| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.2, |
| "eval_steps": 500, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "grad_norm": 5.485438823699951, |
| "learning_rate": 0.0002, |
| "loss": 4.5061, |
| "memory/device_reserved (GiB)": 0.0, |
| "memory/max_active (GiB)": 0.0, |
| "memory/max_allocated (GiB)": 0.0, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 4.593176364898682, |
| "learning_rate": 0.00019510565162951537, |
| "loss": 3.7913, |
| "memory/device_reserved (GiB)": 0.0, |
| "memory/max_active (GiB)": 0.0, |
| "memory/max_allocated (GiB)": 0.0, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 4.607494354248047, |
| "learning_rate": 0.00018090169943749476, |
| "loss": 3.0368, |
| "memory/device_reserved (GiB)": 0.0, |
| "memory/max_active (GiB)": 0.0, |
| "memory/max_allocated (GiB)": 0.0, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 4.247849464416504, |
| "learning_rate": 0.00015877852522924732, |
| "loss": 2.4057, |
| "memory/device_reserved (GiB)": 0.0, |
| "memory/max_active (GiB)": 0.0, |
| "memory/max_allocated (GiB)": 0.0, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 3.5455574989318848, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 1.9879, |
| "memory/device_reserved (GiB)": 0.0, |
| "memory/max_active (GiB)": 0.0, |
| "memory/max_allocated (GiB)": 0.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 3.5534489154815674, |
| "learning_rate": 0.0001, |
| "loss": 1.6576, |
| "memory/device_reserved (GiB)": 0.0, |
| "memory/max_active (GiB)": 0.0, |
| "memory/max_allocated (GiB)": 0.0, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 3.670276403427124, |
| "learning_rate": 6.909830056250527e-05, |
| "loss": 1.4126, |
| "memory/device_reserved (GiB)": 0.0, |
| "memory/max_active (GiB)": 0.0, |
| "memory/max_allocated (GiB)": 0.0, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 4.0369062423706055, |
| "learning_rate": 4.12214747707527e-05, |
| "loss": 1.2206, |
| "memory/device_reserved (GiB)": 0.0, |
| "memory/max_active (GiB)": 0.0, |
| "memory/max_allocated (GiB)": 0.0, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 4.194610595703125, |
| "learning_rate": 1.9098300562505266e-05, |
| "loss": 1.0935, |
| "memory/device_reserved (GiB)": 0.0, |
| "memory/max_active (GiB)": 0.0, |
| "memory/max_allocated (GiB)": 0.0, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 4.174754619598389, |
| "learning_rate": 4.8943483704846475e-06, |
| "loss": 1.0354, |
| "memory/device_reserved (GiB)": 0.0, |
| "memory/max_active (GiB)": 0.0, |
| "memory/max_allocated (GiB)": 0.0, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7993499320320.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
