| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0065930443382231745, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006593044338223175, | |
| "grad_norm": 2.508810520172119, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5273, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006593044338223175, | |
| "eval_loss": 3.6100175380706787, | |
| "eval_runtime": 21.0215, | |
| "eval_samples_per_second": 30.397, | |
| "eval_steps_per_second": 15.223, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001318608867644635, | |
| "grad_norm": 2.0886263847351074, | |
| "learning_rate": 4e-05, | |
| "loss": 3.5705, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0019779133014669525, | |
| "grad_norm": 1.9770153760910034, | |
| "learning_rate": 6e-05, | |
| "loss": 3.3942, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019779133014669525, | |
| "eval_loss": 3.6000754833221436, | |
| "eval_runtime": 19.9102, | |
| "eval_samples_per_second": 32.094, | |
| "eval_steps_per_second": 16.072, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00263721773528927, | |
| "grad_norm": 2.0442955493927, | |
| "learning_rate": 8e-05, | |
| "loss": 2.895, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0032965221691115872, | |
| "grad_norm": 2.478562116622925, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2157, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003955826602933905, | |
| "grad_norm": 2.527894973754883, | |
| "learning_rate": 0.00012, | |
| "loss": 3.6057, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003955826602933905, | |
| "eval_loss": 3.4499459266662598, | |
| "eval_runtime": 20.0525, | |
| "eval_samples_per_second": 31.866, | |
| "eval_steps_per_second": 15.958, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004615131036756222, | |
| "grad_norm": 2.320080280303955, | |
| "learning_rate": 0.00014, | |
| "loss": 2.7976, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00527443547057854, | |
| "grad_norm": 2.5601561069488525, | |
| "learning_rate": 0.00016, | |
| "loss": 3.1589, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005933739904400857, | |
| "grad_norm": 2.978994131088257, | |
| "learning_rate": 0.00018, | |
| "loss": 2.9887, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005933739904400857, | |
| "eval_loss": 3.153538227081299, | |
| "eval_runtime": 19.9718, | |
| "eval_samples_per_second": 31.995, | |
| "eval_steps_per_second": 16.023, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0065930443382231745, | |
| "grad_norm": 4.296704292297363, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3058, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |