| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 450, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.33444816053511706, |
| "grad_norm": 0.7297519445419312, |
| "learning_rate": 9.8e-05, |
| "loss": 0.9176, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6688963210702341, |
| "grad_norm": 0.42905041575431824, |
| "learning_rate": 0.00019800000000000002, |
| "loss": 0.4443, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.6615354418754578, |
| "learning_rate": 0.00019048270524660196, |
| "loss": 0.4325, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.334448160535117, |
| "grad_norm": 0.41986000537872314, |
| "learning_rate": 0.00016304822940447139, |
| "loss": 0.3633, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.6688963210702341, |
| "grad_norm": 0.4028911292552948, |
| "learning_rate": 0.00012312627849299523, |
| "loss": 0.3539, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.7565308809280396, |
| "learning_rate": 7.862388450078855e-05, |
| "loss": 0.3476, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.334448160535117, |
| "grad_norm": 0.3969388008117676, |
| "learning_rate": 3.8355292344053026e-05, |
| "loss": 0.2388, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.668896321070234, |
| "grad_norm": 0.4283983111381531, |
| "learning_rate": 1.0296190561303132e-05, |
| "loss": 0.2346, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.8485210537910461, |
| "learning_rate": 4.028382912890649e-09, |
| "loss": 0.2253, |
| "step": 450 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 450, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.661595675399291e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
