| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.3034134007585335, |
| "eval_steps": 10, |
| "global_step": 40, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.116106641292572, |
| "epoch": 0.07585335018963338, |
| "grad_norm": 1.4921875, |
| "learning_rate": 5.6250000000000005e-05, |
| "loss": 2.914295959472656, |
| "mean_token_accuracy": 0.5410080701112747, |
| "num_tokens": 36823.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07585335018963338, |
| "eval_entropy": 2.552819073200226, |
| "eval_loss": 2.6676909923553467, |
| "eval_mean_token_accuracy": 0.5321294479072094, |
| "eval_num_tokens": 36823.0, |
| "eval_runtime": 14.7674, |
| "eval_samples_per_second": 0.542, |
| "eval_steps_per_second": 0.542, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.9473248382409414, |
| "epoch": 0.15170670037926676, |
| "grad_norm": 0.87890625, |
| "learning_rate": 9.999152908979117e-05, |
| "loss": 1.9090084075927733, |
| "mean_token_accuracy": 0.6584314892689387, |
| "num_tokens": 65881.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.15170670037926676, |
| "eval_entropy": 1.8724936991930008, |
| "eval_loss": 1.9479429721832275, |
| "eval_mean_token_accuracy": 0.6351580396294594, |
| "eval_num_tokens": 65881.0, |
| "eval_runtime": 14.8467, |
| "eval_samples_per_second": 0.539, |
| "eval_steps_per_second": 0.539, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.5991886417071024, |
| "epoch": 0.22756005056890014, |
| "grad_norm": 1.4765625, |
| "learning_rate": 9.984101496455829e-05, |
| "loss": 1.5578083038330077, |
| "mean_token_accuracy": 0.7192381203174592, |
| "num_tokens": 89977.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.22756005056890014, |
| "eval_entropy": 1.6338046044111252, |
| "eval_loss": 1.694503903388977, |
| "eval_mean_token_accuracy": 0.6637412160634995, |
| "eval_num_tokens": 89977.0, |
| "eval_runtime": 14.8298, |
| "eval_samples_per_second": 0.539, |
| "eval_steps_per_second": 0.539, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.6071883370478948, |
| "epoch": 0.3034134007585335, |
| "grad_norm": 0.71484375, |
| "learning_rate": 9.950291051311487e-05, |
| "loss": 1.6236091613769532, |
| "mean_token_accuracy": 0.6928597639004389, |
| "num_tokens": 122672.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.3034134007585335, |
| "eval_entropy": 1.5961390733718872, |
| "eval_loss": 1.5684512853622437, |
| "eval_mean_token_accuracy": 0.6787843257188797, |
| "eval_num_tokens": 122672.0, |
| "eval_runtime": 14.7973, |
| "eval_samples_per_second": 0.541, |
| "eval_steps_per_second": 0.541, |
| "step": 40 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 528, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2110479832547328.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
