| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023781212841854936, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023781212841854932, | |
| "grad_norm": 34.2317008972168, | |
| "learning_rate": 2e-05, | |
| "loss": 11.8787, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023781212841854932, | |
| "eval_loss": 2.7639291286468506, | |
| "eval_runtime": 3.0426, | |
| "eval_samples_per_second": 58.503, | |
| "eval_steps_per_second": 29.252, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0047562425683709865, | |
| "grad_norm": 26.885265350341797, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9029, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007134363852556481, | |
| "grad_norm": 44.130611419677734, | |
| "learning_rate": 6e-05, | |
| "loss": 10.1704, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007134363852556481, | |
| "eval_loss": 2.763669490814209, | |
| "eval_runtime": 2.1616, | |
| "eval_samples_per_second": 82.346, | |
| "eval_steps_per_second": 41.173, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009512485136741973, | |
| "grad_norm": 25.129722595214844, | |
| "learning_rate": 8e-05, | |
| "loss": 10.9121, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011890606420927468, | |
| "grad_norm": 28.124937057495117, | |
| "learning_rate": 0.0001, | |
| "loss": 11.458, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014268727705112961, | |
| "grad_norm": 26.849044799804688, | |
| "learning_rate": 0.00012, | |
| "loss": 11.4832, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014268727705112961, | |
| "eval_loss": 2.750887393951416, | |
| "eval_runtime": 2.1839, | |
| "eval_samples_per_second": 81.506, | |
| "eval_steps_per_second": 40.753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016646848989298454, | |
| "grad_norm": 22.75138282775879, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3443, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019024970273483946, | |
| "grad_norm": 26.50885772705078, | |
| "learning_rate": 0.00016, | |
| "loss": 11.268, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02140309155766944, | |
| "grad_norm": 19.236141204833984, | |
| "learning_rate": 0.00018, | |
| "loss": 10.6174, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02140309155766944, | |
| "eval_loss": 2.715468406677246, | |
| "eval_runtime": 2.1818, | |
| "eval_samples_per_second": 81.585, | |
| "eval_steps_per_second": 40.793, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023781212841854936, | |
| "grad_norm": 23.219770431518555, | |
| "learning_rate": 0.0002, | |
| "loss": 10.4842, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 109660707225600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |