| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 12, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.25, |
| "grad_norm": 6.869666247827064, |
| "learning_rate": 4e-05, |
| "loss": 0.9341, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 6.842871664881322, |
| "learning_rate": 8e-05, |
| "loss": 0.9356, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 17.38739552295052, |
| "learning_rate": 7.804226065180615e-05, |
| "loss": 1.1218, |
| "step": 3 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 23.849681286807776, |
| "learning_rate": 7.236067977499791e-05, |
| "loss": 1.09, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 10.026308687199935, |
| "learning_rate": 6.351141009169893e-05, |
| "loss": 0.9976, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 5.753360435194382, |
| "learning_rate": 5.23606797749979e-05, |
| "loss": 0.9204, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.75, |
| "grad_norm": 5.529849552554458, |
| "learning_rate": 4e-05, |
| "loss": 0.8403, |
| "step": 7 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 76.69488301266507, |
| "learning_rate": 2.7639320225002108e-05, |
| "loss": 0.9154, |
| "step": 8 |
| }, |
| { |
| "epoch": 2.25, |
| "grad_norm": 30.558093298695905, |
| "learning_rate": 1.648858990830108e-05, |
| "loss": 0.7943, |
| "step": 9 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 4.6522238003228304, |
| "learning_rate": 7.639320225002106e-06, |
| "loss": 0.7566, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.75, |
| "grad_norm": 2.326175095128404, |
| "learning_rate": 1.957739348193859e-06, |
| "loss": 0.7171, |
| "step": 11 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.562413841830993, |
| "learning_rate": 0.0, |
| "loss": 0.6852, |
| "step": 12 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 12, |
| "total_flos": 3.087946967448289e+17, |
| "train_loss": 0.8923729360103607, |
| "train_runtime": 2874.2221, |
| "train_samples_per_second": 2.117, |
| "train_steps_per_second": 0.004 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 12, |
| "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": 3.087946967448289e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
