| { | |
| "best_metric": 0.9045712351799011, | |
| "best_model_checkpoint": "autotrain-45ui2-ce6i6/checkpoint-303", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 303, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04950495049504951, | |
| "grad_norm": 6.708970069885254, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 1.084, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09900990099009901, | |
| "grad_norm": 6.528580188751221, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 1.0713, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1485148514851485, | |
| "grad_norm": 8.834931373596191, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 1.0738, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19801980198019803, | |
| "grad_norm": 14.24979305267334, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 1.0781, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24752475247524752, | |
| "grad_norm": 11.004271507263184, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 1.0461, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.297029702970297, | |
| "grad_norm": 10.543661117553711, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 1.0577, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3465346534653465, | |
| "grad_norm": 10.67061710357666, | |
| "learning_rate": 4.9264705882352944e-05, | |
| "loss": 1.0457, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": 9.407144546508789, | |
| "learning_rate": 4.834558823529412e-05, | |
| "loss": 1.0281, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44554455445544555, | |
| "grad_norm": 11.587020874023438, | |
| "learning_rate": 4.742647058823529e-05, | |
| "loss": 1.0348, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.49504950495049505, | |
| "grad_norm": 7.882496356964111, | |
| "learning_rate": 4.6507352941176475e-05, | |
| "loss": 1.0052, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5445544554455446, | |
| "grad_norm": 5.979856014251709, | |
| "learning_rate": 4.558823529411765e-05, | |
| "loss": 1.0017, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.594059405940594, | |
| "grad_norm": 10.8490629196167, | |
| "learning_rate": 4.4669117647058825e-05, | |
| "loss": 1.0315, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6435643564356436, | |
| "grad_norm": 15.452676773071289, | |
| "learning_rate": 4.375e-05, | |
| "loss": 1.0226, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.693069306930693, | |
| "grad_norm": 12.206670761108398, | |
| "learning_rate": 4.2830882352941174e-05, | |
| "loss": 1.0166, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7425742574257426, | |
| "grad_norm": 10.786033630371094, | |
| "learning_rate": 4.1911764705882356e-05, | |
| "loss": 0.99, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 7.7128472328186035, | |
| "learning_rate": 4.099264705882353e-05, | |
| "loss": 0.9677, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8415841584158416, | |
| "grad_norm": 10.314261436462402, | |
| "learning_rate": 4.007352941176471e-05, | |
| "loss": 1.0241, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8910891089108911, | |
| "grad_norm": 8.401986122131348, | |
| "learning_rate": 3.915441176470588e-05, | |
| "loss": 0.9343, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9405940594059405, | |
| "grad_norm": 10.88681697845459, | |
| "learning_rate": 3.8235294117647055e-05, | |
| "loss": 0.9632, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9900990099009901, | |
| "grad_norm": 8.095929145812988, | |
| "learning_rate": 3.731617647058824e-05, | |
| "loss": 0.9717, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5024875621890548, | |
| "eval_f1_macro": 0.23045267489711932, | |
| "eval_f1_micro": 0.5024875621890548, | |
| "eval_f1_weighted": 0.34789017873594985, | |
| "eval_loss": 0.9706681966781616, | |
| "eval_precision_macro": 0.27946127946127947, | |
| "eval_precision_micro": 0.5024875621890548, | |
| "eval_precision_weighted": 0.3856475199758782, | |
| "eval_recall_macro": 0.3310708898944193, | |
| "eval_recall_micro": 0.5024875621890548, | |
| "eval_recall_weighted": 0.5024875621890548, | |
| "eval_runtime": 23.9303, | |
| "eval_samples_per_second": 8.399, | |
| "eval_steps_per_second": 0.543, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.0396039603960396, | |
| "grad_norm": 20.65790367126465, | |
| "learning_rate": 3.639705882352941e-05, | |
| "loss": 0.9095, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.0891089108910892, | |
| "grad_norm": 12.614889144897461, | |
| "learning_rate": 3.5477941176470594e-05, | |
| "loss": 0.9053, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.1386138613861387, | |
| "grad_norm": 17.137245178222656, | |
| "learning_rate": 3.455882352941177e-05, | |
| "loss": 0.9321, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.188118811881188, | |
| "grad_norm": 10.98409652709961, | |
| "learning_rate": 3.363970588235294e-05, | |
| "loss": 0.977, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2376237623762376, | |
| "grad_norm": 6.829283714294434, | |
| "learning_rate": 3.272058823529412e-05, | |
| "loss": 0.9677, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.2871287128712872, | |
| "grad_norm": 7.726484298706055, | |
| "learning_rate": 3.180147058823529e-05, | |
| "loss": 0.9311, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.3366336633663367, | |
| "grad_norm": 9.711603164672852, | |
| "learning_rate": 3.0882352941176475e-05, | |
| "loss": 0.9655, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.386138613861386, | |
| "grad_norm": 9.904062271118164, | |
| "learning_rate": 2.9963235294117646e-05, | |
| "loss": 0.966, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4356435643564356, | |
| "grad_norm": 6.124065399169922, | |
| "learning_rate": 2.9044117647058828e-05, | |
| "loss": 0.9243, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.4851485148514851, | |
| "grad_norm": 6.805947303771973, | |
| "learning_rate": 2.8125000000000003e-05, | |
| "loss": 0.9398, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5346534653465347, | |
| "grad_norm": 16.854427337646484, | |
| "learning_rate": 2.7205882352941174e-05, | |
| "loss": 0.9272, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.5841584158415842, | |
| "grad_norm": 31.26000213623047, | |
| "learning_rate": 2.6286764705882356e-05, | |
| "loss": 0.9341, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6336633663366338, | |
| "grad_norm": 17.125900268554688, | |
| "learning_rate": 2.536764705882353e-05, | |
| "loss": 0.9858, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.6831683168316833, | |
| "grad_norm": 10.775436401367188, | |
| "learning_rate": 2.4448529411764705e-05, | |
| "loss": 0.8983, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.7326732673267327, | |
| "grad_norm": 11.20962905883789, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 0.9343, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.7821782178217822, | |
| "grad_norm": 20.909711837768555, | |
| "learning_rate": 2.261029411764706e-05, | |
| "loss": 0.9835, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8316831683168315, | |
| "grad_norm": 9.628500938415527, | |
| "learning_rate": 2.1691176470588237e-05, | |
| "loss": 0.9921, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.881188118811881, | |
| "grad_norm": 10.983928680419922, | |
| "learning_rate": 2.0772058823529415e-05, | |
| "loss": 0.9928, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.9306930693069306, | |
| "grad_norm": 18.505460739135742, | |
| "learning_rate": 1.9852941176470586e-05, | |
| "loss": 0.8767, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.9801980198019802, | |
| "grad_norm": 33.27599334716797, | |
| "learning_rate": 1.8933823529411765e-05, | |
| "loss": 0.9311, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5074626865671642, | |
| "eval_f1_macro": 0.22442244224422445, | |
| "eval_f1_micro": 0.5074626865671642, | |
| "eval_f1_weighted": 0.34165804640165515, | |
| "eval_loss": 0.9343423247337341, | |
| "eval_precision_macro": 0.1691542288557214, | |
| "eval_precision_micro": 0.5074626865671642, | |
| "eval_precision_weighted": 0.2575183782579639, | |
| "eval_recall_macro": 0.3333333333333333, | |
| "eval_recall_micro": 0.5074626865671642, | |
| "eval_recall_weighted": 0.5074626865671642, | |
| "eval_runtime": 25.7511, | |
| "eval_samples_per_second": 7.806, | |
| "eval_steps_per_second": 0.505, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.0297029702970297, | |
| "grad_norm": 16.32452392578125, | |
| "learning_rate": 1.8014705882352943e-05, | |
| "loss": 0.9146, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.0792079207920793, | |
| "grad_norm": 20.738645553588867, | |
| "learning_rate": 1.7095588235294118e-05, | |
| "loss": 0.9345, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.128712871287129, | |
| "grad_norm": 11.859530448913574, | |
| "learning_rate": 1.6176470588235296e-05, | |
| "loss": 0.892, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.1782178217821784, | |
| "grad_norm": 9.968949317932129, | |
| "learning_rate": 1.5257352941176473e-05, | |
| "loss": 0.9616, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.227722772277228, | |
| "grad_norm": 21.256311416625977, | |
| "learning_rate": 1.4338235294117647e-05, | |
| "loss": 0.9486, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.2772277227722775, | |
| "grad_norm": 8.86528491973877, | |
| "learning_rate": 1.3419117647058824e-05, | |
| "loss": 0.8652, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.3267326732673266, | |
| "grad_norm": 14.925371170043945, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.8879, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.376237623762376, | |
| "grad_norm": 19.46267318725586, | |
| "learning_rate": 1.1580882352941177e-05, | |
| "loss": 0.8791, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.4257425742574257, | |
| "grad_norm": 20.021953582763672, | |
| "learning_rate": 1.0661764705882354e-05, | |
| "loss": 0.9569, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.4752475247524752, | |
| "grad_norm": 11.353257179260254, | |
| "learning_rate": 9.74264705882353e-06, | |
| "loss": 0.8624, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.5247524752475248, | |
| "grad_norm": 14.153010368347168, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 0.9545, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.5742574257425743, | |
| "grad_norm": 5.752263069152832, | |
| "learning_rate": 7.904411764705882e-06, | |
| "loss": 0.8787, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.623762376237624, | |
| "grad_norm": 16.687803268432617, | |
| "learning_rate": 6.985294117647059e-06, | |
| "loss": 0.985, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.6732673267326734, | |
| "grad_norm": 20.000131607055664, | |
| "learning_rate": 6.066176470588236e-06, | |
| "loss": 0.9866, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.7227722772277225, | |
| "grad_norm": 7.210810661315918, | |
| "learning_rate": 5.147058823529412e-06, | |
| "loss": 0.8979, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.772277227722772, | |
| "grad_norm": 15.409006118774414, | |
| "learning_rate": 4.227941176470589e-06, | |
| "loss": 1.0289, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.8217821782178216, | |
| "grad_norm": 14.048492431640625, | |
| "learning_rate": 3.308823529411765e-06, | |
| "loss": 0.882, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.871287128712871, | |
| "grad_norm": 12.120644569396973, | |
| "learning_rate": 2.389705882352941e-06, | |
| "loss": 0.8982, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.9207920792079207, | |
| "grad_norm": 18.88411521911621, | |
| "learning_rate": 1.4705882352941177e-06, | |
| "loss": 0.9771, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.9702970297029703, | |
| "grad_norm": 13.562541961669922, | |
| "learning_rate": 5.514705882352942e-07, | |
| "loss": 0.8367, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5124378109452736, | |
| "eval_f1_macro": 0.23360438147930815, | |
| "eval_f1_micro": 0.5124378109452736, | |
| "eval_f1_weighted": 0.3526136606764151, | |
| "eval_loss": 0.9045712351799011, | |
| "eval_precision_macro": 0.5033333333333333, | |
| "eval_precision_micro": 0.5124378109452736, | |
| "eval_precision_weighted": 0.6468656716417911, | |
| "eval_recall_macro": 0.3376068376068376, | |
| "eval_recall_micro": 0.5124378109452736, | |
| "eval_recall_weighted": 0.5124378109452736, | |
| "eval_runtime": 22.9513, | |
| "eval_samples_per_second": 8.758, | |
| "eval_steps_per_second": 0.566, | |
| "step": 303 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 303, | |
| "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": 5.103312140783002e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |