| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.998745294855709, |
| "eval_steps": 250, |
| "global_step": 199, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005018820577164366, |
| "grad_norm": 0.0, |
| "learning_rate": 0, |
| "loss": 4.6329, |
| "mean_token_accuracy": 0.4609886556863785, |
| "num_tokens": 38259.0, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.10037641154328733, |
| "grad_norm": 5.621291160583496, |
| "learning_rate": 1.868020304568528e-05, |
| "loss": 2.5192, |
| "mean_token_accuracy": 0.5757796107546279, |
| "num_tokens": 797423.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.20075282308657466, |
| "grad_norm": 4.943119049072266, |
| "learning_rate": 1.6649746192893404e-05, |
| "loss": 1.469, |
| "mean_token_accuracy": 0.6556068163365125, |
| "num_tokens": 1598470.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.30112923462986196, |
| "grad_norm": 4.54362678527832, |
| "learning_rate": 1.4619289340101523e-05, |
| "loss": 1.4679, |
| "mean_token_accuracy": 0.6591095954179764, |
| "num_tokens": 2418283.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.4015056461731493, |
| "grad_norm": 4.706456184387207, |
| "learning_rate": 1.2588832487309645e-05, |
| "loss": 1.4474, |
| "mean_token_accuracy": 0.6605883561074734, |
| "num_tokens": 3221019.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5018820577164367, |
| "grad_norm": 4.26887321472168, |
| "learning_rate": 1.0558375634517768e-05, |
| "loss": 1.4264, |
| "mean_token_accuracy": 0.6618994094431401, |
| "num_tokens": 4027025.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6022584692597239, |
| "grad_norm": 4.396352767944336, |
| "learning_rate": 8.52791878172589e-06, |
| "loss": 1.4358, |
| "mean_token_accuracy": 0.6629612062126398, |
| "num_tokens": 4822685.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7026348808030113, |
| "grad_norm": 4.525022506713867, |
| "learning_rate": 6.4974619289340105e-06, |
| "loss": 1.4068, |
| "mean_token_accuracy": 0.6654792346060276, |
| "num_tokens": 5633169.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8030112923462986, |
| "grad_norm": 3.8596858978271484, |
| "learning_rate": 4.467005076142132e-06, |
| "loss": 1.3476, |
| "mean_token_accuracy": 0.68043167963624, |
| "num_tokens": 6423994.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.903387703889586, |
| "grad_norm": 4.018551349639893, |
| "learning_rate": 2.436548223350254e-06, |
| "loss": 1.3961, |
| "mean_token_accuracy": 0.669349530339241, |
| "num_tokens": 7234392.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.998745294855709, |
| "mean_token_accuracy": 0.6814169715109625, |
| "num_tokens": 8019524.0, |
| "step": 199, |
| "total_flos": 15983245094912.0, |
| "train_loss": 1.537205442112295, |
| "train_runtime": 2446.3608, |
| "train_samples_per_second": 10.424, |
| "train_steps_per_second": 0.081 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 199, |
| "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": 15983245094912.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
