| { | |
| "best_metric": 0.05124881863594055, | |
| "best_model_checkpoint": "my_Pytorch_pii_model/checkpoint-20926", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 20926, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04778744146038421, | |
| "grad_norm": 1.7837579250335693, | |
| "learning_rate": 1.997195242749148e-05, | |
| "loss": 0.8081, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09557488292076842, | |
| "grad_norm": 2.2397186756134033, | |
| "learning_rate": 1.9887742837017725e-05, | |
| "loss": 0.2477, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.14336232438115262, | |
| "grad_norm": 1.895089030265808, | |
| "learning_rate": 1.9747845385097936e-05, | |
| "loss": 0.1609, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.19114976584153684, | |
| "grad_norm": 1.4316082000732422, | |
| "learning_rate": 1.9553047975508295e-05, | |
| "loss": 0.1269, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.23893720730192106, | |
| "grad_norm": 0.5299736857414246, | |
| "learning_rate": 1.9304447709107316e-05, | |
| "loss": 0.1052, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.28672464876230525, | |
| "grad_norm": 1.0913931131362915, | |
| "learning_rate": 1.9003444704953408e-05, | |
| "loss": 0.0967, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.33451209022268946, | |
| "grad_norm": 1.8749414682388306, | |
| "learning_rate": 1.865248697176191e-05, | |
| "loss": 0.0889, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.3822995316830737, | |
| "grad_norm": 2.014411211013794, | |
| "learning_rate": 1.825214512447262e-05, | |
| "loss": 0.0843, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.4300869731434579, | |
| "grad_norm": 0.6492653489112854, | |
| "learning_rate": 1.780532711756845e-05, | |
| "loss": 0.0812, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4778744146038421, | |
| "grad_norm": 1.5026785135269165, | |
| "learning_rate": 1.7314549434302465e-05, | |
| "loss": 0.0779, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.5256618560642263, | |
| "grad_norm": 0.5166222453117371, | |
| "learning_rate": 1.6782576139241983e-05, | |
| "loss": 0.0719, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.5734492975246105, | |
| "grad_norm": 0.9983482956886292, | |
| "learning_rate": 1.62124033110307e-05, | |
| "loss": 0.0746, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.6212367389849948, | |
| "grad_norm": 0.8525393605232239, | |
| "learning_rate": 1.5608485174626132e-05, | |
| "loss": 0.0713, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.6690241804453789, | |
| "grad_norm": 1.3193893432617188, | |
| "learning_rate": 1.4971803628070286e-05, | |
| "loss": 0.067, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.7168116219057632, | |
| "grad_norm": 1.7481768131256104, | |
| "learning_rate": 1.4307120836322233e-05, | |
| "loss": 0.0677, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.7645990633661474, | |
| "grad_norm": 0.7293727993965149, | |
| "learning_rate": 1.3618180299169794e-05, | |
| "loss": 0.0649, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.8123865048265316, | |
| "grad_norm": 0.4748859405517578, | |
| "learning_rate": 1.2908862136252995e-05, | |
| "loss": 0.0675, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.8601739462869158, | |
| "grad_norm": 0.9915094971656799, | |
| "learning_rate": 1.218462628244987e-05, | |
| "loss": 0.0648, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.9079613877473001, | |
| "grad_norm": 2.1113200187683105, | |
| "learning_rate": 1.1446650257897558e-05, | |
| "loss": 0.0638, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.9557488292076842, | |
| "grad_norm": 0.7165895700454712, | |
| "learning_rate": 1.0700526685370893e-05, | |
| "loss": 0.0615, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9751704843504109, | |
| "eval_f1": 0.9315204370483973, | |
| "eval_loss": 0.05543896183371544, | |
| "eval_precision": 0.9214454994188416, | |
| "eval_recall": 0.9418181257135804, | |
| "eval_runtime": 190.6513, | |
| "eval_samples_per_second": 109.766, | |
| "eval_steps_per_second": 6.861, | |
| "step": 10463 | |
| }, | |
| { | |
| "epoch": 1.0035362706680684, | |
| "grad_norm": 0.7908827066421509, | |
| "learning_rate": 9.950457739907535e-06, | |
| "loss": 0.0591, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.0513237121284527, | |
| "grad_norm": 0.8281264901161194, | |
| "learning_rate": 9.200667816922936e-06, | |
| "loss": 0.0559, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.099111153588837, | |
| "grad_norm": 0.6375882625579834, | |
| "learning_rate": 8.456863027173128e-06, | |
| "loss": 0.0528, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.146898595049221, | |
| "grad_norm": 0.8089446425437927, | |
| "learning_rate": 7.720252707524596e-06, | |
| "loss": 0.0561, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.1946860365096053, | |
| "grad_norm": 0.5335150957107544, | |
| "learning_rate": 6.9964819462513174e-06, | |
| "loss": 0.0563, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.2424734779699895, | |
| "grad_norm": 0.7552749514579773, | |
| "learning_rate": 6.289627027145937e-06, | |
| "loss": 0.053, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.2902609194303736, | |
| "grad_norm": 1.121811866760254, | |
| "learning_rate": 5.603668963817577e-06, | |
| "loss": 0.0537, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.3380483608907578, | |
| "grad_norm": 1.5103745460510254, | |
| "learning_rate": 4.942471078585398e-06, | |
| "loss": 0.0529, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.3858358023511421, | |
| "grad_norm": 1.125802755355835, | |
| "learning_rate": 4.309757244210676e-06, | |
| "loss": 0.0558, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.4336232438115264, | |
| "grad_norm": 2.0246198177337646, | |
| "learning_rate": 3.709090911010067e-06, | |
| "loss": 0.051, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.4814106852719107, | |
| "grad_norm": 0.31454652547836304, | |
| "learning_rate": 3.1449479986513345e-06, | |
| "loss": 0.0503, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.5291981267322947, | |
| "grad_norm": 1.1729323863983154, | |
| "learning_rate": 2.618245735460083e-06, | |
| "loss": 0.0496, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.576985568192679, | |
| "grad_norm": 1.942895531654358, | |
| "learning_rate": 2.1331175823046777e-06, | |
| "loss": 0.0508, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.624773009653063, | |
| "grad_norm": 0.7527912259101868, | |
| "learning_rate": 1.692295785545267e-06, | |
| "loss": 0.0474, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.6725604511134473, | |
| "grad_norm": 0.9754999279975891, | |
| "learning_rate": 1.299002907484831e-06, | |
| "loss": 0.0505, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.7203478925738316, | |
| "grad_norm": 1.4431662559509277, | |
| "learning_rate": 9.538783949020436e-07, | |
| "loss": 0.0507, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.7681353340342159, | |
| "grad_norm": 0.9095632433891296, | |
| "learning_rate": 6.602380824095455e-07, | |
| "loss": 0.0484, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.8159227754946001, | |
| "grad_norm": 0.47108370065689087, | |
| "learning_rate": 4.185593937350141e-07, | |
| "loss": 0.0503, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.8637102169549842, | |
| "grad_norm": 1.9777565002441406, | |
| "learning_rate": 2.3084346943755388e-07, | |
| "loss": 0.0492, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.9114976584153685, | |
| "grad_norm": 0.7806472182273865, | |
| "learning_rate": 9.814752738334654e-08, | |
| "loss": 0.0493, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.9592850998757525, | |
| "grad_norm": 0.42741918563842773, | |
| "learning_rate": 2.1218912376697043e-08, | |
| "loss": 0.051, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9768446160123027, | |
| "eval_f1": 0.9388393674827523, | |
| "eval_loss": 0.05124881863594055, | |
| "eval_precision": 0.9288864055090761, | |
| "eval_recall": 0.9490079303854105, | |
| "eval_runtime": 115.4429, | |
| "eval_samples_per_second": 181.276, | |
| "eval_steps_per_second": 11.33, | |
| "step": 20926 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 20926, | |
| "total_flos": 1.64925784065024e+16, | |
| "train_loss": 0.0881471913733378, | |
| "train_runtime": 3285.9718, | |
| "train_samples_per_second": 101.893, | |
| "train_steps_per_second": 6.368 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9768446160123027, | |
| "eval_f1": 0.9388393674827523, | |
| "eval_loss": 0.05124881863594055, | |
| "eval_precision": 0.9288864055090761, | |
| "eval_recall": 0.9490079303854105, | |
| "eval_runtime": 122.2255, | |
| "eval_samples_per_second": 171.216, | |
| "eval_steps_per_second": 10.702, | |
| "step": 20926 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 20926, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 1.64925784065024e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |