| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.019230769230769, | |
| "eval_steps": 105, | |
| "global_step": 210, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000495998666222074, | |
| "loss": 1.2516, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0004918306102034011, | |
| "loss": 1.1424, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00048766255418472825, | |
| "loss": 1.1651, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00048349449816605534, | |
| "loss": 1.2994, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.8112102746963501, | |
| "eval_runtime": 199.9162, | |
| "eval_samples_per_second": 1.035, | |
| "eval_steps_per_second": 0.13, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0004793264421473825, | |
| "loss": 0.8928, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0004751583861287096, | |
| "loss": 0.8594, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00047099033011003665, | |
| "loss": 0.8094, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0004668222740913638, | |
| "loss": 0.7945, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 0.5896552205085754, | |
| "eval_runtime": 199.383, | |
| "eval_samples_per_second": 1.038, | |
| "eval_steps_per_second": 0.13, | |
| "step": 210 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 3000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 29, | |
| "save_steps": 105, | |
| "total_flos": 7.391976951801446e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |