| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.046565774155995346, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004656577415599534, | |
| "grad_norm": 0.9818737506866455, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8896, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004656577415599534, | |
| "eval_loss": 2.2087979316711426, | |
| "eval_runtime": 5.7613, | |
| "eval_samples_per_second": 15.795, | |
| "eval_steps_per_second": 7.984, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009313154831199068, | |
| "grad_norm": 1.1392149925231934, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0053, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013969732246798603, | |
| "grad_norm": 1.2315781116485596, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1354, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013969732246798603, | |
| "eval_loss": 2.204477071762085, | |
| "eval_runtime": 4.5143, | |
| "eval_samples_per_second": 20.158, | |
| "eval_steps_per_second": 10.19, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018626309662398137, | |
| "grad_norm": 0.9486850500106812, | |
| "learning_rate": 8e-05, | |
| "loss": 1.982, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023282887077997673, | |
| "grad_norm": 1.1441988945007324, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0982, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027939464493597205, | |
| "grad_norm": 1.3133906126022339, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1796, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.027939464493597205, | |
| "eval_loss": 2.165942907333374, | |
| "eval_runtime": 4.5309, | |
| "eval_samples_per_second": 20.084, | |
| "eval_steps_per_second": 10.152, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03259604190919674, | |
| "grad_norm": 1.119505763053894, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1949, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.037252619324796274, | |
| "grad_norm": 1.6068085432052612, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7999, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04190919674039581, | |
| "grad_norm": 1.812254548072815, | |
| "learning_rate": 0.00018, | |
| "loss": 2.1686, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04190919674039581, | |
| "eval_loss": 1.9648867845535278, | |
| "eval_runtime": 4.5221, | |
| "eval_samples_per_second": 20.124, | |
| "eval_steps_per_second": 10.172, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.046565774155995346, | |
| "grad_norm": 1.7489854097366333, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3195, | |
| "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": 3166205430988800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |