| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.7081339712918662, |
| "eval_steps": 500, |
| "global_step": 90, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.35390625, |
| "epoch": 0.19138755980861244, |
| "grad_norm": 1.577696681022644, |
| "learning_rate": 0.0001999145758387301, |
| "loss": 2.517007064819336, |
| "mean_token_accuracy": 0.4835851963609457, |
| "num_tokens": 32923.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.953515625, |
| "epoch": 0.3827751196172249, |
| "grad_norm": 1.822049856185913, |
| "learning_rate": 0.00019694002659393305, |
| "loss": 1.814153289794922, |
| "mean_token_accuracy": 0.6044577240943909, |
| "num_tokens": 65628.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.36533203125, |
| "epoch": 0.5741626794258373, |
| "grad_norm": 0.8370082974433899, |
| "learning_rate": 0.0001898390981891979, |
| "loss": 1.4171125411987304, |
| "mean_token_accuracy": 0.6942351691424846, |
| "num_tokens": 98592.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.33076171875, |
| "epoch": 0.7655502392344498, |
| "grad_norm": 0.7550845146179199, |
| "learning_rate": 0.00017891405093963938, |
| "loss": 1.3193041801452636, |
| "mean_token_accuracy": 0.7104418903589249, |
| "num_tokens": 131278.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.312109375, |
| "epoch": 0.9569377990430622, |
| "grad_norm": 0.6932047009468079, |
| "learning_rate": 0.00016462992378609407, |
| "loss": 1.3077256202697753, |
| "mean_token_accuracy": 0.7093201003968715, |
| "num_tokens": 164256.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.3107052364864864, |
| "epoch": 1.1339712918660287, |
| "grad_norm": 0.7087656855583191, |
| "learning_rate": 0.00014759473930370736, |
| "loss": 1.2949213981628418, |
| "mean_token_accuracy": 0.7117355780021565, |
| "num_tokens": 194746.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.26064453125, |
| "epoch": 1.325358851674641, |
| "grad_norm": 0.8213269710540771, |
| "learning_rate": 0.00012853362242491053, |
| "loss": 1.244191551208496, |
| "mean_token_accuracy": 0.7226051487028599, |
| "num_tokens": 227482.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.2599609375, |
| "epoch": 1.5167464114832536, |
| "grad_norm": 0.7758288383483887, |
| "learning_rate": 0.00010825793454723325, |
| "loss": 1.2582054138183594, |
| "mean_token_accuracy": 0.7165695309638977, |
| "num_tokens": 260195.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.25322265625, |
| "epoch": 1.7081339712918662, |
| "grad_norm": 0.7961016893386841, |
| "learning_rate": 8.763073687306524e-05, |
| "loss": 1.2671056747436524, |
| "mean_token_accuracy": 0.7158558055758476, |
| "num_tokens": 292968.0, |
| "step": 90 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 159, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 915542027190144.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
