| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08650519031141868, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00865051903114187, | |
| "grad_norm": 0.6758226156234741, | |
| "learning_rate": 5.142857142857142e-06, | |
| "loss": 2.4878, | |
| "mean_token_accuracy": 0.5207233637571335, | |
| "num_tokens": 20480.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01730103806228374, | |
| "grad_norm": 0.527189314365387, | |
| "learning_rate": 1.0857142857142858e-05, | |
| "loss": 2.2677, | |
| "mean_token_accuracy": 0.5652981504797936, | |
| "num_tokens": 40960.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025951557093425604, | |
| "grad_norm": 0.5320698022842407, | |
| "learning_rate": 1.6571428571428574e-05, | |
| "loss": 2.3177, | |
| "mean_token_accuracy": 0.5567937418818474, | |
| "num_tokens": 61440.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03460207612456748, | |
| "grad_norm": 0.4314405918121338, | |
| "learning_rate": 1.9999371690018227e-05, | |
| "loss": 2.1426, | |
| "mean_token_accuracy": 0.571554248034954, | |
| "num_tokens": 81920.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04325259515570934, | |
| "grad_norm": 0.413466215133667, | |
| "learning_rate": 1.9992304109437157e-05, | |
| "loss": 2.2219, | |
| "mean_token_accuracy": 0.5544477015733719, | |
| "num_tokens": 102400.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05190311418685121, | |
| "grad_norm": 0.514323353767395, | |
| "learning_rate": 1.997738912978706e-05, | |
| "loss": 2.1555, | |
| "mean_token_accuracy": 0.5584555208683014, | |
| "num_tokens": 122880.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06055363321799308, | |
| "grad_norm": 0.4057506322860718, | |
| "learning_rate": 1.9954638464462176e-05, | |
| "loss": 2.1002, | |
| "mean_token_accuracy": 0.5628543496131897, | |
| "num_tokens": 143360.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06920415224913495, | |
| "grad_norm": 0.4184742271900177, | |
| "learning_rate": 1.9924069980567823e-05, | |
| "loss": 2.0149, | |
| "mean_token_accuracy": 0.5812316745519638, | |
| "num_tokens": 163840.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07785467128027682, | |
| "grad_norm": 0.4239538013935089, | |
| "learning_rate": 1.9885707684888565e-05, | |
| "loss": 1.9184, | |
| "mean_token_accuracy": 0.6034213066101074, | |
| "num_tokens": 184320.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08650519031141868, | |
| "grad_norm": 0.42795529961586, | |
| "learning_rate": 1.9839581705034626e-05, | |
| "loss": 1.8282, | |
| "mean_token_accuracy": 0.6114858329296112, | |
| "num_tokens": 204800.0, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1156, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3498627091660800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |