| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.151515151515152, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.5151515151515151, | |
| "grad_norm": 1735.82958984375, | |
| "learning_rate": 6.02409638554217e-06, | |
| "loss": 178.0369, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "eval_loss": 141.81396484375, | |
| "eval_runtime": 0.68, | |
| "eval_samples_per_second": 44.12, | |
| "eval_steps_per_second": 5.883, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0303030303030303, | |
| "grad_norm": 878.3958129882812, | |
| "learning_rate": 9.77088948787062e-06, | |
| "loss": 140.1058, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.0303030303030303, | |
| "eval_loss": 125.39718627929688, | |
| "eval_runtime": 0.6771, | |
| "eval_samples_per_second": 44.308, | |
| "eval_steps_per_second": 5.908, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 1332.434326171875, | |
| "learning_rate": 9.097035040431268e-06, | |
| "loss": 114.4198, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "eval_loss": 114.40504455566406, | |
| "eval_runtime": 0.6721, | |
| "eval_samples_per_second": 44.639, | |
| "eval_steps_per_second": 5.952, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.0606060606060606, | |
| "grad_norm": 1204.0079345703125, | |
| "learning_rate": 8.423180592991915e-06, | |
| "loss": 105.3163, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.0606060606060606, | |
| "eval_loss": 108.37521362304688, | |
| "eval_runtime": 0.6767, | |
| "eval_samples_per_second": 44.33, | |
| "eval_steps_per_second": 5.911, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.575757575757576, | |
| "grad_norm": 1180.3629150390625, | |
| "learning_rate": 7.749326145552561e-06, | |
| "loss": 94.5081, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 7.575757575757576, | |
| "eval_loss": 113.66868591308594, | |
| "eval_runtime": 0.6817, | |
| "eval_samples_per_second": 44.009, | |
| "eval_steps_per_second": 5.868, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 9.090909090909092, | |
| "grad_norm": 1183.9482421875, | |
| "learning_rate": 7.0754716981132075e-06, | |
| "loss": 83.6025, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.090909090909092, | |
| "eval_loss": 109.58412170410156, | |
| "eval_runtime": 0.6798, | |
| "eval_samples_per_second": 44.127, | |
| "eval_steps_per_second": 5.884, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.606060606060606, | |
| "grad_norm": 1322.03515625, | |
| "learning_rate": 6.401617250673855e-06, | |
| "loss": 80.1657, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 10.606060606060606, | |
| "eval_loss": 106.66357421875, | |
| "eval_runtime": 0.6829, | |
| "eval_samples_per_second": 43.928, | |
| "eval_steps_per_second": 5.857, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 12.121212121212121, | |
| "grad_norm": 1885.264404296875, | |
| "learning_rate": 5.727762803234502e-06, | |
| "loss": 73.8062, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.121212121212121, | |
| "eval_loss": 115.17276763916016, | |
| "eval_runtime": 0.6809, | |
| "eval_samples_per_second": 44.056, | |
| "eval_steps_per_second": 5.874, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 13.636363636363637, | |
| "grad_norm": 869.5314331054688, | |
| "learning_rate": 5.053908355795149e-06, | |
| "loss": 68.8767, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 13.636363636363637, | |
| "eval_loss": 109.55915832519531, | |
| "eval_runtime": 0.6804, | |
| "eval_samples_per_second": 44.093, | |
| "eval_steps_per_second": 5.879, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 15.151515151515152, | |
| "grad_norm": 1756.1275634765625, | |
| "learning_rate": 4.380053908355795e-06, | |
| "loss": 69.1187, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 15.151515151515152, | |
| "eval_loss": 111.99463653564453, | |
| "eval_runtime": 0.6735, | |
| "eval_samples_per_second": 44.543, | |
| "eval_steps_per_second": 5.939, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 825, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 25, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |