| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9982905982905983, |
| "eval_steps": 500, |
| "global_step": 73, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13675213675213677, |
| "grad_norm": 12.366014396004987, |
| "learning_rate": 4.9970805670808174e-06, |
| "loss": 0.7955, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.27350427350427353, |
| "grad_norm": 7.119569345619287, |
| "learning_rate": 4.654924167200124e-06, |
| "loss": 0.7791, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.41025641025641024, |
| "grad_norm": 7.338418129750288, |
| "learning_rate": 3.819100610265332e-06, |
| "loss": 0.8035, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5470085470085471, |
| "grad_norm": 7.307968476806662, |
| "learning_rate": 2.6810870004044065e-06, |
| "loss": 0.7937, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6837606837606838, |
| "grad_norm": 6.523804942950502, |
| "learning_rate": 1.5015885410857617e-06, |
| "loss": 0.8005, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8205128205128205, |
| "grad_norm": 6.052210409126915, |
| "learning_rate": 5.508141148419443e-07, |
| "loss": 0.7827, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9572649572649573, |
| "grad_norm": 6.848824598292211, |
| "learning_rate": 4.657468465146642e-08, |
| "loss": 0.7632, |
| "step": 70 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 73, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 22366371643392.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
