| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 4500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 0.31903962667783103, |
| "epoch": 1.0, |
| "grad_norm": 3.5418779850006104, |
| "learning_rate": 5e-05, |
| "loss": 0.3342, |
| "mean_token_accuracy": 0.9157681801584032, |
| "num_tokens": 4499836.0, |
| "step": 2250 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_entropy": 0.23254949676990508, |
| "eval_loss": 0.2607364356517792, |
| "eval_mean_token_accuracy": 0.9283432579040527, |
| "eval_num_tokens": 4499836.0, |
| "eval_runtime": 31.0459, |
| "eval_samples_per_second": 32.21, |
| "eval_steps_per_second": 4.026, |
| "step": 2250 |
| }, |
| { |
| "entropy": 0.22166679374045795, |
| "epoch": 2.0, |
| "grad_norm": 4.510587692260742, |
| "learning_rate": 5e-05, |
| "loss": 0.2374, |
| "mean_token_accuracy": 0.9321232258478801, |
| "num_tokens": 8999672.0, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_entropy": 0.21246080088615418, |
| "eval_loss": 0.23861302435398102, |
| "eval_mean_token_accuracy": 0.9319414987564086, |
| "eval_num_tokens": 8999672.0, |
| "eval_runtime": 31.0907, |
| "eval_samples_per_second": 32.164, |
| "eval_steps_per_second": 4.02, |
| "step": 4500 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 6750, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5034715209728e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
