| { | |
| "best_metric": 1.6639649868011475, | |
| "best_model_checkpoint": "ner-bert-ingredients/checkpoint-3750", | |
| "epoch": 6.062647356012126, | |
| "eval_steps": 750, | |
| "global_step": 4500, | |
| "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": 5.3025, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 4.010455131530762, | |
| "eval_runtime": 85.2403, | |
| "eval_samples_per_second": 58.658, | |
| "eval_steps_per_second": 0.927, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.8989218328840976e-05, | |
| "loss": 3.2428, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 2.692633867263794, | |
| "eval_runtime": 84.8728, | |
| "eval_samples_per_second": 58.912, | |
| "eval_steps_per_second": 0.931, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.84845013477089e-05, | |
| "loss": 2.4396, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 2.2496654987335205, | |
| "eval_runtime": 84.957, | |
| "eval_samples_per_second": 58.853, | |
| "eval_steps_per_second": 0.93, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 4.7979110512129385e-05, | |
| "loss": 1.9469, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 1.9068394899368286, | |
| "eval_runtime": 84.9089, | |
| "eval_samples_per_second": 58.887, | |
| "eval_steps_per_second": 0.93, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 4.7473719676549865e-05, | |
| "loss": 1.6198, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_loss": 1.6639649868011475, | |
| "eval_runtime": 84.9276, | |
| "eval_samples_per_second": 58.874, | |
| "eval_steps_per_second": 0.93, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 4.696900269541779e-05, | |
| "loss": 1.4061, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 1.6010338068008423, | |
| "eval_runtime": 84.8998, | |
| "eval_samples_per_second": 58.893, | |
| "eval_steps_per_second": 0.931, | |
| "step": 4500 | |
| } | |
| ], | |
| "logging_steps": 750, | |
| "max_steps": 74200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 750, | |
| "total_flos": 1.9475913345048576e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |