{ "best_global_step": 1000, "best_metric": 0.4237593412399292, "best_model_checkpoint": "./finetuned_entity_extraction_v2_telugu\\checkpoint-1000", "epoch": 1.0, "eval_steps": 200, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.05, "grad_norm": 1.7661869525909424, "learning_rate": 1.9600000000000002e-05, "loss": 2.2122, "step": 50 }, { "epoch": 0.1, "grad_norm": 1.6054468154907227, "learning_rate": 1.9869002134404235e-05, "loss": 1.0335, "step": 100 }, { "epoch": 0.15, "grad_norm": 1.5563281774520874, "learning_rate": 1.946885829634935e-05, "loss": 0.8195, "step": 150 }, { "epoch": 0.2, "grad_norm": 1.888305425643921, "learning_rate": 1.8810428687441415e-05, "loss": 0.7121, "step": 200 }, { "epoch": 0.2, "eval_loss": 0.6703252196311951, "eval_runtime": 28.9212, "eval_samples_per_second": 69.153, "eval_steps_per_second": 17.288, "step": 200 }, { "epoch": 0.25, "grad_norm": 1.5473520755767822, "learning_rate": 1.7911673551013553e-05, "loss": 0.6368, "step": 250 }, { "epoch": 0.3, "grad_norm": 1.4704129695892334, "learning_rate": 1.6797108584307732e-05, "loss": 0.5804, "step": 300 }, { "epoch": 0.35, "grad_norm": 1.578823208808899, "learning_rate": 1.5497136214161662e-05, "loss": 0.549, "step": 350 }, { "epoch": 0.4, "grad_norm": 1.5565356016159058, "learning_rate": 1.4047216298057872e-05, "loss": 0.525, "step": 400 }, { "epoch": 0.4, "eval_loss": 0.5127490758895874, "eval_runtime": 28.1888, "eval_samples_per_second": 70.95, "eval_steps_per_second": 17.738, "step": 400 }, { "epoch": 0.45, "grad_norm": 1.5739060640335083, "learning_rate": 1.2486898871648552e-05, "loss": 0.4904, "step": 450 }, { "epoch": 0.5, "grad_norm": 1.7133370637893677, "learning_rate": 1.0858745326882172e-05, "loss": 0.4795, "step": 500 }, { "epoch": 0.55, "grad_norm": 1.4752830266952515, "learning_rate": 9.20716744818044e-06, "loss": 0.4592, "step": 550 }, { "epoch": 0.6, "grad_norm": 1.4320343732833862, "learning_rate": 7.577215974732139e-06, "loss": 0.4531, "step": 600 }, { "epoch": 0.6, "eval_loss": 0.45128172636032104, "eval_runtime": 30.6969, "eval_samples_per_second": 65.153, "eval_steps_per_second": 16.288, "step": 600 }, { "epoch": 0.65, "grad_norm": 1.5366995334625244, "learning_rate": 6.0133517337665504e-06, "loss": 0.4392, "step": 650 }, { "epoch": 0.7, "grad_norm": 1.3664205074310303, "learning_rate": 4.5582328650874095e-06, "loss": 0.4371, "step": 700 }, { "epoch": 0.75, "grad_norm": 1.2980847358703613, "learning_rate": 3.25155121822048e-06, "loss": 0.4341, "step": 750 }, { "epoch": 0.8, "grad_norm": 1.4085419178009033, "learning_rate": 2.1289496622274754e-06, "loss": 0.4254, "step": 800 }, { "epoch": 0.8, "eval_loss": 0.42791882157325745, "eval_runtime": 31.0012, "eval_samples_per_second": 64.514, "eval_steps_per_second": 16.128, "step": 800 }, { "epoch": 0.85, "grad_norm": 1.3011988401412964, "learning_rate": 1.2210498411520256e-06, "loss": 0.4215, "step": 850 }, { "epoch": 0.9, "grad_norm": 1.3734039068222046, "learning_rate": 5.526168953948752e-07, "loss": 0.4205, "step": 900 }, { "epoch": 0.95, "grad_norm": 1.1741344928741455, "learning_rate": 1.4188393324163663e-07, "loss": 0.4243, "step": 950 }, { "epoch": 1.0, "grad_norm": 1.3026286363601685, "learning_rate": 5.467919892865326e-11, "loss": 0.4166, "step": 1000 }, { "epoch": 1.0, "eval_loss": 0.4237593412399292, "eval_runtime": 29.6043, "eval_samples_per_second": 67.558, "eval_steps_per_second": 16.889, "step": 1000 } ], "logging_steps": 50, "max_steps": 1000, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 907581238726656.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }