| { | |
| "best_metric": 0.6066474914550781, | |
| "best_model_checkpoint": "mikhail-panzo/zlm_b64_le5_s12000/checkpoint-500", | |
| "epoch": 0.4187604690117253, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04187604690117253, | |
| "grad_norm": 4.788218975067139, | |
| "learning_rate": 2.4500000000000004e-07, | |
| "loss": 1.1819, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08375209380234507, | |
| "grad_norm": 15.618935585021973, | |
| "learning_rate": 4.95e-07, | |
| "loss": 1.0042, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12562814070351758, | |
| "grad_norm": 2.7821555137634277, | |
| "learning_rate": 7.4e-07, | |
| "loss": 0.9676, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16750418760469013, | |
| "grad_norm": 3.759263038635254, | |
| "learning_rate": 9.85e-07, | |
| "loss": 0.9362, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.20938023450586266, | |
| "grad_norm": 3.906439781188965, | |
| "learning_rate": 1.235e-06, | |
| "loss": 0.8667, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.25125628140703515, | |
| "grad_norm": 4.397643566131592, | |
| "learning_rate": 1.485e-06, | |
| "loss": 0.8455, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2931323283082077, | |
| "grad_norm": 2.94077467918396, | |
| "learning_rate": 1.7350000000000001e-06, | |
| "loss": 0.8376, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.33500837520938026, | |
| "grad_norm": 4.161074161529541, | |
| "learning_rate": 1.985e-06, | |
| "loss": 0.7521, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3768844221105528, | |
| "grad_norm": 2.8088552951812744, | |
| "learning_rate": 2.235e-06, | |
| "loss": 0.7444, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4187604690117253, | |
| "grad_norm": 2.62283992767334, | |
| "learning_rate": 2.4850000000000003e-06, | |
| "loss": 0.7129, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4187604690117253, | |
| "eval_loss": 0.6066474914550781, | |
| "eval_runtime": 213.4911, | |
| "eval_samples_per_second": 39.763, | |
| "eval_steps_per_second": 4.974, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 12000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 11, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4878617293034496.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |