| { | |
| "best_metric": 1.5090330839157104, | |
| "best_model_checkpoint": "/mnt/storage1/ziya/VQA/M3D/LaMed/output/Llama3.2_3B_PathVQA_BiomedCLIP_KG/checkpoint-39308", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 39308, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05088022794342119, | |
| "grad_norm": 20.461090087890625, | |
| "learning_rate": 3.39097999321804e-05, | |
| "loss": 2.5988, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.10176045588684238, | |
| "grad_norm": 10.889785766601562, | |
| "learning_rate": 6.78195998643608e-05, | |
| "loss": 1.5759, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.15264068383026355, | |
| "grad_norm": 1.6639609336853027, | |
| "learning_rate": 9.999992936778523e-05, | |
| "loss": 1.4497, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.20352091177368475, | |
| "grad_norm": 0.23197871446609497, | |
| "learning_rate": 9.99700066771779e-05, | |
| "loss": 1.3438, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.25440113971710593, | |
| "grad_norm": 1.9678728580474854, | |
| "learning_rate": 9.988580988278223e-05, | |
| "loss": 1.2782, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.3052813676605271, | |
| "grad_norm": 2.1631968021392822, | |
| "learning_rate": 9.97474304335665e-05, | |
| "loss": 1.2025, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.35616159560394833, | |
| "grad_norm": 1.185405969619751, | |
| "learning_rate": 9.955501862810158e-05, | |
| "loss": 1.1717, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.4070418235473695, | |
| "grad_norm": 2.607581377029419, | |
| "learning_rate": 9.930878345131654e-05, | |
| "loss": 1.0606, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.4579220514907907, | |
| "grad_norm": 2.775092840194702, | |
| "learning_rate": 9.900899234751304e-05, | |
| "loss": 1.0918, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.5088022794342119, | |
| "grad_norm": 9.14775276184082, | |
| "learning_rate": 9.865597092988517e-05, | |
| "loss": 1.1604, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.559682507377633, | |
| "grad_norm": 0.0023216097615659237, | |
| "learning_rate": 9.825010262686e-05, | |
| "loss": 1.1628, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.6105627353210542, | |
| "grad_norm": 3.0961430072784424, | |
| "learning_rate": 9.779182826564301e-05, | |
| "loss": 1.019, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.6614429632644754, | |
| "grad_norm": 2.703859567642212, | |
| "learning_rate": 9.728164559342095e-05, | |
| "loss": 1.0538, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.7123231912078967, | |
| "grad_norm": 1.270561695098877, | |
| "learning_rate": 9.67201087367418e-05, | |
| "loss": 0.9991, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.7632034191513178, | |
| "grad_norm": 0.7671055793762207, | |
| "learning_rate": 9.610782759965936e-05, | |
| "loss": 1.0418, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.814083647094739, | |
| "grad_norm": 9.719964027404785, | |
| "learning_rate": 9.544546720129593e-05, | |
| "loss": 1.0275, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.8649638750381602, | |
| "grad_norm": 2.232903003692627, | |
| "learning_rate": 9.473374695354267e-05, | |
| "loss": 0.9921, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.9158441029815814, | |
| "grad_norm": 0.00023140388657338917, | |
| "learning_rate": 9.397343987968223e-05, | |
| "loss": 0.9755, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.9667243309250025, | |
| "grad_norm": 0.16334091126918793, | |
| "learning_rate": 9.316537177478212e-05, | |
| "loss": 1.0277, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.5435537099838257, | |
| "eval_runtime": 306.8844, | |
| "eval_samples_per_second": 20.395, | |
| "eval_steps_per_second": 1.362, | |
| "step": 19654 | |
| }, | |
| { | |
| "epoch": 1.0176045588684237, | |
| "grad_norm": 0.0002304486552020535, | |
| "learning_rate": 9.231042030877097e-05, | |
| "loss": 0.9118, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.068484786811845, | |
| "grad_norm": 2.282210111618042, | |
| "learning_rate": 9.14095140731717e-05, | |
| "loss": 0.8202, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.119365014755266, | |
| "grad_norm": 2.258639097213745, | |
| "learning_rate": 9.046363157252702e-05, | |
| "loss": 0.7903, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.1702452426986873, | |
| "grad_norm": 0.01590500958263874, | |
| "learning_rate": 8.947380016161286e-05, | |
| "loss": 0.7793, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.2211254706421084, | |
| "grad_norm": 3.9215025901794434, | |
| "learning_rate": 8.844109492959372e-05, | |
| "loss": 0.8083, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.2720056985855297, | |
| "grad_norm": 7.533295631408691, | |
| "learning_rate": 8.736663753233221e-05, | |
| "loss": 0.8399, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.3228859265289508, | |
| "grad_norm": 11.74168586730957, | |
| "learning_rate": 8.625159497412098e-05, | |
| "loss": 0.7777, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.373766154472372, | |
| "grad_norm": 0.00011882645776495337, | |
| "learning_rate": 8.509717834016009e-05, | |
| "loss": 0.7841, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.4246463824157933, | |
| "grad_norm": 0.07268673926591873, | |
| "learning_rate": 8.390464148115665e-05, | |
| "loss": 0.7979, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.4755266103592144, | |
| "grad_norm": 1.4805755615234375, | |
| "learning_rate": 8.267527965147542e-05, | |
| "loss": 0.7649, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.5264068383026355, | |
| "grad_norm": 2.261522054672241, | |
| "learning_rate": 8.141042810231957e-05, | |
| "loss": 0.8216, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.5772870662460567, | |
| "grad_norm": 5.646289825439453, | |
| "learning_rate": 8.011146063146943e-05, | |
| "loss": 0.7398, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.628167294189478, | |
| "grad_norm": 6.523326396942139, | |
| "learning_rate": 7.877978809115454e-05, | |
| "loss": 0.7535, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.6790475221328993, | |
| "grad_norm": 10.001418113708496, | |
| "learning_rate": 7.741685685567961e-05, | |
| "loss": 0.7092, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.7299277500763204, | |
| "grad_norm": 1.004066871246323e-05, | |
| "learning_rate": 7.602414725046885e-05, | |
| "loss": 0.7538, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.7808079780197414, | |
| "grad_norm": 0.00714008929207921, | |
| "learning_rate": 7.460317194423467e-05, | |
| "loss": 0.7715, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.8316882059631627, | |
| "grad_norm": 2.5139772333204746e-05, | |
| "learning_rate": 7.31554743060174e-05, | |
| "loss": 0.7172, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.882568433906584, | |
| "grad_norm": 40.69479751586914, | |
| "learning_rate": 7.168262672888032e-05, | |
| "loss": 0.7505, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.933448661850005, | |
| "grad_norm": 0.01439322717487812, | |
| "learning_rate": 7.018622892208068e-05, | |
| "loss": 0.7763, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.9843288897934261, | |
| "grad_norm": 10.337437629699707, | |
| "learning_rate": 6.866790617357171e-05, | |
| "loss": 0.7194, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.5090330839157104, | |
| "eval_runtime": 307.0021, | |
| "eval_samples_per_second": 20.387, | |
| "eval_steps_per_second": 1.362, | |
| "step": 39308 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 98270, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.92706544187648e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |