| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005095909258842464, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6986364196141547e-05, | |
| "eval_loss": 1.3468103408813477, | |
| "eval_runtime": 1823.6205, | |
| "eval_samples_per_second": 13.593, | |
| "eval_steps_per_second": 6.796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.095909258842464e-05, | |
| "grad_norm": 15.388035774230957, | |
| "learning_rate": 3e-05, | |
| "loss": 5.8321, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010191818517684929, | |
| "grad_norm": 12.621480941772461, | |
| "learning_rate": 6e-05, | |
| "loss": 5.5541, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013589091356913237, | |
| "eval_loss": 1.3425273895263672, | |
| "eval_runtime": 1823.6309, | |
| "eval_samples_per_second": 13.593, | |
| "eval_steps_per_second": 6.796, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015287727776527394, | |
| "grad_norm": 40.26927947998047, | |
| "learning_rate": 9e-05, | |
| "loss": 5.5315, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00020383637035369857, | |
| "grad_norm": 47.04484176635742, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 5.9109, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002547954629421232, | |
| "grad_norm": 6.6766252517700195, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.7547, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00027178182713826475, | |
| "eval_loss": 1.2962453365325928, | |
| "eval_runtime": 1823.5636, | |
| "eval_samples_per_second": 13.593, | |
| "eval_steps_per_second": 6.797, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0003057545555305479, | |
| "grad_norm": 2.574517250061035, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 5.7193, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0003567136481189725, | |
| "grad_norm": 2.4038732051849365, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 4.4778, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00040767274070739715, | |
| "grad_norm": 2.2437119483947754, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 5.2389, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00040767274070739715, | |
| "eval_loss": 1.2343007326126099, | |
| "eval_runtime": 1823.5812, | |
| "eval_samples_per_second": 13.593, | |
| "eval_steps_per_second": 6.797, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00045863183329582176, | |
| "grad_norm": 2.8667590618133545, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 5.1294, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0005095909258842464, | |
| "grad_norm": 2.4659061431884766, | |
| "learning_rate": 0.0, | |
| "loss": 4.3906, | |
| "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": 1.0128701987487744e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |