| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.14035087719298245, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004678362573099415, | |
| "eval_loss": 1.7791811227798462, | |
| "eval_runtime": 7.5687, | |
| "eval_samples_per_second": 11.891, | |
| "eval_steps_per_second": 5.946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 5.973121166229248, | |
| "learning_rate": 6e-05, | |
| "loss": 7.3382, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 3.107637643814087, | |
| "learning_rate": 0.00012, | |
| "loss": 7.7302, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "eval_loss": 1.5576945543289185, | |
| "eval_runtime": 6.6991, | |
| "eval_samples_per_second": 13.435, | |
| "eval_steps_per_second": 6.717, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 3.1858153343200684, | |
| "learning_rate": 0.00018, | |
| "loss": 7.3068, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "grad_norm": 2.5051910877227783, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 5.8309, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 3.2672739028930664, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.8671, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07485380116959064, | |
| "eval_loss": 1.4480177164077759, | |
| "eval_runtime": 6.7824, | |
| "eval_samples_per_second": 13.27, | |
| "eval_steps_per_second": 6.635, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 2.2665226459503174, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.4626, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09824561403508772, | |
| "grad_norm": 2.6301050186157227, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 6.1923, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11228070175438597, | |
| "grad_norm": 1.8707858324050903, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 4.8334, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11228070175438597, | |
| "eval_loss": 1.4073123931884766, | |
| "eval_runtime": 6.7895, | |
| "eval_samples_per_second": 13.256, | |
| "eval_steps_per_second": 6.628, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12631578947368421, | |
| "grad_norm": 2.524521589279175, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 6.1063, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 2.786410093307495, | |
| "learning_rate": 0.0, | |
| "loss": 6.0852, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4949223596359680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |