| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009687575684185032, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009687575684185032, | |
| "grad_norm": 1823.1712646484375, | |
| "learning_rate": 2e-05, | |
| "loss": 79.8906, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009687575684185032, | |
| "eval_loss": 19.344316482543945, | |
| "eval_runtime": 2.8368, | |
| "eval_samples_per_second": 153.34, | |
| "eval_steps_per_second": 76.846, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019375151368370065, | |
| "grad_norm": 1855.6845703125, | |
| "learning_rate": 4e-05, | |
| "loss": 70.9241, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00290627270525551, | |
| "grad_norm": 1919.878662109375, | |
| "learning_rate": 6e-05, | |
| "loss": 75.1353, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00290627270525551, | |
| "eval_loss": 19.338275909423828, | |
| "eval_runtime": 1.8472, | |
| "eval_samples_per_second": 235.489, | |
| "eval_steps_per_second": 118.015, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003875030273674013, | |
| "grad_norm": 2271.2294921875, | |
| "learning_rate": 8e-05, | |
| "loss": 92.9838, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004843787842092516, | |
| "grad_norm": 2195.043701171875, | |
| "learning_rate": 0.0001, | |
| "loss": 75.1613, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00581254541051102, | |
| "grad_norm": 1893.9847412109375, | |
| "learning_rate": 0.00012, | |
| "loss": 77.0514, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00581254541051102, | |
| "eval_loss": 19.3157958984375, | |
| "eval_runtime": 1.9091, | |
| "eval_samples_per_second": 227.86, | |
| "eval_steps_per_second": 114.192, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006781302978929523, | |
| "grad_norm": 2108.6474609375, | |
| "learning_rate": 0.00014, | |
| "loss": 84.6611, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007750060547348026, | |
| "grad_norm": 4211.90576171875, | |
| "learning_rate": 0.00016, | |
| "loss": 81.414, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00871881811576653, | |
| "grad_norm": 1921.15087890625, | |
| "learning_rate": 0.00018, | |
| "loss": 72.7033, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00871881811576653, | |
| "eval_loss": 19.256641387939453, | |
| "eval_runtime": 1.9014, | |
| "eval_samples_per_second": 228.78, | |
| "eval_steps_per_second": 114.653, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009687575684185032, | |
| "grad_norm": 2065.03759765625, | |
| "learning_rate": 0.0002, | |
| "loss": 77.5755, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 11074975825920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |