| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007439092430723452, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014878184861446904, | |
| "grad_norm": 121.14286804199219, | |
| "learning_rate": 1e-05, | |
| "loss": 186.2454, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014878184861446904, | |
| "eval_loss": 11.398240089416504, | |
| "eval_runtime": 63.1815, | |
| "eval_samples_per_second": 17.917, | |
| "eval_steps_per_second": 8.958, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029756369722893808, | |
| "grad_norm": 75.25308990478516, | |
| "learning_rate": 2e-05, | |
| "loss": 177.1929, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0029756369722893808, | |
| "eval_loss": 11.134454727172852, | |
| "eval_runtime": 59.6087, | |
| "eval_samples_per_second": 18.991, | |
| "eval_steps_per_second": 9.495, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004463455458434071, | |
| "grad_norm": 77.69330596923828, | |
| "learning_rate": 3e-05, | |
| "loss": 181.7405, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0059512739445787615, | |
| "grad_norm": 85.95173645019531, | |
| "learning_rate": 4e-05, | |
| "loss": 182.8079, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0059512739445787615, | |
| "eval_loss": 10.927868843078613, | |
| "eval_runtime": 55.2298, | |
| "eval_samples_per_second": 20.496, | |
| "eval_steps_per_second": 10.248, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007439092430723452, | |
| "grad_norm": 88.17637634277344, | |
| "learning_rate": 5e-05, | |
| "loss": 180.2879, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6332408345395200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |