| { | |
| "best_metric": 0.5005918962125724, | |
| "best_model_checkpoint": "./output/modernBERT-base-sentiment-v2/checkpoint-40", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8373, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.12910686958067819, | |
| "eval_loss": 1.8330078125, | |
| "eval_precision": 0.16504066117321736, | |
| "eval_recall": 0.1890018282051825, | |
| "eval_runtime": 8.9078, | |
| "eval_samples_per_second": 224.523, | |
| "eval_steps_per_second": 0.112, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8336, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8364, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.12910686958067819, | |
| "eval_loss": 1.8330078125, | |
| "eval_precision": 0.16504066117321736, | |
| "eval_recall": 0.1890018282051825, | |
| "eval_runtime": 0.2841, | |
| "eval_samples_per_second": 7040.66, | |
| "eval_steps_per_second": 3.52, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 5.113753318786621, | |
| "learning_rate": 5.961150787913738e-05, | |
| "loss": 1.7937, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.17970771787293252, | |
| "eval_loss": 1.53515625, | |
| "eval_precision": 0.22861304458868634, | |
| "eval_recall": 0.23211174242424246, | |
| "eval_runtime": 0.2207, | |
| "eval_samples_per_second": 9062.407, | |
| "eval_steps_per_second": 4.531, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.125, | |
| "grad_norm": 1.7188981771469116, | |
| "learning_rate": 5.535570256631384e-05, | |
| "loss": 1.5896, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "grad_norm": 1.9793833494186401, | |
| "learning_rate": 4.704194240193467e-05, | |
| "loss": 1.4145, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.31283295562034524, | |
| "eval_loss": 1.15625, | |
| "eval_precision": 0.5734842356008, | |
| "eval_recall": 0.33733943473317013, | |
| "eval_runtime": 0.1992, | |
| "eval_samples_per_second": 10041.198, | |
| "eval_steps_per_second": 5.021, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 4.375, | |
| "grad_norm": 11.112994194030762, | |
| "learning_rate": 3.6000770813281334e-05, | |
| "loss": 1.2037, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 2.136584758758545, | |
| "learning_rate": 2.399922918671867e-05, | |
| "loss": 1.0167, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_f1": 0.5005918962125724, | |
| "eval_loss": 0.916015625, | |
| "eval_precision": 0.5713280704919877, | |
| "eval_recall": 0.49814126531372666, | |
| "eval_runtime": 0.2727, | |
| "eval_samples_per_second": 7333.058, | |
| "eval_steps_per_second": 3.667, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 40, | |
| "total_flos": 3738898811322368.0, | |
| "train_loss": 1.565679931640625, | |
| "train_runtime": 80.5078, | |
| "train_samples_per_second": 993.693, | |
| "train_steps_per_second": 0.497 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 40, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 5.0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3738898811322368.0, | |
| "train_batch_size": 1024, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |