| { | |
| "best_metric": 3.142681837081909, | |
| "best_model_checkpoint": "supermarketNRVSMELOC/checkpoint-792", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 792, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04924242424242424, | |
| "grad_norm": 6.067267894744873, | |
| "learning_rate": 8.125000000000001e-06, | |
| "loss": 3.7636, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09848484848484848, | |
| "grad_norm": 4.615681171417236, | |
| "learning_rate": 1.6250000000000002e-05, | |
| "loss": 3.7539, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.14772727272727273, | |
| "grad_norm": 4.366635799407959, | |
| "learning_rate": 2.4375e-05, | |
| "loss": 3.7559, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.19696969696969696, | |
| "grad_norm": 6.396846294403076, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 3.7443, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.24621212121212122, | |
| "grad_norm": 5.848783493041992, | |
| "learning_rate": 4.0625000000000005e-05, | |
| "loss": 3.7299, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.29545454545454547, | |
| "grad_norm": 3.787656784057617, | |
| "learning_rate": 4.875e-05, | |
| "loss": 3.718, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3446969696969697, | |
| "grad_norm": 6.08660364151001, | |
| "learning_rate": 4.9227528089887644e-05, | |
| "loss": 3.6869, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.3939393939393939, | |
| "grad_norm": 4.681759357452393, | |
| "learning_rate": 4.831460674157304e-05, | |
| "loss": 3.6771, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.4431818181818182, | |
| "grad_norm": 5.893486499786377, | |
| "learning_rate": 4.740168539325843e-05, | |
| "loss": 3.6445, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.49242424242424243, | |
| "grad_norm": 6.639739513397217, | |
| "learning_rate": 4.648876404494382e-05, | |
| "loss": 3.6046, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5416666666666666, | |
| "grad_norm": 5.436135292053223, | |
| "learning_rate": 4.5575842696629217e-05, | |
| "loss": 3.6118, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.5909090909090909, | |
| "grad_norm": 4.141537189483643, | |
| "learning_rate": 4.4662921348314605e-05, | |
| "loss": 3.6243, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.6401515151515151, | |
| "grad_norm": 7.079050540924072, | |
| "learning_rate": 4.375e-05, | |
| "loss": 3.5685, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.6893939393939394, | |
| "grad_norm": 5.841846942901611, | |
| "learning_rate": 4.2837078651685394e-05, | |
| "loss": 3.5209, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.7386363636363636, | |
| "grad_norm": 4.406051158905029, | |
| "learning_rate": 4.192415730337079e-05, | |
| "loss": 3.5112, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7878787878787878, | |
| "grad_norm": 7.7401862144470215, | |
| "learning_rate": 4.1011235955056184e-05, | |
| "loss": 3.5028, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.8371212121212122, | |
| "grad_norm": 7.258950710296631, | |
| "learning_rate": 4.009831460674158e-05, | |
| "loss": 3.4542, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.8863636363636364, | |
| "grad_norm": 9.357794761657715, | |
| "learning_rate": 3.918539325842697e-05, | |
| "loss": 3.4528, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.9356060606060606, | |
| "grad_norm": 6.444118022918701, | |
| "learning_rate": 3.827247191011236e-05, | |
| "loss": 3.4161, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.9848484848484849, | |
| "grad_norm": 5.109555721282959, | |
| "learning_rate": 3.735955056179776e-05, | |
| "loss": 3.4052, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.20265151515151514, | |
| "eval_f1_macro": 0.025505336473483867, | |
| "eval_f1_micro": 0.20265151515151514, | |
| "eval_f1_weighted": 0.08755512614736226, | |
| "eval_loss": 3.434072256088257, | |
| "eval_precision_macro": 0.037007570606101825, | |
| "eval_precision_micro": 0.20265151515151514, | |
| "eval_precision_weighted": 0.09952466920668675, | |
| "eval_recall_macro": 0.05048996382408151, | |
| "eval_recall_micro": 0.20265151515151514, | |
| "eval_recall_weighted": 0.20265151515151514, | |
| "eval_runtime": 56.3872, | |
| "eval_samples_per_second": 9.364, | |
