| { | |
| "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, | |
| "eval_f1": 0.1456953642384106, | |
| "eval_fn": 11, | |
| "eval_fp": 4117, | |
| "eval_loss": 0.7862394452095032, | |
| "eval_precision": 0.07876482434549116, | |
| "eval_recall": 0.9696969696969697, | |
| "eval_runtime": 48.4563, | |
| "eval_samples_per_second": 96.437, | |
| "eval_steps_per_second": 6.047, | |
| "eval_tn": 193, | |
| "eval_tp": 352, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 0.018026137899954935, | |
| "grad_norm": 5.399981498718262, | |
| "learning_rate": 4.9548736462093865e-05, | |
| "loss": 0.5179, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03605227579990987, | |
| "grad_norm": 1.6319377422332764, | |
| "learning_rate": 4.909747292418773e-05, | |
| "loss": 0.2969, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054078413699864804, | |
| "grad_norm": 1.8271431922912598, | |
| "learning_rate": 4.864620938628159e-05, | |
| "loss": 0.3075, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07210455159981974, | |
| "grad_norm": 2.5912694931030273, | |
| "learning_rate": 4.819494584837546e-05, | |
| "loss": 0.3096, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09013068949977468, | |
| "grad_norm": 3.3950061798095703, | |
| "learning_rate": 4.7743682310469314e-05, | |
| "loss": 0.2585, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10815682739972961, | |
| "grad_norm": 1.6037261486053467, | |
| "learning_rate": 4.7292418772563177e-05, | |
| "loss": 0.2461, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12618296529968454, | |
| "grad_norm": 3.6747143268585205, | |
| "learning_rate": 4.684115523465704e-05, | |
| "loss": 0.2803, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14420910319963948, | |
| "grad_norm": 6.330898284912109, | |
| "learning_rate": 4.63898916967509e-05, | |
| "loss": 0.2735, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16223524109959442, | |
| "grad_norm": 4.724136829376221, | |
| "learning_rate": 4.5938628158844764e-05, | |
| "loss": 0.2551, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18026137899954936, | |
| "grad_norm": 3.852949619293213, | |
| "learning_rate": 4.548736462093863e-05, | |
| "loss": 0.2286, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19828751689950427, | |
| "grad_norm": 10.743219375610352, | |
| "learning_rate": 4.5036101083032495e-05, | |
| "loss": 0.2511, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.21631365479945922, | |
| "grad_norm": 24.62398910522461, | |
| "learning_rate": 4.458483754512636e-05, | |
| "loss": 0.1756, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23433979269941416, | |
| "grad_norm": 6.864269256591797, | |
| "learning_rate": 4.413357400722022e-05, | |
| "loss": 0.1947, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.25236593059936907, | |
| "grad_norm": 11.810012817382812, | |
| "learning_rate": 4.368231046931408e-05, | |
| "loss": 0.1976, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.270392068499324, | |
| "grad_norm": 4.794726848602295, | |
| "learning_rate": 4.3231046931407945e-05, | |
| "loss": 0.2081, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.28841820639927895, | |
| "grad_norm": 7.1115875244140625, | |
| "learning_rate": 4.277978339350181e-05, | |
| "loss": 0.2055, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3064443442992339, | |
| "grad_norm": 6.199843883514404, | |
| "learning_rate": 4.232851985559567e-05, | |
| "loss": 0.1764, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.32447048219918884, | |
| "grad_norm": 5.7516679763793945, | |
| "learning_rate": 4.187725631768953e-05, | |
| "loss": 0.185, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3424966200991438, | |
| "grad_norm": 17.204120635986328, | |
| "learning_rate": 4.1425992779783394e-05, | |
| "loss": 0.175, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3605227579990987, | |
| "grad_norm": 6.416110038757324, | |
| "learning_rate": 4.0974729241877256e-05, | |
| "loss": 0.1197, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3785488958990536, | |
| "grad_norm": 8.525187492370605, | |
| "learning_rate": 4.052346570397112e-05, | |
| "loss": 0.1968, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.39657503379900855, | |
| "grad_norm": 42.04795455932617, | |
| "learning_rate": 4.007220216606498e-05, | |
| "loss": 0.1718, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4146011716989635, | |
| "grad_norm": 4.502872467041016, | |
| "learning_rate": 3.962093862815885e-05, | |
| "loss": 0.1442, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.43262730959891843, | |
| "grad_norm": 3.215198278427124, | |
| "learning_rate": 3.916967509025271e-05, | |
| "loss": 0.1675, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.45065344749887337, | |
| "grad_norm": 6.314309120178223, | |
| "learning_rate": 3.8718411552346575e-05, | |
| "loss": 0.1492, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4686795853988283, | |
| "grad_norm": 8.839702606201172, | |
| "learning_rate": 3.826714801444044e-05, | |
| "loss": 0.1399, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.48670572329878325, | |
| "grad_norm": 183.9261016845703, | |
| "learning_rate": 3.78158844765343e-05, | |
| "loss": 0.1801, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5047318611987381, | |
| "grad_norm": 5.393545150756836, | |
| "learning_rate": 3.7364620938628155e-05, | |
| "loss": 0.1353, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5227579990986931, | |
| "grad_norm": 3.587885856628418, | |
| "learning_rate": 3.6913357400722025e-05, | |
| "loss": 0.1428, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.540784136998648, | |
| "grad_norm": 9.456450462341309, | |
| "learning_rate": 3.646209386281589e-05, | |
| "loss": 0.1758, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.558810274898603, | |
| "grad_norm": 4.051924705505371, | |
| "learning_rate": 3.601083032490975e-05, | |
| "loss": 0.1874, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5768364127985579, | |
| "grad_norm": 6.4390363693237305, | |
| "learning_rate": 3.555956678700361e-05, | |
| "loss": 0.1472, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5948625506985128, | |
| "grad_norm": 3.86102557182312, | |
| "learning_rate": 3.5108303249097474e-05, | |
| "loss": 0.1659, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6128886885984678, | |
| "grad_norm": 6.6616644859313965, | |
| "learning_rate": 3.4657039711191336e-05, | |
| "loss": 0.191, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "grad_norm": 6.867959976196289, | |
| "learning_rate": 3.42057761732852e-05, | |
| "loss": 0.1343, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6489409643983777, | |
| "grad_norm": 8.724226951599121, | |
| "learning_rate": 3.375451263537907e-05, | |
| "loss": 0.145, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6669671022983326, | |
| "grad_norm": 3.5500874519348145, | |
| "learning_rate": 3.330324909747293e-05, | |
| "loss": 0.1153, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6849932401982876, | |
| "grad_norm": 9.760895729064941, | |
| "learning_rate": 3.2851985559566786e-05, | |
| "loss": 0.1362, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7030193780982424, | |
| "grad_norm": 3.9465765953063965, | |
| "learning_rate": 3.240072202166065e-05, | |
| "loss": 0.1281, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7210455159981974, | |
| "grad_norm": 3.495382070541382, | |
| "learning_rate": 3.194945848375451e-05, | |
| "loss": 0.1792, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7390716538981523, | |
| "grad_norm": 2.8898510932922363, | |
| "learning_rate": 3.149819494584837e-05, | |
| "loss": 0.1085, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7570977917981072, | |
| "grad_norm": 3.3261382579803467, | |
| "learning_rate": 3.104693140794224e-05, | |
| "loss": 0.203, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7751239296980622, | |
| "grad_norm": 3.417875051498413, | |
| "learning_rate": 3.0595667870036104e-05, | |
| "loss": 0.1491, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7931500675980171, | |
| "grad_norm": 7.868630409240723, | |
| "learning_rate": 3.0144404332129967e-05, | |
| "loss": 0.1777, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8111762054979721, | |
| "grad_norm": 2.16607403755188, | |
| "learning_rate": 2.969314079422383e-05, | |
| "loss": 0.1406, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.829202343397927, | |
| "grad_norm": 5.121480464935303, | |
| "learning_rate": 2.924187725631769e-05, | |
| "loss": 0.1387, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.847228481297882, | |
| "grad_norm": 6.610152244567871, | |
| "learning_rate": 2.879061371841155e-05, | |
| "loss": 0.1158, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.8652546191978369, | |
| "grad_norm": 5.962329387664795, | |
| "learning_rate": 2.8339350180505413e-05, | |
| "loss": 0.127, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8832807570977917, | |
| "grad_norm": 5.11064338684082, | |
| "learning_rate": 2.7888086642599282e-05, | |
| "loss": 0.1232, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9013068949977467, | |
| "grad_norm": 5.128263473510742, | |
| "learning_rate": 2.7436823104693144e-05, | |
| "loss": 0.1084, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9193330328977016, | |
| "grad_norm": 8.249767303466797, | |
| "learning_rate": 2.6985559566787007e-05, | |
| "loss": 0.1453, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.9373591707976566, | |
| "grad_norm": 14.850152969360352, | |
| "learning_rate": 2.6534296028880866e-05, | |
| "loss": 0.1102, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9553853086976115, | |
| "grad_norm": 4.934476852416992, | |
| "learning_rate": 2.6083032490974728e-05, | |
| "loss": 0.1493, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9734114465975665, | |
| "grad_norm": 6.984730243682861, | |
| "learning_rate": 2.563176895306859e-05, | |
| "loss": 0.1344, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9914375844975214, | |
| "grad_norm": 4.595370292663574, | |
| "learning_rate": 2.518050541516246e-05, | |
| "loss": 0.1246, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.7272727272727273, | |
| "eval_fn": 95, | |
| "eval_fp": 106, | |
| "eval_loss": 0.11311017721891403, | |
| "eval_precision": 0.7165775401069518, | |
| "eval_recall": 0.7382920110192838, | |
| "eval_runtime": 56.8141, | |
| "eval_samples_per_second": 82.251, | |
| "eval_steps_per_second": 5.157, | |
| "eval_tn": 4204, | |
| "eval_tp": 268, | |
| "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": 3.84912704311296e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |