| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 91, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11049723756906077, |
| "grad_norm": 6.43610954284668, |
| "learning_rate": 2.7e-06, |
| "loss": 1.719, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22099447513812154, |
| "grad_norm": 3.241476535797119, |
| "learning_rate": 2.9095389311788626e-06, |
| "loss": 1.2341, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3314917127071823, |
| "grad_norm": 2.4715421199798584, |
| "learning_rate": 2.610816019663507e-06, |
| "loss": 1.0176, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.4419889502762431, |
| "grad_norm": 2.168630361557007, |
| "learning_rate": 2.1470790985218807e-06, |
| "loss": 0.9334, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5524861878453039, |
| "grad_norm": 2.1965219974517822, |
| "learning_rate": 1.5872172433657137e-06, |
| "loss": 0.9148, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6629834254143646, |
| "grad_norm": 2.0333597660064697, |
| "learning_rate": 1.0143990869125186e-06, |
| "loss": 0.9086, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7734806629834254, |
| "grad_norm": 2.1323087215423584, |
| "learning_rate": 5.137179471464047e-07, |
| "loss": 0.9005, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.8839779005524862, |
| "grad_norm": 2.0045676231384277, |
| "learning_rate": 1.5955103951488177e-07, |
| "loss": 0.9112, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.994475138121547, |
| "grad_norm": 2.074873208999634, |
| "learning_rate": 4.510588248311964e-09, |
| "loss": 0.9107, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 91, |
| "total_flos": 368013566017536.0, |
| "train_loss": 1.0434565075806208, |
| "train_runtime": 20621.8217, |
| "train_samples_per_second": 0.14, |
| "train_steps_per_second": 0.004 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 91, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 368013566017536.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
