| { | |
| "best_metric": 0.5538778174700708, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-4276", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 4276, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4677268475210477, | |
| "grad_norm": 4.76369571685791, | |
| "learning_rate": 2.2292054345772622e-05, | |
| "loss": 0.5655, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9354536950420954, | |
| "grad_norm": 15.750553131103516, | |
| "learning_rate": 1.93402463021057e-05, | |
| "loss": 0.4835, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.468739777803421, | |
| "eval_matthews_correlation": 0.45788183343120153, | |
| "eval_runtime": 0.7397, | |
| "eval_samples_per_second": 1409.989, | |
| "eval_steps_per_second": 89.223, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 1.4031805425631432, | |
| "grad_norm": 2.3343119621276855, | |
| "learning_rate": 1.6388438258438773e-05, | |
| "loss": 0.3553, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.8709073900841908, | |
| "grad_norm": 18.42914390563965, | |
| "learning_rate": 1.3436630214771844e-05, | |
| "loss": 0.3549, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5877938270568848, | |
| "eval_matthews_correlation": 0.5113261407690263, | |
| "eval_runtime": 0.7225, | |
| "eval_samples_per_second": 1443.572, | |
| "eval_steps_per_second": 91.348, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 2.3386342376052385, | |
| "grad_norm": 66.43087005615234, | |
| "learning_rate": 1.0484822171104921e-05, | |
| "loss": 0.2535, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.8063610851262863, | |
| "grad_norm": 2.8678722381591797, | |
| "learning_rate": 7.533014127437994e-06, | |
| "loss": 0.2356, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.7891482710838318, | |
| "eval_matthews_correlation": 0.5377587696044389, | |
| "eval_runtime": 0.8084, | |
| "eval_samples_per_second": 1290.228, | |
| "eval_steps_per_second": 81.644, | |
| "step": 3207 | |
| }, | |
| { | |
| "epoch": 3.2740879326473338, | |
| "grad_norm": 6.688732147216797, | |
| "learning_rate": 4.581206083771068e-06, | |
| "loss": 0.1868, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.7418147801683816, | |
| "grad_norm": 0.05465169623494148, | |
| "learning_rate": 1.629398040104143e-06, | |
| "loss": 0.1421, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.8958505988121033, | |
| "eval_matthews_correlation": 0.5538778174700708, | |
| "eval_runtime": 0.8734, | |
| "eval_samples_per_second": 1194.183, | |
| "eval_steps_per_second": 75.567, | |
| "step": 4276 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4276, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 150753332903676.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.524386238943955e-05, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 8, | |
| "seed": 11 | |
| } | |
| } | |