| { | |
| "best_metric": 0.996666049268383, | |
| "best_model_checkpoint": "wav2vec2-base-finetuned-ks/checkpoint-421", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 421, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023752969121140142, | |
| "grad_norm": 3.1579225063323975, | |
| "learning_rate": 1.4218009478672985e-06, | |
| "loss": 0.69, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.047505938242280284, | |
| "grad_norm": 3.6760764122009277, | |
| "learning_rate": 2.843601895734597e-06, | |
| "loss": 0.6769, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07125890736342043, | |
| "grad_norm": 4.035228729248047, | |
| "learning_rate": 4.265402843601896e-06, | |
| "loss": 0.6482, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09501187648456057, | |
| "grad_norm": 5.847353458404541, | |
| "learning_rate": 5.687203791469194e-06, | |
| "loss": 0.6134, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1187648456057007, | |
| "grad_norm": 6.475171089172363, | |
| "learning_rate": 7.1090047393364935e-06, | |
| "loss": 0.5474, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14251781472684086, | |
| "grad_norm": 7.511197566986084, | |
| "learning_rate": 8.530805687203792e-06, | |
| "loss": 0.4575, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.166270783847981, | |
| "grad_norm": 12.910219192504883, | |
| "learning_rate": 9.95260663507109e-06, | |
| "loss": 0.3523, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19002375296912113, | |
| "grad_norm": 7.936448574066162, | |
| "learning_rate": 1.1374407582938388e-05, | |
| "loss": 0.2608, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21377672209026127, | |
| "grad_norm": 22.39988899230957, | |
| "learning_rate": 1.2796208530805688e-05, | |
| "loss": 0.2022, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2375296912114014, | |
| "grad_norm": 74.65003967285156, | |
| "learning_rate": 1.4218009478672987e-05, | |
| "loss": 0.162, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26128266033254155, | |
| "grad_norm": 2.993229389190674, | |
| "learning_rate": 1.5639810426540286e-05, | |
| "loss": 0.1456, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2850356294536817, | |
| "grad_norm": 5.789615154266357, | |
| "learning_rate": 1.7061611374407583e-05, | |
| "loss": 0.0996, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3087885985748218, | |
| "grad_norm": 49.30809020996094, | |
| "learning_rate": 1.8483412322274884e-05, | |
| "loss": 0.0696, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.332541567695962, | |
| "grad_norm": 1.4047824144363403, | |
| "learning_rate": 1.990521327014218e-05, | |
| "loss": 0.074, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35629453681710216, | |
| "grad_norm": 12.824111938476562, | |
| "learning_rate": 2.1327014218009478e-05, | |
| "loss": 0.0472, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.38004750593824227, | |
| "grad_norm": 1.3231825828552246, | |
| "learning_rate": 2.2748815165876775e-05, | |
| "loss": 0.0228, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.40380047505938244, | |
| "grad_norm": 0.6064344048500061, | |
| "learning_rate": 2.4170616113744076e-05, | |
| "loss": 0.0219, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.42755344418052255, | |
| "grad_norm": 0.5575058460235596, | |
| "learning_rate": 2.5592417061611376e-05, | |
| "loss": 0.0234, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4513064133016627, | |
| "grad_norm": 0.5436674952507019, | |
| "learning_rate": 2.7014218009478674e-05, | |
| "loss": 0.0222, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4750593824228028, | |
| "grad_norm": 53.069393157958984, | |
| "learning_rate": 2.8436018957345974e-05, | |
| "loss": 0.0291, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.498812351543943, | |
| "grad_norm": 61.781707763671875, | |
| "learning_rate": 2.9857819905213268e-05, | |
| "loss": 0.0629, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5225653206650831, | |
| "grad_norm": 0.30075332522392273, | |
| "learning_rate": 2.9857444561774023e-05, | |
| "loss": 0.0427, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5463182897862233, | |
| "grad_norm": 0.26658549904823303, | |
| "learning_rate": 2.969904963041183e-05, | |
| "loss": 0.0082, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5700712589073634, | |
| "grad_norm": 29.976423263549805, | |
| "learning_rate": 2.954065469904963e-05, | |
| "loss": 0.0328, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5938242280285035, | |
| "grad_norm": 8.100483894348145, | |
| "learning_rate": 2.9382259767687437e-05, | |
| "loss": 0.0257, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6175771971496437, | |
| "grad_norm": 215.22640991210938, | |
| "learning_rate": 2.9223864836325236e-05, | |
| "loss": 0.0236, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6413301662707839, | |
| "grad_norm": 0.21856270730495453, | |
| "learning_rate": 2.906546990496304e-05, | |
| "loss": 0.0073, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.665083135391924, | |
| "grad_norm": 203.41920471191406, | |
| "learning_rate": 2.8907074973600844e-05, | |
| "loss": 0.0214, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6888361045130641, | |
| "grad_norm": 0.17976981401443481, | |
| "learning_rate": 2.874868004223865e-05, | |
| "loss": 0.0179, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7125890736342043, | |
| "grad_norm": 87.75640106201172, | |
| "learning_rate": 2.8590285110876456e-05, | |
| "loss": 0.0127, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7363420427553444, | |
| "grad_norm": 0.13777469098567963, | |
| "learning_rate": 2.8431890179514255e-05, | |
| "loss": 0.0152, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7600950118764845, | |
| "grad_norm": 0.15721271932125092, | |
| "learning_rate": 2.827349524815206e-05, | |
| "loss": 0.0112, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7838479809976246, | |
| "grad_norm": 0.11672163009643555, | |
| "learning_rate": 2.8115100316789863e-05, | |
| "loss": 0.0064, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8076009501187649, | |
| "grad_norm": 0.12480423599481583, | |
| "learning_rate": 2.795670538542767e-05, | |
| "loss": 0.0134, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.831353919239905, | |
| "grad_norm": 0.0994909331202507, | |
| "learning_rate": 2.779831045406547e-05, | |
| "loss": 0.0335, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8551068883610451, | |
| "grad_norm": 0.24741250276565552, | |
| "learning_rate": 2.7639915522703273e-05, | |
| "loss": 0.0098, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8788598574821853, | |
| "grad_norm": 0.086154043674469, | |
| "learning_rate": 2.7481520591341076e-05, | |
| "loss": 0.0113, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9026128266033254, | |
| "grad_norm": 0.0834391638636589, | |
| "learning_rate": 2.732312565997888e-05, | |
| "loss": 0.001, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9263657957244655, | |
| "grad_norm": 0.07236961275339127, | |
| "learning_rate": 2.7164730728616687e-05, | |
| "loss": 0.0033, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9501187648456056, | |
| "grad_norm": 0.06638740003108978, | |
| "learning_rate": 2.700633579725449e-05, | |
| "loss": 0.0008, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9738717339667459, | |
| "grad_norm": 0.06140037626028061, | |
| "learning_rate": 2.6847940865892292e-05, | |
| "loss": 0.0007, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.997624703087886, | |
| "grad_norm": 0.8051447868347168, | |
| "learning_rate": 2.6689545934530094e-05, | |
| "loss": 0.0109, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.996666049268383, | |
| "eval_loss": 0.021043801680207253, | |
| "eval_runtime": 437.9848, | |
| "eval_samples_per_second": 24.654, | |
| "eval_steps_per_second": 0.772, | |
| "step": 421 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2105, | |
| "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": 2.4451992597902285e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |