| { | |
| "best_metric": 0.889969527721405, | |
| "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale4/lora/sft/checkpoint-50", | |
| "epoch": 0.04434589800443459, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022172949002217295, | |
| "grad_norm": 10.675163725573233, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.9514, | |
| "num_input_tokens_seen": 52584, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004434589800443459, | |
| "grad_norm": 40.324863066721726, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.8884, | |
| "num_input_tokens_seen": 105192, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0066518847006651885, | |
| "grad_norm": 11.862755525069886, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.8391, | |
| "num_input_tokens_seen": 157768, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008869179600886918, | |
| "grad_norm": 6.612134100058155, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.6078, | |
| "num_input_tokens_seen": 209816, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011086474501108648, | |
| "grad_norm": 5.778999894409448, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.3229, | |
| "num_input_tokens_seen": 262088, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013303769401330377, | |
| "grad_norm": 7.203619868080236, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0884, | |
| "num_input_tokens_seen": 314464, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015521064301552107, | |
| "grad_norm": 1.9403341193840407, | |
| "learning_rate": 5.833333333333334e-05, | |
| "loss": 0.9507, | |
| "num_input_tokens_seen": 365768, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017738359201773836, | |
| "grad_norm": 1.227381877798724, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.8783, | |
| "num_input_tokens_seen": 418744, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019955654101995565, | |
| "grad_norm": 1.192341449931711, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8569, | |
| "num_input_tokens_seen": 470176, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.022172949002217297, | |
| "grad_norm": 0.9027870808759253, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.8773, | |
| "num_input_tokens_seen": 521992, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022172949002217297, | |
| "eval_loss": 0.889969527721405, | |
| "eval_runtime": 47.7178, | |
| "eval_samples_per_second": 1.257, | |
| "eval_steps_per_second": 0.314, | |
| "num_input_tokens_seen": 521992, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024390243902439025, | |
| "grad_norm": 0.9805700614384589, | |
| "learning_rate": 9.166666666666667e-05, | |
| "loss": 0.9117, | |
| "num_input_tokens_seen": 574288, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.026607538802660754, | |
| "grad_norm": 0.9233792774186961, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8536, | |
| "num_input_tokens_seen": 626960, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.028824833702882482, | |
| "grad_norm": 0.6897618492525014, | |
| "learning_rate": 9.999525361252996e-05, | |
| "loss": 0.8525, | |
| "num_input_tokens_seen": 678248, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.031042128603104215, | |
| "grad_norm": 0.4751822186720059, | |
| "learning_rate": 9.998101535124758e-05, | |
| "loss": 0.8411, | |
| "num_input_tokens_seen": 730376, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03325942350332594, | |
| "grad_norm": 0.8184941608670437, | |
| "learning_rate": 9.995728791936504e-05, | |
| "loss": 0.8105, | |
| "num_input_tokens_seen": 781648, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03547671840354767, | |
| "grad_norm": 0.930967493911239, | |
| "learning_rate": 9.992407582166581e-05, | |
| "loss": 0.8383, | |
| "num_input_tokens_seen": 833096, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.037694013303769404, | |
| "grad_norm": 0.9048736490092079, | |
| "learning_rate": 9.988138536364922e-05, | |
| "loss": 0.8133, | |
| "num_input_tokens_seen": 885648, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03991130820399113, | |
| "grad_norm": 1.4017690802266505, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.8217, | |
| "num_input_tokens_seen": 938208, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04212860310421286, | |
| "grad_norm": 1.2230184844510747, | |
| "learning_rate": 9.976760358471686e-05, | |
| "loss": 0.7601, | |
| "num_input_tokens_seen": 989992, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.04434589800443459, | |
| "grad_norm": 1.108668630058659, | |
| "learning_rate": 9.969653386589748e-05, | |
| "loss": 0.7938, | |
| "num_input_tokens_seen": 1042120, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04434589800443459, | |
| "eval_loss": 0.8915936946868896, | |
| "eval_runtime": 19.4403, | |
| "eval_samples_per_second": 3.086, | |
| "eval_steps_per_second": 0.772, | |
| "num_input_tokens_seen": 1042120, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1200, | |
| "num_input_tokens_seen": 1042120, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 68727405543424.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |