| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003709256139591673, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2364187131972243e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2025.6854, | |
| "eval_samples_per_second": 16.812, | |
| "eval_steps_per_second": 8.406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.709256139591673e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.182093565986121e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2026.4832, | |
| "eval_samples_per_second": 16.805, | |
| "eval_steps_per_second": 8.403, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.418512279183346e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011127768418775018, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00012364187131972242, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2026.0518, | |
| "eval_samples_per_second": 16.809, | |
| "eval_steps_per_second": 8.405, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00014837024558366692, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00018546280697958364, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00018546280697958364, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2026.6651, | |
| "eval_samples_per_second": 16.803, | |
| "eval_steps_per_second": 8.402, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00022255536837550036, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00024728374263944484, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2026.1515, | |
| "eval_samples_per_second": 16.808, | |
| "eval_steps_per_second": 8.404, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002596479297714171, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00029674049116733384, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0003091046782993061, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2020.9264, | |
| "eval_samples_per_second": 16.851, | |
| "eval_steps_per_second": 8.426, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00033383305256325053, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0003709256139591673, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0003709256139591673, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2018.034, | |
| "eval_samples_per_second": 16.875, | |
| "eval_steps_per_second": 8.438, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0630094036926464e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |