| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 555, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018026137899954935, | |
| "grad_norm": 2.7659523487091064, | |
| "learning_rate": 4.9548736462093865e-05, | |
| "loss": 0.1292, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03605227579990987, | |
| "grad_norm": 1.665235161781311, | |
| "learning_rate": 4.909747292418773e-05, | |
| "loss": 0.0471, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054078413699864804, | |
| "grad_norm": 1.1857678890228271, | |
| "learning_rate": 4.864620938628159e-05, | |
| "loss": 0.0522, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07210455159981974, | |
| "grad_norm": 10.890019416809082, | |
| "learning_rate": 4.819494584837546e-05, | |
| "loss": 0.0968, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09013068949977468, | |
| "grad_norm": 7.386863708496094, | |
| "learning_rate": 4.7743682310469314e-05, | |
| "loss": 0.0392, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10815682739972961, | |
| "grad_norm": 8.243688583374023, | |
| "learning_rate": 4.7292418772563177e-05, | |
| "loss": 0.0603, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12618296529968454, | |
| "grad_norm": 0.6079480051994324, | |
| "learning_rate": 4.684115523465704e-05, | |
| "loss": 0.0417, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14420910319963948, | |
| "grad_norm": 3.4293453693389893, | |
| "learning_rate": 4.63898916967509e-05, | |
| "loss": 0.0479, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16223524109959442, | |
| "grad_norm": 0.9851968288421631, | |
| "learning_rate": 4.5938628158844764e-05, | |
| "loss": 0.0836, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18026137899954936, | |
| "grad_norm": 0.508313775062561, | |
| "learning_rate": 4.548736462093863e-05, | |
| "loss": 0.0207, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19828751689950427, | |
| "grad_norm": 0.2911165952682495, | |
| "learning_rate": 4.5036101083032495e-05, | |
| "loss": 0.0605, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.21631365479945922, | |
| "grad_norm": 0.7530468106269836, | |
| "learning_rate": 4.458483754512636e-05, | |
| "loss": 0.059, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23433979269941416, | |
| "grad_norm": 0.6048161387443542, | |
| "learning_rate": 4.413357400722022e-05, | |
| "loss": 0.0426, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.25236593059936907, | |
| "grad_norm": 7.237401485443115, | |
| "learning_rate": 4.368231046931408e-05, | |
| "loss": 0.0553, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.270392068499324, | |
| "grad_norm": 4.217318058013916, | |
| "learning_rate": 4.3231046931407945e-05, | |
| "loss": 0.0314, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.28841820639927895, | |
| "grad_norm": 3.7883381843566895, | |
| "learning_rate": 4.277978339350181e-05, | |
| "loss": 0.0422, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3064443442992339, | |
| "grad_norm": 7.496313571929932, | |
| "learning_rate": 4.232851985559567e-05, | |
| "loss": 0.0422, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.32447048219918884, | |
| "grad_norm": 1.371532678604126, | |
| "learning_rate": 4.187725631768953e-05, | |
| "loss": 0.0574, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3424966200991438, | |
| "grad_norm": 1.0054638385772705, | |
| "learning_rate": 4.1425992779783394e-05, | |
| "loss": 0.0528, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3605227579990987, | |
| "grad_norm": 6.67033052444458, | |
| "learning_rate": 4.0974729241877256e-05, | |
| "loss": 0.0528, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3785488958990536, | |
| "grad_norm": 2.814408779144287, | |
| "learning_rate": 4.052346570397112e-05, | |
| "loss": 0.0514, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.39657503379900855, | |
| "grad_norm": 0.7789732217788696, | |
| "learning_rate": 4.007220216606498e-05, | |
| "loss": 0.0241, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4146011716989635, | |
| "grad_norm": 5.927615642547607, | |
| "learning_rate": 3.962093862815885e-05, | |
| "loss": 0.0742, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.43262730959891843, | |
| "grad_norm": 4.2895307540893555, | |
| "learning_rate": 3.916967509025271e-05, | |
| "loss": 0.0487, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.45065344749887337, | |
| "grad_norm": 0.24509297311306, | |
| "learning_rate": 3.8718411552346575e-05, | |
| "loss": 0.0185, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4686795853988283, | |
| "grad_norm": 0.12779287993907928, | |
| "learning_rate": 3.826714801444044e-05, | |
| "loss": 0.011, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.48670572329878325, | |
| "grad_norm": 3.5602619647979736, | |
| "learning_rate": 3.78158844765343e-05, | |
| "loss": 0.0605, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5047318611987381, | |
| "grad_norm": 7.118227005004883, | |
| "learning_rate": 3.7364620938628155e-05, | |
| "loss": 0.062, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5227579990986931, | |
| "grad_norm": 0.6336535215377808, | |
| "learning_rate": 3.6913357400722025e-05, | |
| "loss": 0.0278, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.540784136998648, | |
| "grad_norm": 3.6674723625183105, | |
| "learning_rate": 3.646209386281589e-05, | |
| "loss": 0.0519, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.558810274898603, | |
| "grad_norm": 7.329596519470215, | |
| "learning_rate": 3.601083032490975e-05, | |
| "loss": 0.0337, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5768364127985579, | |
| "grad_norm": 1.3290072679519653, | |
| "learning_rate": 3.555956678700361e-05, | |
| "loss": 0.0528, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5948625506985128, | |
| "grad_norm": 1.0643926858901978, | |
| "learning_rate": 3.5108303249097474e-05, | |
| "loss": 0.0592, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6128886885984678, | |
| "grad_norm": 1.0425355434417725, | |
| "learning_rate": 3.4657039711191336e-05, | |
| "loss": 0.0485, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "grad_norm": 3.1306347846984863, | |
| "learning_rate": 3.42057761732852e-05, | |
| "loss": 0.0221, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6489409643983777, | |
| "grad_norm": 0.37137073278427124, | |
| "learning_rate": 3.375451263537907e-05, | |
| "loss": 0.0401, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6669671022983326, | |
| "grad_norm": 0.29780980944633484, | |
| "learning_rate": 3.330324909747293e-05, | |
| "loss": 0.0374, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6849932401982876, | |
| "grad_norm": 1.7151790857315063, | |
| "learning_rate": 3.2851985559566786e-05, | |
| "loss": 0.0364, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7030193780982424, | |
| "grad_norm": 0.6182792782783508, | |
| "learning_rate": 3.240072202166065e-05, | |
| "loss": 0.0253, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7210455159981974, | |
| "grad_norm": 0.5171168446540833, | |
| "learning_rate": 3.194945848375451e-05, | |
| "loss": 0.0234, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7390716538981523, | |
| "grad_norm": 3.500291585922241, | |
| "learning_rate": 3.149819494584837e-05, | |
| "loss": 0.048, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7570977917981072, | |
| "grad_norm": 4.192553520202637, | |
| "learning_rate": 3.104693140794224e-05, | |
| "loss": 0.0191, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7751239296980622, | |
| "grad_norm": 0.2889997661113739, | |
| "learning_rate": 3.0595667870036104e-05, | |
| "loss": 0.073, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7931500675980171, | |
| "grad_norm": 0.731918215751648, | |
| "learning_rate": 3.0144404332129967e-05, | |
| "loss": 0.0269, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8111762054979721, | |
| "grad_norm": 3.4268507957458496, | |
| "learning_rate": 2.969314079422383e-05, | |
| "loss": 0.0634, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.829202343397927, | |
| "grad_norm": 0.8300638794898987, | |
| "learning_rate": 2.924187725631769e-05, | |
| "loss": 0.0382, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.847228481297882, | |
| "grad_norm": 0.6669813990592957, | |
| "learning_rate": 2.879061371841155e-05, | |
| "loss": 0.0678, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.8652546191978369, | |
| "grad_norm": 1.2740308046340942, | |
| "learning_rate": 2.8339350180505413e-05, | |
| "loss": 0.0415, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8832807570977917, | |
| "grad_norm": 3.1045358180999756, | |
| "learning_rate": 2.7888086642599282e-05, | |
| "loss": 0.031, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9013068949977467, | |
| "grad_norm": 3.4434397220611572, | |
| "learning_rate": 2.7436823104693144e-05, | |
| "loss": 0.051, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9193330328977016, | |
| "grad_norm": 8.245412826538086, | |
| "learning_rate": 2.6985559566787007e-05, | |
| "loss": 0.0209, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.9373591707976566, | |
| "grad_norm": 1.196775197982788, | |
| "learning_rate": 2.6534296028880866e-05, | |
| "loss": 0.0416, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9553853086976115, | |
| "grad_norm": 0.6041325330734253, | |
| "learning_rate": 2.6083032490974728e-05, | |
| "loss": 0.0503, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9734114465975665, | |
| "grad_norm": 0.4048420190811157, | |
| "learning_rate": 2.563176895306859e-05, | |
| "loss": 0.0298, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9914375844975214, | |
| "grad_norm": 0.48081880807876587, | |
| "learning_rate": 2.518050541516246e-05, | |
| "loss": 0.0507, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.0, | |
| "eval_fn": 43, | |
| "eval_fp": 0, | |
| "eval_loss": 0.042322322726249695, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 14.9507, | |
| "eval_samples_per_second": 312.56, | |
| "eval_steps_per_second": 39.129, | |
| "eval_tn": 4630, | |
| "eval_tp": 0, | |
| "step": 555 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1108, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 4670747454750720.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |