| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 90, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11204481792717087, |
| "grad_norm": 29.25, |
| "learning_rate": 1e-05, |
| "loss": 1.3767690658569336, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22408963585434175, |
| "grad_norm": 23.0, |
| "learning_rate": 9.628619846344453e-06, |
| "loss": 1.287515354156494, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.33613445378151263, |
| "grad_norm": 18.0, |
| "learning_rate": 8.569648672789496e-06, |
| "loss": 1.2844683647155761, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.4481792717086835, |
| "grad_norm": 14.3125, |
| "learning_rate": 6.980398830195785e-06, |
| "loss": 1.2283113479614258, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5602240896358543, |
| "grad_norm": 14.8125, |
| "learning_rate": 5.096956658859122e-06, |
| "loss": 1.1659849166870118, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6722689075630253, |
| "grad_norm": 15.125, |
| "learning_rate": 3.1991113759764493e-06, |
| "loss": 1.2485424995422363, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7843137254901961, |
| "grad_norm": 12.875, |
| "learning_rate": 1.5687918106563326e-06, |
| "loss": 1.2000310897827149, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.896358543417367, |
| "grad_norm": 17.5, |
| "learning_rate": 4.481852951692672e-07, |
| "loss": 1.219639205932617, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 53.0, |
| "learning_rate": 3.760237478849793e-09, |
| "loss": 1.250431442260742, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.125481128692627, |
| "eval_runtime": 7.4107, |
| "eval_samples_per_second": 9.716, |
| "eval_steps_per_second": 1.214, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 90, |
| "total_flos": 1.054823986446048e+16, |
| "train_loss": 1.251299254099528, |
| "train_runtime": 241.5055, |
| "train_samples_per_second": 14.753, |
| "train_steps_per_second": 0.373 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 90, |
| "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": 1.054823986446048e+16, |
| "train_batch_size": 10, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
