | |
| "loss": 4.9888, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "eval_loss": 4.827907562255859, | |
| "eval_runtime": 3.1939, | |
| "eval_samples_per_second": 3.444, | |
| "eval_steps_per_second": 0.939, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.454545454545454, | |
| "grad_norm": 18.679607391357422, | |
| "learning_rate": 4.71455594568616e-05, | |
| "loss": 4.3176, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.363636363636363, | |
| "grad_norm": 17.530826568603516, | |
| "learning_rate": 3.3197530339228487e-05, | |
| "loss": 3.9827, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 7.2727272727272725, | |
| "grad_norm": 13.915569305419922, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 3.5305, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 8.181818181818182, | |
| "grad_norm": 14.944436073303223, | |
| "learning_rate": 1.0404887703886251e-05, | |
| "loss": 3.4139, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 9.090909090909092, | |
| "grad_norm": 15.253994941711426, | |
| "learning_rate": 3.406798539427386e-06, | |
| "loss": 3.326, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 9.090909090909092, | |
| "eval_loss": 3.6801536083221436, | |
| "eval_runtime": 3.2002, | |
| "eval_samples_per_second": 3.437, | |
| "eval_steps_per_second": 0.937, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 15.849159240722656, | |
| "learning_rate": 1.8341345686543332e-07, | |
| "loss": 3.2823, | |
| "step": 110 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 110, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.014886293307392e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |