| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.7246376811594203, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.1672008395195008, |
| "epoch": 0.07246376811594203, |
| "grad_norm": 0.5196013675880937, |
| "learning_rate": 1.3846153846153847e-05, |
| "loss": 0.1163, |
| "mean_token_accuracy": 0.9755751550197601, |
| "num_tokens": 684207.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.1451235294342041, |
| "epoch": 0.14492753623188406, |
| "grad_norm": 0.12279766914075808, |
| "learning_rate": 1.9988954038232098e-05, |
| "loss": 0.1032, |
| "mean_token_accuracy": 0.9854924380779266, |
| "num_tokens": 1384915.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.1682737946510315, |
| "epoch": 0.21739130434782608, |
| "grad_norm": 0.11855212926213639, |
| "learning_rate": 1.9921539290043846e-05, |
| "loss": 0.0471, |
| "mean_token_accuracy": 0.9901047766208648, |
| "num_tokens": 2148413.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.2033948302268982, |
| "epoch": 0.2898550724637681, |
| "grad_norm": 0.21467341414107938, |
| "learning_rate": 1.979325950184511e-05, |
| "loss": 0.0477, |
| "mean_token_accuracy": 0.9882820785045624, |
| "num_tokens": 2814343.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.1613067984580994, |
| "epoch": 0.36231884057971014, |
| "grad_norm": 0.10971133409734304, |
| "learning_rate": 1.9604901623544868e-05, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.9847880423069, |
| "num_tokens": 3554118.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.2155601382255554, |
| "epoch": 0.43478260869565216, |
| "grad_norm": 0.25848802070836036, |
| "learning_rate": 1.9357621162314325e-05, |
| "loss": 0.046, |
| "mean_token_accuracy": 0.9875870645046234, |
| "num_tokens": 4274087.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.2151318550109864, |
| "epoch": 0.5072463768115942, |
| "grad_norm": 0.5463161288354474, |
| "learning_rate": 1.9052935093970097e-05, |
| "loss": 0.0482, |
| "mean_token_accuracy": 0.9867257714271546, |
| "num_tokens": 4995138.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.2199562430381774, |
| "epoch": 0.5797101449275363, |
| "grad_norm": 0.13160204776259016, |
| "learning_rate": 1.869271255687855e-05, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9862560451030731, |
| "num_tokens": 5752229.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.227805531024933, |
| "epoch": 0.6521739130434783, |
| "grad_norm": 0.13142100307101248, |
| "learning_rate": 1.827916338547079e-05, |
| "loss": 0.0382, |
| "mean_token_accuracy": 0.9892027378082275, |
| "num_tokens": 6451519.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 1.2010000348091125, |
| "epoch": 0.7246376811594203, |
| "grad_norm": 0.1876410091154084, |
| "learning_rate": 1.7814824553711062e-05, |
| "loss": 0.0524, |
| "mean_token_accuracy": 0.9872801005840302, |
| "num_tokens": 7179797.0, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 414, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1109742516699136.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
