| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04864864864864865, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005405405405405406, | |
| "grad_norm": 0.2000586837530136, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3204, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005405405405405406, | |
| "eval_loss": 2.2008719444274902, | |
| "eval_runtime": 9.7979, | |
| "eval_samples_per_second": 7.961, | |
| "eval_steps_per_second": 3.98, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010810810810810811, | |
| "grad_norm": 0.17591507732868195, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6394, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016216216216216217, | |
| "grad_norm": 0.19049879908561707, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2241, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.016216216216216217, | |
| "eval_loss": 2.1992404460906982, | |
| "eval_runtime": 9.8906, | |
| "eval_samples_per_second": 7.886, | |
| "eval_steps_per_second": 3.943, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021621621621621623, | |
| "grad_norm": 0.21317099034786224, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0634, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02702702702702703, | |
| "grad_norm": 0.16591224074363708, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2234, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.032432432432432434, | |
| "grad_norm": 0.22719058394432068, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4093, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.032432432432432434, | |
| "eval_loss": 2.1915857791900635, | |
| "eval_runtime": 9.9284, | |
| "eval_samples_per_second": 7.856, | |
| "eval_steps_per_second": 3.928, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03783783783783784, | |
| "grad_norm": 0.24013416469097137, | |
| "learning_rate": 0.00014, | |
| "loss": 2.034, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.043243243243243246, | |
| "grad_norm": 0.19061008095741272, | |
| "learning_rate": 0.00016, | |
| "loss": 2.0807, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04864864864864865, | |
| "grad_norm": 0.22366337478160858, | |
| "learning_rate": 0.00018, | |
| "loss": 2.2467, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04864864864864865, | |
| "eval_loss": 2.179177761077881, | |
| "eval_runtime": 9.9529, | |
| "eval_samples_per_second": 7.837, | |
| "eval_steps_per_second": 3.918, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6057323004952576.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |