| { | |
| "best_metric": 1.4048632383346558, | |
| "best_model_checkpoint": "ner-bert-ingredients/checkpoint-8250", | |
| "epoch": 17.181542606938365, | |
| "eval_steps": 750, | |
| "global_step": 12750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.949460916442048e-05, | |
| "loss": 5.4, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 3.985283613204956, | |
| "eval_runtime": 84.6074, | |
| "eval_samples_per_second": 59.096, | |
| "eval_steps_per_second": 0.934, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.8989218328840976e-05, | |
| "loss": 3.3737, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 2.947718858718872, | |
| "eval_runtime": 84.1622, | |
| "eval_samples_per_second": 59.409, | |
| "eval_steps_per_second": 0.939, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.84845013477089e-05, | |
| "loss": 2.5551, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 2.259490728378296, | |
| "eval_runtime": 84.2333, | |
| "eval_samples_per_second": 59.359, | |
| "eval_steps_per_second": 0.938, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 4.7979110512129385e-05, | |
| "loss": 2.0321, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 1.9211012125015259, | |
| "eval_runtime": 84.2271, | |
| "eval_samples_per_second": 59.363, | |
| "eval_steps_per_second": 0.938, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 4.7473719676549865e-05, | |
| "loss": 1.6766, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_loss": 1.6346299648284912, | |
| "eval_runtime": 84.1885, | |
| "eval_samples_per_second": 59.391, | |
| "eval_steps_per_second": 0.938, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 4.696900269541779e-05, | |
| "loss": 1.437, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 1.5281634330749512, | |
| "eval_runtime": 84.2371, | |
| "eval_samples_per_second": 59.356, | |
| "eval_steps_per_second": 0.938, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 4.949460916442048e-05, | |
| "loss": 3.7548, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "eval_loss": 2.378469228744507, | |
| "eval_runtime": 84.0031, | |
| "eval_samples_per_second": 59.522, | |
| "eval_steps_per_second": 0.94, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 4.8989218328840976e-05, | |
| "loss": 1.9326, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "eval_loss": 1.8503246307373047, | |
| "eval_runtime": 83.659, | |
| "eval_samples_per_second": 59.766, | |
| "eval_steps_per_second": 0.944, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 4.84845013477089e-05, | |
| "loss": 1.489, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_loss": 1.630631685256958, | |
| "eval_runtime": 83.6797, | |
| "eval_samples_per_second": 59.752, | |
| "eval_steps_per_second": 0.944, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 4.7979784366576826e-05, | |
| "loss": 1.2457, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "eval_loss": 1.4776005744934082, | |
| "eval_runtime": 83.6823, | |
| "eval_samples_per_second": 59.75, | |
| "eval_steps_per_second": 0.944, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 4.7474393530997306e-05, | |
| "loss": 1.0713, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "eval_loss": 1.4048632383346558, | |
| "eval_runtime": 83.6632, | |
| "eval_samples_per_second": 59.763, | |
| "eval_steps_per_second": 0.944, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 4.696900269541779e-05, | |
| "loss": 0.9469, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "eval_loss": 1.349704384803772, | |
| "eval_runtime": 83.6712, | |
| "eval_samples_per_second": 59.758, | |
| "eval_steps_per_second": 0.944, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "learning_rate": 4.949460916442048e-05, | |
| "loss": 3.1119, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "eval_loss": 2.09057354927063, | |
| "eval_runtime": 84.2266, | |
| "eval_samples_per_second": 59.364, | |
| "eval_steps_per_second": 0.938, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "learning_rate": 4.8989218328840976e-05, | |
| "loss": 1.5021, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "eval_loss": 1.6629363298416138, | |
| "eval_runtime": 83.9283, | |
| "eval_samples_per_second": 59.575, | |
| "eval_steps_per_second": 0.941, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 4.84845013477089e-05, | |
| "loss": 1.1682, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "eval_loss": 1.5476787090301514, | |
| "eval_runtime": 83.9134, | |
| "eval_samples_per_second": 59.585, | |
| "eval_steps_per_second": 0.941, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 4.7979110512129385e-05, | |
| "loss": 0.9836, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "eval_loss": 1.5123697519302368, | |
| "eval_runtime": 83.9374, | |
| "eval_samples_per_second": 59.568, | |
| "eval_steps_per_second": 0.941, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 17.18, | |
| "learning_rate": 4.7474393530997306e-05, | |
| "loss": 0.8542, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 17.18, | |
| "eval_loss": 1.3803095817565918, | |
| "eval_runtime": 83.8966, | |
| "eval_samples_per_second": 59.597, | |
| "eval_steps_per_second": 0.942, | |
| "step": 12750 | |
| } | |
| ], | |
| "logging_steps": 750, | |
| "max_steps": 74200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 750, | |
| "total_flos": 5.518175447763763e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |