| { | |
| "best_metric": 0.6852618455886841, | |
| "best_model_checkpoint": "saves/Gemma-7B/lora/train_1/checkpoint-200", | |
| "epoch": 0.8750341810226961, | |
| "eval_steps": 200, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21875854525567404, | |
| "grad_norm": 0.797392725944519, | |
| "learning_rate": 0.00029607910744048336, | |
| "loss": 0.589, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21875854525567404, | |
| "eval_loss": 0.6852618455886841, | |
| "eval_runtime": 1805.3292, | |
| "eval_samples_per_second": 26.101, | |
| "eval_steps_per_second": 3.263, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4375170905113481, | |
| "grad_norm": 0.9750909209251404, | |
| "learning_rate": 0.0002845214084081106, | |
| "loss": 0.3117, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4375170905113481, | |
| "eval_loss": 0.8605772852897644, | |
| "eval_runtime": 1806.5428, | |
| "eval_samples_per_second": 26.083, | |
| "eval_steps_per_second": 3.26, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6562756357670222, | |
| "grad_norm": 1.1119354963302612, | |
| "learning_rate": 0.0002659311228514304, | |
| "loss": 0.1797, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6562756357670222, | |
| "eval_loss": 0.9866830110549927, | |
| "eval_runtime": 1806.3409, | |
| "eval_samples_per_second": 26.086, | |
| "eval_steps_per_second": 3.261, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8750341810226961, | |
| "grad_norm": 0.9399241805076599, | |
| "learning_rate": 0.00024128012426802252, | |
| "loss": 0.0901, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8750341810226961, | |
| "eval_loss": 1.209547519683838, | |
| "eval_runtime": 1804.9908, | |
| "eval_samples_per_second": 26.105, | |
| "eval_steps_per_second": 3.263, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8750341810226961, | |
| "step": 800, | |
| "total_flos": 1.4693665240409702e+18, | |
| "train_loss": 0.2926054573059082, | |
| "train_runtime": 35741.6924, | |
| "train_samples_per_second": 19.644, | |
| "train_steps_per_second": 0.077 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 2742, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "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": 1.4693665240409702e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |