| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0026138665621120044, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002613866562112004, | |
| "grad_norm": 0.7599478363990784, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2521, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002613866562112004, | |
| "eval_loss": 0.38426417112350464, | |
| "eval_runtime": 59.5072, | |
| "eval_samples_per_second": 108.273, | |
| "eval_steps_per_second": 13.545, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005227733124224008, | |
| "grad_norm": 0.6357631683349609, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2179, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007841599686336013, | |
| "grad_norm": 0.7394877672195435, | |
| "learning_rate": 6e-05, | |
| "loss": 0.283, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007841599686336013, | |
| "eval_loss": 0.3338756859302521, | |
| "eval_runtime": 59.6614, | |
| "eval_samples_per_second": 107.993, | |
| "eval_steps_per_second": 13.51, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010455466248448016, | |
| "grad_norm": 0.7267158627510071, | |
| "learning_rate": 8e-05, | |
| "loss": 0.2419, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013069332810560022, | |
| "grad_norm": 0.5915173888206482, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2027, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015683199372672025, | |
| "grad_norm": 0.4983539581298828, | |
| "learning_rate": 0.00012, | |
| "loss": 0.1424, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015683199372672025, | |
| "eval_loss": 0.17498068511486053, | |
| "eval_runtime": 59.665, | |
| "eval_samples_per_second": 107.986, | |
| "eval_steps_per_second": 13.509, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018297065934784029, | |
| "grad_norm": 0.43685799837112427, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0965, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0020910932496896032, | |
| "grad_norm": 0.6890192627906799, | |
| "learning_rate": 0.00016, | |
| "loss": 0.1035, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002352479905900804, | |
| "grad_norm": 0.38788190484046936, | |
| "learning_rate": 0.00018, | |
| "loss": 0.07, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002352479905900804, | |
| "eval_loss": 0.05562698468565941, | |
| "eval_runtime": 59.7185, | |
| "eval_samples_per_second": 107.889, | |
| "eval_steps_per_second": 13.497, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026138665621120044, | |
| "grad_norm": 0.44018974900245667, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0476, | |
| "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": 7765973637529600.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |