| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 1000, | |
| "global_step": 2363, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00042319085907744394, | |
| "grad_norm": 6.409224510192871, | |
| "learning_rate": 0.0, | |
| "loss": 2.8813, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.4231908590774439, | |
| "grad_norm": 5.12570333480835, | |
| "learning_rate": 2.8636363636363637e-05, | |
| "loss": 2.153, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4231908590774439, | |
| "eval_cosine_accuracy": 0.9628772735595703, | |
| "eval_loss": 0.4968035817146301, | |
| "eval_runtime": 35.9081, | |
| "eval_samples_per_second": 264.815, | |
| "eval_steps_per_second": 1.058, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8463817181548878, | |
| "grad_norm": 7.6122307777404785, | |
| "learning_rate": 2.3934169278996865e-05, | |
| "loss": 1.1564, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8463817181548878, | |
| "eval_cosine_accuracy": 0.9654011726379395, | |
| "eval_loss": 0.45379361510276794, | |
| "eval_runtime": 33.9596, | |
| "eval_samples_per_second": 280.009, | |
| "eval_steps_per_second": 1.119, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 7089, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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 | |
| } | |