| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.144082332761578, | |
| "eval_steps": 500, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.951270856073601e-05, | |
| "loss": 1.4381, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.902541712147201e-05, | |
| "loss": 1.3041, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.853812568220802e-05, | |
| "loss": 1.2816, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.805083424294402e-05, | |
| "loss": 1.2974, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.756354280368003e-05, | |
| "loss": 1.2876, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.707625136441603e-05, | |
| "loss": 1.3029, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.6588959925152037e-05, | |
| "loss": 1.301, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.610166848588804e-05, | |
| "loss": 1.3153, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.5614377046624046e-05, | |
| "loss": 1.2989, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.512708560736005e-05, | |
| "loss": 1.1589, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.4639794168096056e-05, | |
| "loss": 1.1053, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.415250272883206e-05, | |
| "loss": 1.1314, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 4.3665211289568066e-05, | |
| "loss": 1.1446, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.317791985030407e-05, | |
| "loss": 1.1701, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.269062841104008e-05, | |
| "loss": 1.1702, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.220333697177608e-05, | |
| "loss": 1.1764, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 4.1716045532512085e-05, | |
| "loss": 1.1933, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 4.122875409324809e-05, | |
| "loss": 1.1964, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.0741462653984095e-05, | |
| "loss": 1.1274, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.025417121472011e-05, | |
| "loss": 1.0048, | |
| "step": 10000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 51304, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 11, | |
| "save_steps": 10000, | |
| "total_flos": 2.0901272223744e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |