| { | |
| "best_metric": 0.6029486060142517, | |
| "best_model_checkpoint": "mikhail-panzo/zlm_b64_le5_s8000/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": 5.415271759033203, | |
| "learning_rate": 2.4000000000000003e-07, | |
| "loss": 1.1819, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08375209380234507, | |
| "grad_norm": 16.256921768188477, | |
| "learning_rate": 4.900000000000001e-07, | |
| "loss": 1.0035, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12562814070351758, | |
| "grad_norm": 3.2439260482788086, | |
| "learning_rate": 7.350000000000001e-07, | |
| "loss": 0.9742, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16750418760469013, | |
| "grad_norm": 4.24526834487915, | |
| "learning_rate": 9.85e-07, | |
| "loss": 0.9361, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.20938023450586266, | |
| "grad_norm": 3.625537872314453, | |
| "learning_rate": 1.235e-06, | |
| "loss": 0.8733, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.25125628140703515, | |
| "grad_norm": 4.1455464363098145, | |
| "learning_rate": 1.485e-06, | |
| "loss": 0.8471, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2931323283082077, | |
| "grad_norm": 3.164158582687378, | |
| "learning_rate": 1.7350000000000001e-06, | |
| "loss": 0.838, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.33500837520938026, | |
| "grad_norm": 4.24931001663208, | |
| "learning_rate": 1.985e-06, | |
| "loss": 0.7467, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3768844221105528, | |
| "grad_norm": 2.332688331604004, | |
| "learning_rate": 2.235e-06, | |
| "loss": 0.7389, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4187604690117253, | |
| "grad_norm": 2.370961904525757, | |
| "learning_rate": 2.4850000000000003e-06, | |
| "loss": 0.7074, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4187604690117253, | |
| "eval_loss": 0.6029486060142517, | |
| "eval_runtime": 220.2253, | |
| "eval_samples_per_second": 38.547, | |
| "eval_steps_per_second": 4.822, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 8000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "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": 4787434919241216.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |