| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013893713094824591, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013893713094824591, | |
| "grad_norm": 0.6566469669342041, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3182, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013893713094824591, | |
| "eval_loss": 1.5639820098876953, | |
| "eval_runtime": 7.7286, | |
| "eval_samples_per_second": 39.205, | |
| "eval_steps_per_second": 19.667, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027787426189649182, | |
| "grad_norm": 0.7382369041442871, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3753, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004168113928447377, | |
| "grad_norm": 0.6682201623916626, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004168113928447377, | |
| "eval_loss": 1.5597419738769531, | |
| "eval_runtime": 7.7432, | |
| "eval_samples_per_second": 39.131, | |
| "eval_steps_per_second": 19.63, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0055574852379298365, | |
| "grad_norm": 0.7677498459815979, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5734, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0069468565474122956, | |
| "grad_norm": 0.7228012084960938, | |
| "learning_rate": 0.0001, | |
| "loss": 1.553, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008336227856894755, | |
| "grad_norm": 0.7682281732559204, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4623, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008336227856894755, | |
| "eval_loss": 1.5117799043655396, | |
| "eval_runtime": 7.8138, | |
| "eval_samples_per_second": 38.777, | |
| "eval_steps_per_second": 19.453, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009725599166377214, | |
| "grad_norm": 0.8317832350730896, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2603, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011114970475859673, | |
| "grad_norm": 0.8683997392654419, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3767, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012504341785342132, | |
| "grad_norm": 0.8667774796485901, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3886, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012504341785342132, | |
| "eval_loss": 1.2922290563583374, | |
| "eval_runtime": 7.819, | |
| "eval_samples_per_second": 38.752, | |
| "eval_steps_per_second": 19.44, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013893713094824591, | |
| "grad_norm": 0.983684778213501, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1264, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 820048664985600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |