| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005100089251561903, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005100089251561902, | |
| "grad_norm": 0.6452195644378662, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9055, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005100089251561902, | |
| "eval_loss": 0.9768646955490112, | |
| "eval_runtime": 32.3814, | |
| "eval_samples_per_second": 25.508, | |
| "eval_steps_per_second": 12.754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010200178503123804, | |
| "grad_norm": 0.6374425292015076, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0606, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015300267754685707, | |
| "grad_norm": 0.7021344900131226, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8635, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015300267754685707, | |
| "eval_loss": 0.9749233722686768, | |
| "eval_runtime": 32.3827, | |
| "eval_samples_per_second": 25.507, | |
| "eval_steps_per_second": 12.754, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002040035700624761, | |
| "grad_norm": 0.6206414103507996, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9365, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0025500446257809514, | |
| "grad_norm": 0.5406132340431213, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8756, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0030600535509371415, | |
| "grad_norm": 0.7608964443206787, | |
| "learning_rate": 0.00012, | |
| "loss": 0.9695, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0030600535509371415, | |
| "eval_loss": 0.9506598711013794, | |
| "eval_runtime": 32.4284, | |
| "eval_samples_per_second": 25.471, | |
| "eval_steps_per_second": 12.736, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0035700624760933316, | |
| "grad_norm": 0.7209481596946716, | |
| "learning_rate": 0.00014, | |
| "loss": 0.885, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004080071401249522, | |
| "grad_norm": 0.8551030158996582, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0577, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004590080326405712, | |
| "grad_norm": 1.1315573453903198, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9613, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004590080326405712, | |
| "eval_loss": 0.9206755757331848, | |
| "eval_runtime": 32.3843, | |
| "eval_samples_per_second": 25.506, | |
| "eval_steps_per_second": 12.753, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005100089251561903, | |
| "grad_norm": 0.7657261490821838, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8224, | |
| "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": 1000194661416960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |