| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.918032786885246, |
| "eval_steps": 500, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.32786885245901637, |
| "grad_norm": 2.921875, |
| "learning_rate": 1.12224987555998e-05, |
| "loss": 1.1087, |
| "mean_token_accuracy": 0.7001501113176346, |
| "num_tokens": 1499762.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.6557377049180327, |
| "grad_norm": 1.8515625, |
| "learning_rate": 2.525062220009955e-05, |
| "loss": 0.9597, |
| "mean_token_accuracy": 0.7305080831050873, |
| "num_tokens": 3011646.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.9836065573770492, |
| "grad_norm": 1.2734375, |
| "learning_rate": 3.92787456445993e-05, |
| "loss": 0.8149, |
| "mean_token_accuracy": 0.7581357553601265, |
| "num_tokens": 4535370.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.2622950819672132, |
| "grad_norm": 0.96484375, |
| "learning_rate": 5.330686908909905e-05, |
| "loss": 0.7007, |
| "mean_token_accuracy": 0.7876129360759959, |
| "num_tokens": 5810536.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.5901639344262295, |
| "grad_norm": 0.890625, |
| "learning_rate": 6.73349925335988e-05, |
| "loss": 0.6624, |
| "mean_token_accuracy": 0.7920720010995865, |
| "num_tokens": 7320611.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.918032786885246, |
| "grad_norm": 0.9296875, |
| "learning_rate": 8.136311597809856e-05, |
| "loss": 0.6201, |
| "mean_token_accuracy": 0.8009632602334023, |
| "num_tokens": 8820797.0, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 32, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.390928890169037e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
