| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 28.2, | |
| "eval_steps": 100, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 2.900357484817505, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.3709, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "grad_norm": 0.9515049457550049, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.727, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "grad_norm": 3.473623037338257, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.6508, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "grad_norm": 3.4193975925445557, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.9384, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "grad_norm": 1.4595755338668823, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 1.3815, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "grad_norm": 4.304596424102783, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2123, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "grad_norm": 1.4083904027938843, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.7774, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 18.7, | |
| "grad_norm": 1.2791956663131714, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.5555, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 21.15, | |
| "grad_norm": 3.859661102294922, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.4299, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 23.45, | |
| "grad_norm": 1.0227820873260498, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.2811, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 25.75, | |
| "grad_norm": 1.0740314722061157, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.2445, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 28.2, | |
| "grad_norm": 3.271472454071045, | |
| "learning_rate": 0.0, | |
| "loss": 0.2564, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 28.2, | |
| "step": 60, | |
| "total_flos": 1937902246297600.0, | |
| "train_loss": 1.3188127915064494, | |
| "train_runtime": 64.4224, | |
| "train_samples_per_second": 71.249, | |
| "train_steps_per_second": 0.931 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1937902246297600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |