Instructions to use dzungpham/graphcodebert-code-classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dzungpham/graphcodebert-code-classification with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dzungpham/graphcodebert-code-classification", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": 2000, | |
| "best_metric": 0.970164263786433, | |
| "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-2000", | |
| "epoch": 0.128, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00064, | |
| "grad_norm": 3.3732223510742188, | |
| "learning_rate": 9.6e-08, | |
| "loss": 0.2065, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00128, | |
| "grad_norm": 2.8028833866119385, | |
| "learning_rate": 2.0266666666666668e-07, | |
| "loss": 0.2003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00192, | |
| "grad_norm": 3.137962818145752, | |
| "learning_rate": 3.0933333333333335e-07, | |
| "loss": 0.2119, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00256, | |
| "grad_norm": 2.2841057777404785, | |
| "learning_rate": 4.16e-07, | |
| "loss": 0.1858, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0032, | |
| "grad_norm": 2.4040842056274414, | |
| "learning_rate": 5.226666666666667e-07, | |
| "loss": 0.1755, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00384, | |
| "grad_norm": 2.1078808307647705, | |
| "learning_rate": 6.293333333333334e-07, | |
| "loss": 0.1836, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00448, | |
| "grad_norm": 2.1723551750183105, | |
| "learning_rate": 7.36e-07, | |
| "loss": 0.182, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.00512, | |
| "grad_norm": 3.8697516918182373, | |
| "learning_rate": 8.426666666666668e-07, | |
| "loss": 0.1893, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.00576, | |
| "grad_norm": 2.2711849212646484, | |
| "learning_rate": 9.493333333333334e-07, | |
| "loss": 0.1645, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0064, | |
| "grad_norm": 2.9138245582580566, | |
| "learning_rate": 1.0560000000000001e-06, | |
| "loss": 0.1753, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.00704, | |
| "grad_norm": 2.136301279067993, | |
| "learning_rate": 1.1626666666666667e-06, | |
| "loss": 0.1639, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.00768, | |
| "grad_norm": 3.216343641281128, | |
| "learning_rate": 1.2693333333333335e-06, | |
| "loss": 0.1623, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.00832, | |
| "grad_norm": 3.192094326019287, | |
| "learning_rate": 1.376e-06, | |
| "loss": 0.1607, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.00896, | |
| "grad_norm": 4.722238540649414, | |
| "learning_rate": 1.4826666666666666e-06, | |
| "loss": 0.1653, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0096, | |
| "grad_norm": 4.088972568511963, | |
| "learning_rate": 1.5893333333333336e-06, | |
| "loss": 0.1557, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01024, | |
| "grad_norm": 2.2773237228393555, | |
| "learning_rate": 1.6960000000000002e-06, | |
| "loss": 0.1634, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.01088, | |
| "grad_norm": 2.53987193107605, | |
| "learning_rate": 1.8026666666666667e-06, | |
| "loss": 0.1435, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01152, | |
| "grad_norm": 3.688382387161255, | |
| "learning_rate": 1.9093333333333335e-06, | |
| "loss": 0.1396, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01216, | |
| "grad_norm": 1.8855538368225098, | |
| "learning_rate": 2.0160000000000003e-06, | |
| "loss": 0.1476, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0128, | |
| "grad_norm": 2.2272040843963623, | |
| "learning_rate": 2.1226666666666666e-06, | |
| "loss": 0.144, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01344, | |
| "grad_norm": 3.505934476852417, | |
| "learning_rate": 2.229333333333334e-06, | |
| "loss": 0.1306, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.01408, | |
| "grad_norm": 1.8632491827011108, | |
| "learning_rate": 2.336e-06, | |
| "loss": 0.1504, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.01472, | |
| "grad_norm": 2.191713333129883, | |
| "learning_rate": 2.442666666666667e-06, | |
| "loss": 0.1346, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.01536, | |
| "grad_norm": 1.9042261838912964, | |
| "learning_rate": 2.5493333333333337e-06, | |
| "loss": 0.135, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 2.266148090362549, | |
| "learning_rate": 2.656e-06, | |
| "loss": 0.1356, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.01664, | |
| "grad_norm": 2.4776418209075928, | |
| "learning_rate": 2.762666666666667e-06, | |
| "loss": 0.129, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.01728, | |
| "grad_norm": 2.340693712234497, | |
| "learning_rate": 2.8693333333333336e-06, | |
| "loss": 0.1236, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.01792, | |
| "grad_norm": 1.6849262714385986, | |
| "learning_rate": 2.976e-06, | |
| "loss": 0.1152, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.01856, | |
| "grad_norm": 3.5535154342651367, | |
| "learning_rate": 3.082666666666667e-06, | |
| "loss": 0.1335, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.0192, | |
| "grad_norm": 2.9307031631469727, | |
| "learning_rate": 3.1893333333333335e-06, | |
| "loss": 0.1136, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01984, | |
| "grad_norm": 3.0100226402282715, | |
| "learning_rate": 3.2960000000000003e-06, | |
| "loss": 0.1186, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.02048, | |
| "grad_norm": 2.088911771774292, | |
| "learning_rate": 3.402666666666667e-06, | |
| "loss": 0.1051, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.02112, | |
| "grad_norm": 4.332556247711182, | |
| "learning_rate": 3.5093333333333334e-06, | |
| "loss": 0.1075, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.02176, | |
| "grad_norm": 2.954036235809326, | |
| "learning_rate": 3.616e-06, | |
| "loss": 0.11, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.0224, | |
| "grad_norm": 2.262308359146118, | |
| "learning_rate": 3.7226666666666674e-06, | |
| "loss": 0.1057, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.02304, | |
| "grad_norm": 1.5145989656448364, | |
| "learning_rate": 3.829333333333334e-06, | |
| "loss": 0.1049, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.02368, | |
| "grad_norm": 1.740663766860962, | |
| "learning_rate": 3.936e-06, | |
| "loss": 0.0964, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.02432, | |
| "grad_norm": 1.7438851594924927, | |
| "learning_rate": 4.042666666666667e-06, | |
| "loss": 0.0936, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.02496, | |
| "grad_norm": 3.946115493774414, | |
| "learning_rate": 4.149333333333334e-06, | |
| "loss": 0.1038, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.0256, | |
| "grad_norm": 5.289428234100342, | |
| "learning_rate": 4.256e-06, | |
| "loss": 0.1015, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02624, | |
| "grad_norm": 1.9344863891601562, | |
| "learning_rate": 4.362666666666667e-06, | |
| "loss": 0.0855, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.02688, | |
| "grad_norm": 7.482412338256836, | |
| "learning_rate": 4.469333333333334e-06, | |
| "loss": 0.1031, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.02752, | |
| "grad_norm": 2.5646328926086426, | |
| "learning_rate": 4.576000000000001e-06, | |
| "loss": 0.0777, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.02816, | |
| "grad_norm": 1.473496437072754, | |
| "learning_rate": 4.682666666666667e-06, | |
| "loss": 0.0854, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.0288, | |
| "grad_norm": 2.204341411590576, | |
| "learning_rate": 4.7893333333333334e-06, | |
| "loss": 0.0739, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.02944, | |
| "grad_norm": 3.1363987922668457, | |
| "learning_rate": 4.896e-06, | |
| "loss": 0.0886, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.03008, | |
| "grad_norm": 2.0473029613494873, | |
| "learning_rate": 5.002666666666667e-06, | |
| "loss": 0.0794, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.03072, | |
| "grad_norm": 1.6088207960128784, | |
| "learning_rate": 5.109333333333334e-06, | |
| "loss": 0.0604, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.03136, | |
| "grad_norm": 2.974717617034912, | |
| "learning_rate": 5.216e-06, | |
| "loss": 0.0827, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 6.114630699157715, | |
| "learning_rate": 5.322666666666667e-06, | |
| "loss": 0.0631, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "eval_accuracy": 0.88603, | |
| "eval_f1_weighted": 0.8857328199768308, | |
| "eval_loss": 0.08366190642118454, | |
| "eval_macro_f1": 0.8859061279979327, | |
| "eval_precision": 0.8966428429175579, | |
| "eval_recall": 0.88603, | |
| "eval_runtime": 1629.6546, | |
| "eval_samples_per_second": 61.363, | |
| "eval_steps_per_second": 0.959, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03264, | |
| "grad_norm": 1.4639947414398193, | |
| "learning_rate": 5.429333333333334e-06, | |
| "loss": 0.0724, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.03328, | |
| "grad_norm": 4.234114646911621, | |
| "learning_rate": 5.536e-06, | |
| "loss": 0.0737, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.03392, | |
| "grad_norm": 1.9391822814941406, | |
| "learning_rate": 5.642666666666668e-06, | |
| "loss": 0.0875, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.03456, | |
| "grad_norm": 2.0388095378875732, | |
| "learning_rate": 5.7493333333333336e-06, | |
| "loss": 0.0661, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.0352, | |
| "grad_norm": 1.9697074890136719, | |
| "learning_rate": 5.856e-06, | |
| "loss": 0.0647, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.03584, | |
| "grad_norm": 3.9906229972839355, | |
| "learning_rate": 5.962666666666666e-06, | |
| "loss": 0.0696, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.03648, | |
| "grad_norm": 1.5516153573989868, | |
| "learning_rate": 6.069333333333334e-06, | |
| "loss": 0.0576, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.03712, | |
| "grad_norm": 3.5216825008392334, | |
| "learning_rate": 6.176000000000001e-06, | |
| "loss": 0.0793, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.03776, | |
| "grad_norm": 6.22791051864624, | |
| "learning_rate": 6.282666666666667e-06, | |
| "loss": 0.0757, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.0384, | |
| "grad_norm": 1.8255369663238525, | |
| "learning_rate": 6.389333333333334e-06, | |
| "loss": 0.0602, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.03904, | |
| "grad_norm": 2.506188154220581, | |
| "learning_rate": 6.496e-06, | |
| "loss": 0.0643, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.03968, | |
| "grad_norm": 1.5877528190612793, | |
| "learning_rate": 6.602666666666667e-06, | |
| "loss": 0.0501, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.04032, | |
| "grad_norm": 2.1468632221221924, | |
| "learning_rate": 6.7093333333333345e-06, | |
| "loss": 0.0521, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.04096, | |
| "grad_norm": 2.6225597858428955, | |
| "learning_rate": 6.8160000000000005e-06, | |
| "loss": 0.068, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.0416, | |
| "grad_norm": 3.1171772480010986, | |
| "learning_rate": 6.922666666666667e-06, | |
| "loss": 0.0644, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.04224, | |
| "grad_norm": 2.7589240074157715, | |
| "learning_rate": 7.029333333333333e-06, | |
| "loss": 0.0763, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.04288, | |
| "grad_norm": 2.3155124187469482, | |
| "learning_rate": 7.136000000000001e-06, | |
| "loss": 0.0451, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.04352, | |
| "grad_norm": 0.9795209169387817, | |
| "learning_rate": 7.242666666666667e-06, | |
| "loss": 0.0552, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.04416, | |
| "grad_norm": 6.224135398864746, | |
| "learning_rate": 7.3493333333333335e-06, | |
| "loss": 0.0614, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.0448, | |
| "grad_norm": 1.9188823699951172, | |
| "learning_rate": 7.456000000000001e-06, | |
| "loss": 0.0539, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.04544, | |
| "grad_norm": 2.0834364891052246, | |
| "learning_rate": 7.562666666666667e-06, | |
| "loss": 0.0545, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.04608, | |
| "grad_norm": 2.081609010696411, | |
| "learning_rate": 7.669333333333335e-06, | |
| "loss": 0.0563, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.04672, | |
| "grad_norm": 1.461228370666504, | |
| "learning_rate": 7.776e-06, | |
| "loss": 0.0495, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.04736, | |
| "grad_norm": 2.7746951580047607, | |
| "learning_rate": 7.882666666666667e-06, | |
| "loss": 0.0517, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 1.2801299095153809, | |
| "learning_rate": 7.989333333333335e-06, | |
| "loss": 0.034, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.04864, | |
| "grad_norm": 3.921491861343384, | |
| "learning_rate": 8.096e-06, | |
| "loss": 0.0537, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.04928, | |
| "grad_norm": 1.9986109733581543, | |
| "learning_rate": 8.202666666666667e-06, | |
| "loss": 0.0444, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.04992, | |
| "grad_norm": 4.678001403808594, | |
| "learning_rate": 8.309333333333334e-06, | |
| "loss": 0.0589, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.05056, | |
| "grad_norm": 1.7302327156066895, | |
| "learning_rate": 8.416e-06, | |
| "loss": 0.043, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.0512, | |
| "grad_norm": 2.5643601417541504, | |
| "learning_rate": 8.522666666666667e-06, | |
| "loss": 0.0671, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.05184, | |
| "grad_norm": 2.8869082927703857, | |
| "learning_rate": 8.629333333333334e-06, | |
| "loss": 0.0565, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.05248, | |
| "grad_norm": 3.723088264465332, | |
| "learning_rate": 8.736e-06, | |
| "loss": 0.0428, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.05312, | |
| "grad_norm": 4.387404441833496, | |
| "learning_rate": 8.842666666666667e-06, | |
| "loss": 0.0559, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.05376, | |
| "grad_norm": 1.889413833618164, | |
| "learning_rate": 8.949333333333334e-06, | |
| "loss": 0.0405, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.0544, | |
| "grad_norm": 1.4773402214050293, | |
| "learning_rate": 9.056000000000001e-06, | |
| "loss": 0.0414, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.05504, | |
| "grad_norm": 0.4495583176612854, | |
| "learning_rate": 9.162666666666668e-06, | |
| "loss": 0.0446, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.05568, | |
| "grad_norm": 1.158181071281433, | |
| "learning_rate": 9.269333333333335e-06, | |
| "loss": 0.0432, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.05632, | |
| "grad_norm": 2.434063196182251, | |
| "learning_rate": 9.376000000000001e-06, | |
| "loss": 0.0502, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.05696, | |
| "grad_norm": 1.2009385824203491, | |
| "learning_rate": 9.482666666666668e-06, | |
| "loss": 0.0473, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.0576, | |
| "grad_norm": 3.9361023902893066, | |
| "learning_rate": 9.589333333333333e-06, | |
| "loss": 0.046, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.05824, | |
| "grad_norm": 2.926988124847412, | |
| "learning_rate": 9.696000000000002e-06, | |
| "loss": 0.0464, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.05888, | |
| "grad_norm": 2.215726375579834, | |
| "learning_rate": 9.802666666666667e-06, | |
| "loss": 0.0471, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.05952, | |
| "grad_norm": 2.4104645252227783, | |
| "learning_rate": 9.909333333333334e-06, | |
| "loss": 0.0482, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.06016, | |
| "grad_norm": 5.664385795593262, | |
| "learning_rate": 1.0016000000000002e-05, | |
| "loss": 0.044, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.0608, | |
| "grad_norm": 1.7977851629257202, | |
| "learning_rate": 1.0122666666666667e-05, | |
| "loss": 0.0429, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.06144, | |
| "grad_norm": 2.953789472579956, | |
| "learning_rate": 1.0229333333333334e-05, | |
| "loss": 0.0533, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.06208, | |
| "grad_norm": 1.6272608041763306, | |
| "learning_rate": 1.0336000000000002e-05, | |
| "loss": 0.0307, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.06272, | |
| "grad_norm": 2.8621678352355957, | |
| "learning_rate": 1.0442666666666667e-05, | |
| "loss": 0.0461, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.06336, | |
| "grad_norm": 3.70019793510437, | |
| "learning_rate": 1.0549333333333334e-05, | |
| "loss": 0.0546, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 1.1777608394622803, | |
| "learning_rate": 1.0656000000000003e-05, | |
| "loss": 0.0508, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "eval_accuracy": 0.96139, | |
| "eval_f1_weighted": 0.9613900534763816, | |
| "eval_loss": 0.031560152769088745, | |
| "eval_macro_f1": 0.9613078781032101, | |
| "eval_precision": 0.9613901086866451, | |
| "eval_recall": 0.96139, | |
| "eval_runtime": 1630.3285, | |
| "eval_samples_per_second": 61.337, | |
| "eval_steps_per_second": 0.959, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06464, | |
| "grad_norm": 1.070363163948059, | |
| "learning_rate": 1.0762666666666668e-05, | |
| "loss": 0.0383, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.06528, | |
| "grad_norm": 1.6929458379745483, | |
| "learning_rate": 1.0869333333333335e-05, | |
| "loss": 0.0411, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.06592, | |
| "grad_norm": 3.4057459831237793, | |
| "learning_rate": 1.0976e-05, | |
| "loss": 0.0366, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.06656, | |
| "grad_norm": 4.279348850250244, | |
| "learning_rate": 1.1082666666666668e-05, | |
| "loss": 0.0518, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.0672, | |
| "grad_norm": 2.8239481449127197, | |
| "learning_rate": 1.1189333333333335e-05, | |
| "loss": 0.0628, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.06784, | |
| "grad_norm": 0.6896284222602844, | |
| "learning_rate": 1.1296e-05, | |
| "loss": 0.0326, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.06848, | |
| "grad_norm": 2.390023946762085, | |
| "learning_rate": 1.1402666666666668e-05, | |
| "loss": 0.023, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.06912, | |
| "grad_norm": 4.928287506103516, | |
| "learning_rate": 1.1509333333333335e-05, | |
| "loss": 0.054, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.06976, | |
| "grad_norm": 0.56038498878479, | |
| "learning_rate": 1.1616e-05, | |
| "loss": 0.0455, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.0704, | |
| "grad_norm": 1.9952913522720337, | |
| "learning_rate": 1.1722666666666667e-05, | |
| "loss": 0.0498, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.07104, | |
| "grad_norm": 3.672297239303589, | |
| "learning_rate": 1.1829333333333335e-05, | |
| "loss": 0.0316, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.07168, | |
| "grad_norm": 1.2902151346206665, | |
| "learning_rate": 1.1936e-05, | |
| "loss": 0.0307, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.07232, | |
| "grad_norm": 3.4965603351593018, | |
| "learning_rate": 1.2042666666666667e-05, | |
| "loss": 0.0276, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.07296, | |
| "grad_norm": 2.104722261428833, | |
| "learning_rate": 1.2149333333333336e-05, | |
| "loss": 0.0418, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.0736, | |
| "grad_norm": 3.112037420272827, | |
| "learning_rate": 1.2256000000000001e-05, | |
| "loss": 0.0273, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.07424, | |
| "grad_norm": 3.404317855834961, | |
| "learning_rate": 1.2362666666666668e-05, | |
| "loss": 0.05, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.07488, | |
| "grad_norm": 3.429887056350708, | |
| "learning_rate": 1.2469333333333333e-05, | |
| "loss": 0.0373, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.07552, | |
| "grad_norm": 3.0430426597595215, | |
| "learning_rate": 1.2576000000000001e-05, | |
| "loss": 0.0416, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.07616, | |
| "grad_norm": 0.9473117589950562, | |
| "learning_rate": 1.2682666666666668e-05, | |
| "loss": 0.0386, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.0768, | |
| "grad_norm": 3.2402405738830566, | |
| "learning_rate": 1.2789333333333333e-05, | |
| "loss": 0.0483, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.07744, | |
| "grad_norm": 0.6574758291244507, | |
| "learning_rate": 1.2896000000000002e-05, | |
| "loss": 0.0325, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.07808, | |
| "grad_norm": 1.2989708185195923, | |
| "learning_rate": 1.3002666666666668e-05, | |
| "loss": 0.0317, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.07872, | |
| "grad_norm": 2.3091909885406494, | |
| "learning_rate": 1.3109333333333333e-05, | |
| "loss": 0.0333, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.07936, | |
| "grad_norm": 1.9569207429885864, | |
| "learning_rate": 1.3216000000000002e-05, | |
| "loss": 0.0551, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.9818898439407349, | |
| "learning_rate": 1.3322666666666669e-05, | |
| "loss": 0.0456, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.08064, | |
| "grad_norm": 1.6688885688781738, | |
| "learning_rate": 1.3429333333333334e-05, | |
| "loss": 0.0282, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.08128, | |
| "grad_norm": 3.399576425552368, | |
| "learning_rate": 1.3536e-05, | |
| "loss": 0.0272, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.08192, | |
| "grad_norm": 1.1946886777877808, | |
| "learning_rate": 1.3642666666666669e-05, | |
| "loss": 0.0286, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.08256, | |
| "grad_norm": 0.6542123556137085, | |
| "learning_rate": 1.3749333333333334e-05, | |
| "loss": 0.0402, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.0832, | |
| "grad_norm": 0.3911895453929901, | |
| "learning_rate": 1.3856e-05, | |
| "loss": 0.0233, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.08384, | |
| "grad_norm": 2.623258352279663, | |
| "learning_rate": 1.396266666666667e-05, | |
| "loss": 0.032, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.08448, | |
| "grad_norm": 0.648289144039154, | |
| "learning_rate": 1.4069333333333334e-05, | |
| "loss": 0.0228, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.08512, | |
| "grad_norm": 3.750211000442505, | |
| "learning_rate": 1.4176000000000001e-05, | |
| "loss": 0.0502, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.08576, | |
| "grad_norm": 2.802426815032959, | |
| "learning_rate": 1.4282666666666666e-05, | |
| "loss": 0.0287, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.0864, | |
| "grad_norm": 1.0664188861846924, | |
| "learning_rate": 1.4389333333333335e-05, | |
| "loss": 0.0385, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.08704, | |
| "grad_norm": 3.218820571899414, | |
| "learning_rate": 1.4496000000000001e-05, | |
| "loss": 0.0515, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.08768, | |
| "grad_norm": 1.9482243061065674, | |
| "learning_rate": 1.4602666666666667e-05, | |
| "loss": 0.0258, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.08832, | |
| "grad_norm": 0.695675253868103, | |
| "learning_rate": 1.4709333333333335e-05, | |
| "loss": 0.0422, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.08896, | |
| "grad_norm": 0.9671708941459656, | |
| "learning_rate": 1.4816000000000002e-05, | |
| "loss": 0.0319, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.0896, | |
| "grad_norm": 0.8047491908073425, | |
| "learning_rate": 1.4922666666666667e-05, | |
| "loss": 0.0423, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.09024, | |
| "grad_norm": 1.894417643547058, | |
| "learning_rate": 1.5029333333333334e-05, | |
| "loss": 0.0327, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.09088, | |
| "grad_norm": 3.023747444152832, | |
| "learning_rate": 1.5136000000000002e-05, | |
| "loss": 0.0356, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.09152, | |
| "grad_norm": 1.0697004795074463, | |
| "learning_rate": 1.5242666666666667e-05, | |
| "loss": 0.038, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.09216, | |
| "grad_norm": 1.0740805864334106, | |
| "learning_rate": 1.5349333333333332e-05, | |
| "loss": 0.037, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.0928, | |
| "grad_norm": 1.7463656663894653, | |
| "learning_rate": 1.5456000000000002e-05, | |
| "loss": 0.0277, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.09344, | |
| "grad_norm": 0.6604284644126892, | |
| "learning_rate": 1.556266666666667e-05, | |
| "loss": 0.0259, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.09408, | |
| "grad_norm": 2.2307727336883545, | |
| "learning_rate": 1.5669333333333333e-05, | |
| "loss": 0.0311, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.09472, | |
| "grad_norm": 0.47977620363235474, | |
| "learning_rate": 1.5776e-05, | |
| "loss": 0.0184, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.09536, | |
| "grad_norm": 1.1453766822814941, | |
| "learning_rate": 1.588266666666667e-05, | |
| "loss": 0.0303, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 2.8183929920196533, | |
| "learning_rate": 1.5989333333333333e-05, | |
| "loss": 0.0498, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "eval_accuracy": 0.96992, | |
| "eval_f1_weighted": 0.9699323760484765, | |
| "eval_loss": 0.029355797916650772, | |
| "eval_macro_f1": 0.9698851462608304, | |
| "eval_precision": 0.9702279455514112, | |
| "eval_recall": 0.96992, | |
| "eval_runtime": 1629.7849, | |
| "eval_samples_per_second": 61.358, | |
| "eval_steps_per_second": 0.959, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.09664, | |
| "grad_norm": 2.631521224975586, | |
| "learning_rate": 1.6096e-05, | |
| "loss": 0.0309, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.09728, | |
| "grad_norm": 4.332648277282715, | |
| "learning_rate": 1.620266666666667e-05, | |
| "loss": 0.0265, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.09792, | |
| "grad_norm": 2.661992311477661, | |
| "learning_rate": 1.6309333333333333e-05, | |
| "loss": 0.0333, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.09856, | |
| "grad_norm": 4.480170726776123, | |
| "learning_rate": 1.6416e-05, | |
| "loss": 0.0164, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.0992, | |
| "grad_norm": 3.6200265884399414, | |
| "learning_rate": 1.652266666666667e-05, | |
| "loss": 0.0496, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.09984, | |
| "grad_norm": 0.8664556741714478, | |
| "learning_rate": 1.6629333333333334e-05, | |
| "loss": 0.0405, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.10048, | |
| "grad_norm": 0.4059486985206604, | |
| "learning_rate": 1.6736e-05, | |
| "loss": 0.0204, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.10112, | |
| "grad_norm": 6.29810094833374, | |
| "learning_rate": 1.6842666666666667e-05, | |
| "loss": 0.0373, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.10176, | |
| "grad_norm": 0.3921312987804413, | |
| "learning_rate": 1.6949333333333334e-05, | |
| "loss": 0.0296, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.1024, | |
| "grad_norm": 0.5871056318283081, | |
| "learning_rate": 1.7056e-05, | |
| "loss": 0.0272, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.10304, | |
| "grad_norm": 0.8386616706848145, | |
| "learning_rate": 1.7162666666666667e-05, | |
| "loss": 0.0268, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.10368, | |
| "grad_norm": 0.24483710527420044, | |
| "learning_rate": 1.7269333333333334e-05, | |
| "loss": 0.026, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.10432, | |
| "grad_norm": 1.1107805967330933, | |
| "learning_rate": 1.7376e-05, | |
| "loss": 0.0212, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.10496, | |
| "grad_norm": 2.1698811054229736, | |
| "learning_rate": 1.7482666666666668e-05, | |
| "loss": 0.034, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.1056, | |
| "grad_norm": 0.20654629170894623, | |
| "learning_rate": 1.7589333333333335e-05, | |
| "loss": 0.0341, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.10624, | |
| "grad_norm": 1.9759390354156494, | |
| "learning_rate": 1.7696e-05, | |
| "loss": 0.0185, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.10688, | |
| "grad_norm": 3.4848012924194336, | |
| "learning_rate": 1.7802666666666668e-05, | |
| "loss": 0.0353, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.10752, | |
| "grad_norm": 0.2271997630596161, | |
| "learning_rate": 1.7909333333333335e-05, | |
| "loss": 0.0394, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.10816, | |
| "grad_norm": 2.6998696327209473, | |
| "learning_rate": 1.8016e-05, | |
| "loss": 0.05, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.1088, | |
| "grad_norm": 0.7117211222648621, | |
| "learning_rate": 1.812266666666667e-05, | |
| "loss": 0.0221, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.10944, | |
| "grad_norm": 1.4605228900909424, | |
| "learning_rate": 1.8229333333333335e-05, | |
| "loss": 0.0225, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.11008, | |
| "grad_norm": 0.8530828952789307, | |
| "learning_rate": 1.8336000000000002e-05, | |
| "loss": 0.0227, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.11072, | |
| "grad_norm": 1.9308661222457886, | |
| "learning_rate": 1.844266666666667e-05, | |
| "loss": 0.0331, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.11136, | |
| "grad_norm": 0.4266184866428375, | |
| "learning_rate": 1.8549333333333336e-05, | |
| "loss": 0.0269, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 0.24159789085388184, | |
| "learning_rate": 1.8656000000000002e-05, | |
| "loss": 0.016, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.11264, | |
| "grad_norm": 2.9888405799865723, | |
| "learning_rate": 1.876266666666667e-05, | |
| "loss": 0.0183, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.11328, | |
| "grad_norm": 0.3445536494255066, | |
| "learning_rate": 1.8869333333333336e-05, | |
| "loss": 0.0275, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.11392, | |
| "grad_norm": 0.8499478101730347, | |
| "learning_rate": 1.8976000000000003e-05, | |
| "loss": 0.0279, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.11456, | |
| "grad_norm": 0.6538372039794922, | |
| "learning_rate": 1.908266666666667e-05, | |
| "loss": 0.0386, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.1152, | |
| "grad_norm": 1.7591469287872314, | |
| "learning_rate": 1.9189333333333336e-05, | |
| "loss": 0.0295, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.11584, | |
| "grad_norm": 3.075883150100708, | |
| "learning_rate": 1.9296000000000003e-05, | |
| "loss": 0.0261, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.11648, | |
| "grad_norm": 0.967818021774292, | |
| "learning_rate": 1.9402666666666666e-05, | |
| "loss": 0.0324, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.11712, | |
| "grad_norm": 3.656330108642578, | |
| "learning_rate": 1.9509333333333337e-05, | |
| "loss": 0.0319, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.11776, | |
| "grad_norm": 1.274255394935608, | |
| "learning_rate": 1.9616000000000003e-05, | |
| "loss": 0.0348, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.1184, | |
| "grad_norm": 1.348671793937683, | |
| "learning_rate": 1.9722666666666667e-05, | |
| "loss": 0.0268, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.11904, | |
| "grad_norm": 2.5715315341949463, | |
| "learning_rate": 1.9829333333333337e-05, | |
| "loss": 0.0484, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.11968, | |
| "grad_norm": 1.6529572010040283, | |
| "learning_rate": 1.9936000000000004e-05, | |
| "loss": 0.0288, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.12032, | |
| "grad_norm": 0.4880078136920929, | |
| "learning_rate": 1.999999582377099e-05, | |
| "loss": 0.0166, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.12096, | |
| "grad_norm": 0.04303014650940895, | |
| "learning_rate": 1.9999948841234694e-05, | |
| "loss": 0.0328, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.1216, | |
| "grad_norm": 1.308612585067749, | |
| "learning_rate": 1.999984965612191e-05, | |
| "loss": 0.0188, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.12224, | |
| "grad_norm": 0.04864171892404556, | |
| "learning_rate": 1.999969826895043e-05, | |
| "loss": 0.0138, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.12288, | |
| "grad_norm": 3.7564399242401123, | |
| "learning_rate": 1.999949468051052e-05, | |
| "loss": 0.0332, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.12352, | |
| "grad_norm": 0.5204304456710815, | |
| "learning_rate": 1.999923889186498e-05, | |
| "loss": 0.0262, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.12416, | |
| "grad_norm": 1.1759312152862549, | |
| "learning_rate": 1.9998930904349093e-05, | |
| "loss": 0.0437, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.1248, | |
| "grad_norm": 1.0756793022155762, | |
| "learning_rate": 1.999857071957065e-05, | |
| "loss": 0.0268, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.12544, | |
| "grad_norm": 2.0290422439575195, | |
| "learning_rate": 1.999815833940991e-05, | |
| "loss": 0.0167, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.12608, | |
| "grad_norm": 2.2367708683013916, | |
| "learning_rate": 1.999769376601962e-05, | |
| "loss": 0.0291, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.12672, | |
| "grad_norm": 1.9560596942901611, | |
| "learning_rate": 1.999717700182498e-05, | |
| "loss": 0.0322, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.12736, | |
| "grad_norm": 0.5732283592224121, | |
| "learning_rate": 1.9996608049523648e-05, | |
| "loss": 0.0288, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 3.124932050704956, | |
| "learning_rate": 1.9995986912085723e-05, | |
| "loss": 0.03, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "eval_accuracy": 0.97019, | |
| "eval_f1_weighted": 0.9702046600903295, | |
| "eval_loss": 0.030205972492694855, | |
| "eval_macro_f1": 0.970164263786433, | |
| "eval_precision": 0.9707624849401539, | |
| "eval_recall": 0.97019, | |
| "eval_runtime": 1729.5857, | |
| "eval_samples_per_second": 57.817, | |
| "eval_steps_per_second": 0.904, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 15625, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.68312142113792e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |