| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.899408284023669, | |
| "eval_steps": 500, | |
| "global_step": 63, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.23668639053254437, | |
| "grad_norm": 2.409322500228882, | |
| "learning_rate": 4.996811065272715e-05, | |
| "loss": 1.0822, | |
| "mean_token_accuracy": 0.7053477883338928, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.47337278106508873, | |
| "grad_norm": 0.9640182852745056, | |
| "learning_rate": 4.8861446190538576e-05, | |
| "loss": 0.921, | |
| "mean_token_accuracy": 0.7317641347646713, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7100591715976331, | |
| "grad_norm": 0.7025872468948364, | |
| "learning_rate": 4.624956317935659e-05, | |
| "loss": 0.8498, | |
| "mean_token_accuracy": 0.7442429676651955, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9467455621301775, | |
| "grad_norm": 0.46222633123397827, | |
| "learning_rate": 4.2316506028963374e-05, | |
| "loss": 0.8105, | |
| "mean_token_accuracy": 0.75324527323246, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1420118343195267, | |
| "grad_norm": 0.510589063167572, | |
| "learning_rate": 3.733941471032425e-05, | |
| "loss": 0.7696, | |
| "mean_token_accuracy": 0.7617284547198903, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.378698224852071, | |
| "grad_norm": 0.37975624203681946, | |
| "learning_rate": 3.1668996291960073e-05, | |
| "loss": 0.7509, | |
| "mean_token_accuracy": 0.7663201123476029, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6153846153846154, | |
| "grad_norm": 0.3334354758262634, | |
| "learning_rate": 2.570481262505563e-05, | |
| "loss": 0.7224, | |
| "mean_token_accuracy": 0.7735484451055527, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.8520710059171597, | |
| "grad_norm": 0.2994464933872223, | |
| "learning_rate": 1.986712551234432e-05, | |
| "loss": 0.7218, | |
| "mean_token_accuracy": 0.7732948541641236, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0473372781065087, | |
| "grad_norm": 0.7119457721710205, | |
| "learning_rate": 1.4567283270175847e-05, | |
| "loss": 0.7124, | |
| "mean_token_accuracy": 0.7780754186890342, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.2840236686390534, | |
| "grad_norm": 0.3027782440185547, | |
| "learning_rate": 1.0178735372827107e-05, | |
| "loss": 0.6834, | |
| "mean_token_accuracy": 0.7832115352153778, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.5207100591715976, | |
| "grad_norm": 0.2431010901927948, | |
| "learning_rate": 7.010717610764453e-06, | |
| "loss": 0.682, | |
| "mean_token_accuracy": 0.7827403783798218, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.757396449704142, | |
| "grad_norm": 0.23020850121974945, | |
| "learning_rate": 5.286462018769748e-06, | |
| "loss": 0.673, | |
| "mean_token_accuracy": 0.7855649277567863, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.899408284023669, | |
| "mean_token_accuracy": 0.785752405722936, | |
| "step": 63, | |
| "total_flos": 92935576092672.0, | |
| "train_loss": 0.7762386950235518, | |
| "train_runtime": 1655.1689, | |
| "train_samples_per_second": 4.899, | |
| "train_steps_per_second": 0.038 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 63, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 92935576092672.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |