| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05925925925925926, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005925925925925926, | |
| "grad_norm": 9.069441795349121, | |
| "learning_rate": 2e-05, | |
| "loss": 14.6795, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005925925925925926, | |
| "eval_loss": 15.117592811584473, | |
| "eval_runtime": 3.5688, | |
| "eval_samples_per_second": 19.894, | |
| "eval_steps_per_second": 10.087, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011851851851851851, | |
| "grad_norm": 9.230694770812988, | |
| "learning_rate": 4e-05, | |
| "loss": 15.4274, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017777777777777778, | |
| "grad_norm": 8.99022388458252, | |
| "learning_rate": 6e-05, | |
| "loss": 15.0401, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017777777777777778, | |
| "eval_loss": 15.060223579406738, | |
| "eval_runtime": 2.1996, | |
| "eval_samples_per_second": 32.279, | |
| "eval_steps_per_second": 16.367, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.023703703703703703, | |
| "grad_norm": 10.761432647705078, | |
| "learning_rate": 8e-05, | |
| "loss": 14.8401, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02962962962962963, | |
| "grad_norm": 11.122270584106445, | |
| "learning_rate": 0.0001, | |
| "loss": 14.4769, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.035555555555555556, | |
| "grad_norm": 16.866044998168945, | |
| "learning_rate": 0.00012, | |
| "loss": 13.9125, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.035555555555555556, | |
| "eval_loss": 13.018987655639648, | |
| "eval_runtime": 2.2115, | |
| "eval_samples_per_second": 32.105, | |
| "eval_steps_per_second": 16.278, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04148148148148148, | |
| "grad_norm": 14.603727340698242, | |
| "learning_rate": 0.00014, | |
| "loss": 13.3584, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.047407407407407405, | |
| "grad_norm": 16.81561851501465, | |
| "learning_rate": 0.00016, | |
| "loss": 10.804, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05333333333333334, | |
| "grad_norm": 17.650020599365234, | |
| "learning_rate": 0.00018, | |
| "loss": 10.0794, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05333333333333334, | |
| "eval_loss": 8.098217964172363, | |
| "eval_runtime": 2.2842, | |
| "eval_samples_per_second": 31.083, | |
| "eval_steps_per_second": 15.76, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05925925925925926, | |
| "grad_norm": 17.741235733032227, | |
| "learning_rate": 0.0002, | |
| "loss": 8.3415, | |
| "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 | |
| } | |