| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 239, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.895920844078064, |
| "epoch": 0.10476689366160294, |
| "grad_norm": 0.044189453125, |
| "learning_rate": 0.00019764184991921178, |
| "loss": 1.963738250732422, |
| "mean_token_accuracy": 0.5797919100522995, |
| "num_tokens": 149736.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.5705001145601272, |
| "epoch": 0.20953378732320588, |
| "grad_norm": 0.08544921875, |
| "learning_rate": 0.00018485282065350235, |
| "loss": 1.5540313720703125, |
| "mean_token_accuracy": 0.6486601567268372, |
| "num_tokens": 304644.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.2710277213156222, |
| "epoch": 0.3143006809848088, |
| "grad_norm": 0.150390625, |
| "learning_rate": 0.00016234898018587337, |
| "loss": 1.2361648559570313, |
| "mean_token_accuracy": 0.7193574538826942, |
| "num_tokens": 460349.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 0.966906747892499, |
| "epoch": 0.41906757464641176, |
| "grad_norm": 0.146484375, |
| "learning_rate": 0.00013270679633174218, |
| "loss": 0.9067485046386718, |
| "mean_token_accuracy": 0.7868660807609558, |
| "num_tokens": 617068.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.0063887759670616, |
| "epoch": 0.5238344683080147, |
| "grad_norm": 0.2041015625, |
| "learning_rate": 9.932000683061653e-05, |
| "loss": 0.9463423156738281, |
| "mean_token_accuracy": 0.7903232343494893, |
| "num_tokens": 773251.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 0.8647172609902918, |
| "epoch": 0.6286013619696176, |
| "grad_norm": 0.11962890625, |
| "learning_rate": 6.601106984173835e-05, |
| "loss": 0.8425812530517578, |
| "mean_token_accuracy": 0.8200736752152443, |
| "num_tokens": 928411.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.7620210253261029, |
| "epoch": 0.7333682556312205, |
| "grad_norm": 0.1416015625, |
| "learning_rate": 3.6593530179427535e-05, |
| "loss": 0.7302579498291015, |
| "mean_token_accuracy": 0.8442804780602455, |
| "num_tokens": 1087845.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 0.6012546026986092, |
| "epoch": 0.8381351492928235, |
| "grad_norm": 0.08544921875, |
| "learning_rate": 1.443540603852227e-05, |
| "loss": 0.5850217437744141, |
| "mean_token_accuracy": 0.8818806144595146, |
| "num_tokens": 1240058.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.5766908147186041, |
| "epoch": 0.9429020429544264, |
| "grad_norm": 0.11767578125, |
| "learning_rate": 2.073584124257899e-06, |
| "loss": 0.5253746795654297, |
| "mean_token_accuracy": 0.8891260415315628, |
| "num_tokens": 1397266.0, |
| "step": 225 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 239, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.314400645093274e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