| "eval_steps_per_second": 0.585, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.0340909090909092, | |
| "grad_norm": 27.62860679626465, | |
| "learning_rate": 3.6446629213483145e-05, | |
| "loss": 3.4113, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.0833333333333333, | |
| "grad_norm": 12.518967628479004, | |
| "learning_rate": 3.553370786516854e-05, | |
| "loss": 3.3479, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 1.1325757575757576, | |
| "grad_norm": 7.984549045562744, | |
| "learning_rate": 3.4620786516853935e-05, | |
| "loss": 3.3677, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 8.635626792907715, | |
| "learning_rate": 3.370786516853933e-05, | |
| "loss": 3.3681, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.231060606060606, | |
| "grad_norm": 9.190679550170898, | |
| "learning_rate": 3.2794943820224725e-05, | |
| "loss": 3.4162, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.2803030303030303, | |
| "grad_norm": 6.9372663497924805, | |
| "learning_rate": 3.188202247191011e-05, | |
| "loss": 3.2836, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 1.3295454545454546, | |
| "grad_norm": 4.514989376068115, | |
| "learning_rate": 3.096910112359551e-05, | |
| "loss": 3.3598, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.378787878787879, | |
| "grad_norm": 6.12080717086792, | |
| "learning_rate": 3.0056179775280903e-05, | |
| "loss": 3.3846, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.428030303030303, | |
| "grad_norm": 5.432583332061768, | |
| "learning_rate": 2.914325842696629e-05, | |
| "loss": 3.18, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 1.4772727272727273, | |
| "grad_norm": 5.338773250579834, | |
| "learning_rate": 2.8230337078651686e-05, | |
| "loss": 3.2837, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.5265151515151514, | |
| "grad_norm": 15.422748565673828, | |
| "learning_rate": 2.731741573033708e-05, | |
| "loss": 3.1643, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.5757575757575757, | |
| "grad_norm": 5.844562530517578, | |
| "learning_rate": 2.6404494382022472e-05, | |
| "loss": 3.2549, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.625, | |
| "grad_norm": 9.893993377685547, | |
| "learning_rate": 2.5491573033707867e-05, | |
| "loss": 3.3227, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.6742424242424243, | |
| "grad_norm": 6.3434295654296875, | |
| "learning_rate": 2.457865168539326e-05, | |
| "loss": 3.1929, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.7234848484848486, | |
| "grad_norm": 7.492882251739502, | |
| "learning_rate": 2.3665730337078653e-05, | |
| "loss": 3.2937, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.7727272727272727, | |
| "grad_norm": 5.293882369995117, | |
| "learning_rate": 2.2752808988764045e-05, | |
| "loss": 3.2394, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.821969696969697, | |
| "grad_norm": 13.984901428222656, | |
| "learning_rate": 2.183988764044944e-05, | |
| "loss": 3.2516, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.871212121212121, | |
| "grad_norm": 6.005086421966553, | |
| "learning_rate": 2.0926966292134835e-05, | |
| "loss": 3.2613, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.9204545454545454, | |
| "grad_norm": 7.952373027801514, | |
| "learning_rate": 2.0014044943820226e-05, | |
| "loss": 3.2926, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.9696969696969697, | |
| "grad_norm": 7.9951043128967285, | |
| "learning_rate": 1.9101123595505618e-05, | |
| "loss": 3.1585, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.20454545454545456, | |
| "eval_f1_macro": 0.02462602836447254, | |
| "eval_f1_micro": 0.20454545454545456, | |
| "eval_f1_weighted": 0.08562023329167062, | |
| "eval_loss": 3.193603992462158, | |
| "eval_precision_macro": 0.034878596742616244, | |
| "eval_precision_micro": 0.20454545454545456, | |
| "eval_precision_weighted": 0.09384124563573254, | |
| "eval_recall_macro": 0.05068899317325554, | |
| "eval_recall_micro": 0.20454545454545456, | |
| "eval_recall_weighted": 0.20454545454545456, | |
| "eval_runtime": 55.1855, | |
| "eval_samples_per_second": 9.568, | |
| "eval_steps_per_second": 0.598, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 2.018939393939394, | |
| "grad_norm": 11.740503311157227, | |
| "learning_rate": 1.818820224719101e-05, | |
| "loss": 3.2347, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 2.0681818181818183, | |
| "grad_norm": 5.635743618011475, | |
| "learning_rate": 1.7275280898876404e-05, | |
| "loss": 3.0835, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 2.117424242424242, | |
| "grad_norm": 11.321329116821289, | |
| "learning_rate": 1.63623595505618e-05, | |
| "loss": 3.1773, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 2.1666666666666665, | |
| "grad_norm": 12.002336502075195, | |
| "learning_rate": 1.544943820224719e-05, | |
| "loss": 3.2081, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 2.215909090909091, | |
| "grad_norm": 13.068202018737793, | |
| "learning_rate": 1.4536516853932586e-05, | |
| "loss": 3.1807, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 2.265151515151515, | |
| "grad_norm": 15.093032836914062, | |
| "learning_rate": 1.3623595505617979e-05, | |
| "loss": 3.1387, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 2.3143939393939394, | |
| "grad_norm": 9.244571685791016, | |
| "learning_rate": 1.271067415730337e-05, | |
| "loss": 3.3179, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 2.3636363636363638, | |
| "grad_norm": 13.117069244384766, | |
| "learning_rate": 1.1797752808988765e-05, | |
| "loss": 3.1844, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 2.412878787878788, | |
| "grad_norm": 8.456986427307129, | |
| "learning_rate": 1.0884831460674158e-05, | |
| "loss": 3.2497, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 2.462121212121212, | |
| "grad_norm": 6.265410423278809, | |
| "learning_rate": 9.97191011235955e-06, | |
| "loss": 3.2243, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.5113636363636362, | |
| "grad_norm": 11.483809471130371, | |
| "learning_rate": 9.058988764044945e-06, | |
| "loss": 3.1206, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 2.5606060606060606, | |
| "grad_norm": 16.1591796875, | |
| "learning_rate": 8.146067415730338e-06, | |
| "loss": 3.1371, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 2.609848484848485, | |
| "grad_norm": 9.152714729309082, | |
| "learning_rate": 7.23314606741573e-06, | |
| "loss": 3.1618, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 2.659090909090909, | |
| "grad_norm": 7.563583850860596, | |
| "learning_rate": 6.320224719101124e-06, | |
| "loss": 3.2177, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 2.7083333333333335, | |
| "grad_norm": 5.385344982147217, | |
| "learning_rate": 5.407303370786517e-06, | |
| "loss": 3.1986, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 2.757575757575758, | |
| "grad_norm": 6.828423500061035, | |
| "learning_rate": 4.49438202247191e-06, | |
| "loss": 3.1137, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 2.8068181818181817, | |
| "grad_norm": 8.450451850891113, | |
| "learning_rate": 3.581460674157303e-06, | |
| "loss": 3.2061, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 2.856060606060606, | |
| "grad_norm": 8.725029945373535, | |
| "learning_rate": 2.6685393258426968e-06, | |
| "loss": 3.0328, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 2.9053030303030303, | |
| "grad_norm": 6.6716694831848145, | |
| "learning_rate": 1.7556179775280902e-06, | |
| "loss": 3.045, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 2.9545454545454546, | |
| "grad_norm": 8.45450496673584, | |
| "learning_rate": 8.426966292134832e-07, | |
| "loss": 3.0927, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.20643939393939395, | |
| "eval_f1_macro": 0.02830170335299915, | |
| "eval_f1_micro": 0.20643939393939395, | |
| "eval_f1_weighted": 0.09619191663674405, | |
| "eval_loss": 3.142681837081909, | |
| "eval_precision_macro": 0.03697093460585543, | |
| "eval_precision_micro": 0.20643939393939395, | |
| "eval_precision_weighted": 0.0998764466790715, | |
| "eval_recall_macro": 0.05223286714505793, | |
| "eval_recall_micro": 0.20643939393939395, | |
| "eval_recall_weighted": 0.20643939393939395, | |
| "eval_runtime": 55.8145, | |
| "eval_samples_per_second": 9.46, | |
| "eval_steps_per_second": 0.591, | |
| "step": 792 | |
| } | |
| ], | |
| "logging_steps": 13, | |
| "max_steps": 792, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3502825530667827e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |