| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002390800200827217, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.390800200827217e-05, | |
| "grad_norm": 0.4438362717628479, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6713, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.390800200827217e-05, | |
| "eval_loss": 3.2513158321380615, | |
| "eval_runtime": 631.3902, | |
| "eval_samples_per_second": 27.894, | |
| "eval_steps_per_second": 13.947, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.781600401654434e-05, | |
| "grad_norm": 0.8004191517829895, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3516, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.17240060248165e-05, | |
| "grad_norm": 0.5055680274963379, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9398, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.17240060248165e-05, | |
| "eval_loss": 3.2502992153167725, | |
| "eval_runtime": 641.0363, | |
| "eval_samples_per_second": 27.474, | |
| "eval_steps_per_second": 13.737, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.563200803308868e-05, | |
| "grad_norm": 0.6738940477371216, | |
| "learning_rate": 8e-05, | |
| "loss": 3.1372, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00011954001004136085, | |
| "grad_norm": 0.6546339392662048, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9797, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000143448012049633, | |
| "grad_norm": 0.8025781512260437, | |
| "learning_rate": 0.00012, | |
| "loss": 3.1045, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000143448012049633, | |
| "eval_loss": 3.238287925720215, | |
| "eval_runtime": 903.5962, | |
| "eval_samples_per_second": 19.491, | |
| "eval_steps_per_second": 9.746, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001673560140579052, | |
| "grad_norm": 1.1959559917449951, | |
| "learning_rate": 0.00014, | |
| "loss": 3.7878, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00019126401606617735, | |
| "grad_norm": 0.7699796557426453, | |
| "learning_rate": 0.00016, | |
| "loss": 3.144, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002151720180744495, | |
| "grad_norm": 1.2344245910644531, | |
| "learning_rate": 0.00018, | |
| "loss": 3.656, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002151720180744495, | |
| "eval_loss": 3.1701889038085938, | |
| "eval_runtime": 988.1134, | |
| "eval_samples_per_second": 17.824, | |
| "eval_steps_per_second": 8.912, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002390800200827217, | |
| "grad_norm": 1.1103814840316772, | |
| "learning_rate": 0.0002, | |
| "loss": 2.8396, | |
| "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": 1942042460553216.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |