Frenz/modelsent_test

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: albert/albert-base-v2
 tags:
 - generated_from_trainer
-base_model: albert/albert-base-v2
 metrics:
 - accuracy
 - f1
@@ -20,13 +20,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2510
-- Accuracy: 0.9261
-- F1: 0.9261
-- Precision: 0.9261
-- Recall: 0.9261
-- Accuracy Label Negative: 0.9255
-- Accuracy Label Positive: 0.9266
+- Loss: 0.2310
+- Accuracy: 0.9279
+- F1: 0.9279
+- Precision: 0.9280
+- Recall: 0.9279
+- Accuracy Label Negative: 0.9192
+- Accuracy Label Positive: 0.9361
 
 ## Model description
 
@@ -60,23 +60,23 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Accuracy Label Negative | Accuracy Label Positive |
 |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-----------------------:|:-----------------------:|
-| 0.5848        | 0.2442 | 100  | 0.5668          | 0.7783   | 0.7774 | 0.7869    | 0.7783 | 0.8548                  | 0.7065                  |
-| 0.2761        | 0.4884 | 200  | 0.2858          | 0.8913   | 0.8912 | 0.8944    | 0.8913 | 0.9318                  | 0.8533                  |
-| 0.2099        | 0.7326 | 300  | 0.2412          | 0.9114   | 0.9114 | 0.9116    | 0.9114 | 0.8965                  | 0.9254                  |
-| 0.2717        | 0.9768 | 400  | 0.2532          | 0.9133   | 0.9133 | 0.9141    | 0.9133 | 0.9318                  | 0.8959                  |
-| 0.2076        | 1.2210 | 500  | 0.2588          | 0.9084   | 0.9083 | 0.9111    | 0.9084 | 0.9457                  | 0.8734                  |
-| 0.1745        | 1.4652 | 600  | 0.2217          | 0.9133   | 0.9132 | 0.9133    | 0.9133 | 0.9028                  | 0.9231                  |
-| 0.21          | 1.7094 | 700  | 0.2161          | 0.9157   | 0.9157 | 0.9157    | 0.9157 | 0.9078                  | 0.9231                  |
-| 0.1349        | 1.9536 | 800  | 0.2092          | 0.9243   | 0.9242 | 0.9245    | 0.9243 | 0.9078                  | 0.9396                  |
-| 0.1795        | 2.1978 | 900  | 0.2492          | 0.9175   | 0.9175 | 0.9189    | 0.9175 | 0.9432                  | 0.8935                  |
-| 0.107         | 2.4420 | 1000 | 0.2743          | 0.9120   | 0.9120 | 0.9163    | 0.9120 | 0.9596                  | 0.8675                  |
-| 0.08          | 2.6862 | 1100 | 0.2606          | 0.9188   | 0.9188 | 0.9200    | 0.9188 | 0.9432                  | 0.8959                  |
-| 0.1275        | 2.9304 | 1200 | 0.2550          | 0.9255   | 0.9255 | 0.9255    | 0.9255 | 0.9167                  | 0.9337                  |
+| 0.5427        | 0.2442 | 100  | 0.5228          | 0.7544   | 0.7539 | 0.7602    | 0.7544 | 0.8157                  | 0.6970                  |
+| 0.2745        | 0.4884 | 200  | 0.2897          | 0.8937   | 0.8937 | 0.8940    | 0.8937 | 0.9028                  | 0.8852                  |
+| 0.2409        | 0.7326 | 300  | 0.3172          | 0.8992   | 0.8985 | 0.9069    | 0.8992 | 0.8232                  | 0.9704                  |
+| 0.2717        | 0.9768 | 400  | 0.2341          | 0.9163   | 0.9163 | 0.9169    | 0.9163 | 0.9306                  | 0.9030                  |
+| 0.2178        | 1.2210 | 500  | 0.2670          | 0.9169   | 0.9169 | 0.9171    | 0.9169 | 0.9230                  | 0.9112                  |
+| 0.2011        | 1.4652 | 600  | 0.2634          | 0.9145   | 0.9143 | 0.9158    | 0.9145 | 0.8813                  | 0.9456                  |
+| 0.2179        | 1.7094 | 700  | 0.2657          | 0.9016   | 0.9015 | 0.9027    | 0.9016 | 0.8699                  | 0.9314                  |
+| 0.1465        | 1.9536 | 800  | 0.2150          | 0.9212   | 0.9210 | 0.9228    | 0.9212 | 0.8851                  | 0.9550                  |
+| 0.1602        | 2.1978 | 900  | 0.2421          | 0.9261   | 0.9261 | 0.9264    | 0.9261 | 0.9356                  | 0.9172                  |
+| 0.1293        | 2.4420 | 1000 | 0.2693          | 0.9181   | 0.9181 | 0.9204    | 0.9181 | 0.9520                  | 0.8864                  |
+| 0.1023        | 2.6862 | 1100 | 0.2392          | 0.9236   | 0.9237 | 0.9240    | 0.9236 | 0.9343                  | 0.9136                  |
+| 0.1663        | 2.9304 | 1200 | 0.2326          | 0.9267   | 0.9267 | 0.9269    | 0.9267 | 0.9116                  | 0.9408                  |
 
 
 ### Framework versions
 
 - Transformers 4.41.2
 - Pytorch 2.3.0+cu121
-- Datasets 2.19.1
+- Datasets 2.20.0
 - Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d29a598f2808b8a565502687990d28082b2a6e7357728d3bedda42ed80cbc0
+oid sha256:7658f279f86ab2384500a655e07375ddbae1aedf7d189dd07a1bbf49bbd867ca
 size 46743912

runs/Jun16_10-55-42_e074026fd21f/events.out.tfevents.1718535344.e074026fd21f.458.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6102f1e33b41655e2bf8505f584ce427a69ed06bba24ff162f5d2db8b482092d
+size 38395

runs/Jun16_10-55-42_e074026fd21f/events.out.tfevents.1718536095.e074026fd21f.458.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89412c03fb5853141045de7c352ac64c46896161e57e5303dd74bc5b40df6761
+size 694

trainer_state.json

@@ -10,1047 +10,1047 @@
   "log_history": [
     {
       "epoch": 0.02442002442002442,
-      "grad_norm": 10.498289108276367,
+      "grad_norm": 20.259180068969727,
       "learning_rate": 4.0000000000000003e-07,
-      "loss": 0.7042,
+      "loss": 0.7339,
       "step": 10
     },
     {
       "epoch": 0.04884004884004884,
-      "grad_norm": 9.02344799041748,
+      "grad_norm": 14.779166221618652,
       "learning_rate": 8.000000000000001e-07,
-      "loss": 0.7274,
+      "loss": 0.7128,
       "step": 20
     },
     {
       "epoch": 0.07326007326007326,
-      "grad_norm": 12.760648727416992,
+      "grad_norm": 14.740580558776855,
       "learning_rate": 1.2000000000000002e-06,
-      "loss": 0.7136,
+      "loss": 0.6777,
       "step": 30
     },
     {
       "epoch": 0.09768009768009768,
-      "grad_norm": 11.814812660217285,
+      "grad_norm": 15.626840591430664,
       "learning_rate": 1.6000000000000001e-06,
-      "loss": 0.7063,
+      "loss": 0.6666,
       "step": 40
     },
     {
       "epoch": 0.1221001221001221,
-      "grad_norm": 10.731100082397461,
+      "grad_norm": 15.19382095336914,
       "learning_rate": 2.0000000000000003e-06,
-      "loss": 0.6947,
+      "loss": 0.6723,
       "step": 50
     },
     {
       "epoch": 0.14652014652014653,
-      "grad_norm": 9.641815185546875,
+      "grad_norm": 18.021406173706055,
       "learning_rate": 2.4000000000000003e-06,
-      "loss": 0.6883,
+      "loss": 0.6702,
       "step": 60
     },
     {
       "epoch": 0.17094017094017094,
-      "grad_norm": 10.62743854522705,
+      "grad_norm": 14.912147521972656,
       "learning_rate": 2.8000000000000003e-06,
-      "loss": 0.6673,
+      "loss": 0.6382,
       "step": 70
     },
     {
       "epoch": 0.19536019536019536,
-      "grad_norm": 15.131406784057617,
+      "grad_norm": 18.795974731445312,
       "learning_rate": 3.2000000000000003e-06,
-      "loss": 0.6422,
+      "loss": 0.6014,
       "step": 80
     },
     {
       "epoch": 0.21978021978021978,
-      "grad_norm": 11.530914306640625,
+      "grad_norm": 14.359152793884277,
       "learning_rate": 3.6000000000000003e-06,
-      "loss": 0.6155,
+      "loss": 0.5685,
       "step": 90
     },
     {
       "epoch": 0.2442002442002442,
-      "grad_norm": 9.192888259887695,
+      "grad_norm": 16.193758010864258,
       "learning_rate": 4.000000000000001e-06,
-      "loss": 0.5848,
+      "loss": 0.5427,
       "step": 100
     },
     {
       "epoch": 0.2442002442002442,
-      "eval_accuracy": 0.7782529016493586,
-      "eval_accuracy_label_negative": 0.8547979797979798,
-      "eval_accuracy_label_positive": 0.7065088757396449,
-      "eval_f1": 0.7773703489129234,
-      "eval_loss": 0.5668291449546814,
-      "eval_precision": 0.7869130340900089,
-      "eval_recall": 0.7782529016493586,
-      "eval_runtime": 6.1736,
-      "eval_samples_per_second": 265.16,
-      "eval_steps_per_second": 16.684,
+      "eval_accuracy": 0.7544288332315211,
+      "eval_accuracy_label_negative": 0.8156565656565656,
+      "eval_accuracy_label_positive": 0.6970414201183432,
+      "eval_f1": 0.7538535596614978,
+      "eval_loss": 0.5227517485618591,
+      "eval_precision": 0.7601522126200779,
+      "eval_recall": 0.7544288332315211,
+      "eval_runtime": 7.0366,
+      "eval_samples_per_second": 232.64,
+      "eval_steps_per_second": 14.638,
       "step": 100
     },
     {
       "epoch": 0.2686202686202686,
-      "grad_norm": 11.79243278503418,
+      "grad_norm": 15.085676193237305,
       "learning_rate": 4.4e-06,
-      "loss": 0.5391,
+      "loss": 0.5023,
       "step": 110
     },
     {
       "epoch": 0.29304029304029305,
-      "grad_norm": 13.897492408752441,
+      "grad_norm": 19.296276092529297,
       "learning_rate": 4.800000000000001e-06,
-      "loss": 0.4971,
+      "loss": 0.4881,
       "step": 120
     },
     {
       "epoch": 0.31746031746031744,
-      "grad_norm": 18.756803512573242,
+      "grad_norm": 29.949970245361328,
       "learning_rate": 5.2e-06,
-      "loss": 0.4148,
+      "loss": 0.3837,
       "step": 130
     },
     {
       "epoch": 0.3418803418803419,
-      "grad_norm": 18.242826461791992,
+      "grad_norm": 22.738380432128906,
       "learning_rate": 5.600000000000001e-06,
-      "loss": 0.3547,
+      "loss": 0.352,
       "step": 140
     },
     {
       "epoch": 0.3663003663003663,
-      "grad_norm": 7.90754508972168,
+      "grad_norm": 62.512149810791016,
       "learning_rate": 6e-06,
-      "loss": 0.3547,
+      "loss": 0.3676,
       "step": 150
     },
     {
       "epoch": 0.3907203907203907,
-      "grad_norm": 11.013474464416504,
+      "grad_norm": 28.634130477905273,
       "learning_rate": 6.4000000000000006e-06,
-      "loss": 0.309,
+      "loss": 0.306,
       "step": 160
     },
     {
       "epoch": 0.41514041514041516,
-      "grad_norm": 24.09418487548828,
+      "grad_norm": 27.88077735900879,
       "learning_rate": 6.800000000000001e-06,
-      "loss": 0.3168,
+      "loss": 0.2976,
       "step": 170
     },
     {
       "epoch": 0.43956043956043955,
-      "grad_norm": 12.913431167602539,
+      "grad_norm": 26.289413452148438,
       "learning_rate": 7.2000000000000005e-06,
-      "loss": 0.2891,
+      "loss": 0.3203,
       "step": 180
     },
     {
       "epoch": 0.463980463980464,
-      "grad_norm": 38.170555114746094,
+      "grad_norm": 38.563026428222656,
       "learning_rate": 7.600000000000001e-06,
-      "loss": 0.277,
+      "loss": 0.2835,
       "step": 190
     },
     {
       "epoch": 0.4884004884004884,
-      "grad_norm": 19.653949737548828,
+      "grad_norm": 19.998462677001953,
       "learning_rate": 8.000000000000001e-06,
-      "loss": 0.2761,
+      "loss": 0.2745,
       "step": 200
     },
     {
       "epoch": 0.4884004884004884,
-      "eval_accuracy": 0.8912645082467929,
-      "eval_accuracy_label_negative": 0.9318181818181818,
-      "eval_accuracy_label_positive": 0.8532544378698225,
-      "eval_f1": 0.8912162170726895,
-      "eval_loss": 0.2858136296272278,
-      "eval_precision": 0.8944362774670781,
-      "eval_recall": 0.8912645082467929,
-      "eval_runtime": 6.345,
-      "eval_samples_per_second": 257.999,
-      "eval_steps_per_second": 16.233,
+      "eval_accuracy": 0.8937080024434942,
+      "eval_accuracy_label_negative": 0.9027777777777778,
+      "eval_accuracy_label_positive": 0.8852071005917159,
+      "eval_f1": 0.8937341917301531,
+      "eval_loss": 0.28969109058380127,
+      "eval_precision": 0.8940271813652473,
+      "eval_recall": 0.8937080024434942,
+      "eval_runtime": 6.9835,
+      "eval_samples_per_second": 234.408,
+      "eval_steps_per_second": 14.749,
       "step": 200
     },
     {
       "epoch": 0.5128205128205128,
-      "grad_norm": 38.47966003417969,
+      "grad_norm": 28.719772338867188,
       "learning_rate": 8.400000000000001e-06,
-      "loss": 0.228,
+      "loss": 0.2126,
       "step": 210
     },
     {
       "epoch": 0.5372405372405372,
-      "grad_norm": 37.67184829711914,
+      "grad_norm": 18.826200485229492,
       "learning_rate": 8.8e-06,
-      "loss": 0.204,
+      "loss": 0.226,
       "step": 220
     },
     {
       "epoch": 0.5616605616605617,
-      "grad_norm": 9.530702590942383,
+      "grad_norm": 10.376764297485352,
       "learning_rate": 9.200000000000002e-06,
-      "loss": 0.2728,
+      "loss": 0.285,
       "step": 230
     },
     {
       "epoch": 0.5860805860805861,
-      "grad_norm": 24.261260986328125,
+      "grad_norm": 8.594544410705566,
       "learning_rate": 9.600000000000001e-06,
-      "loss": 0.2755,
+      "loss": 0.2463,
       "step": 240
     },
     {
       "epoch": 0.6105006105006106,
-      "grad_norm": 25.7033634185791,
+      "grad_norm": 37.928585052490234,
       "learning_rate": 1e-05,
-      "loss": 0.2787,
+      "loss": 0.2655,
       "step": 250
     },
     {
       "epoch": 0.6349206349206349,
-      "grad_norm": 21.64457893371582,
+      "grad_norm": 15.18250560760498,
       "learning_rate": 1.04e-05,
-      "loss": 0.2357,
+      "loss": 0.2481,
       "step": 260
     },
     {
       "epoch": 0.6593406593406593,
-      "grad_norm": 23.77570915222168,
+      "grad_norm": 22.519500732421875,
       "learning_rate": 1.0800000000000002e-05,
-      "loss": 0.2388,
+      "loss": 0.2731,
       "step": 270
     },
     {
       "epoch": 0.6837606837606838,
-      "grad_norm": 20.548864364624023,
+      "grad_norm": 17.65134620666504,
       "learning_rate": 1.1200000000000001e-05,
-      "loss": 0.2058,
+      "loss": 0.1948,
       "step": 280
     },
     {
       "epoch": 0.7081807081807082,
-      "grad_norm": 14.279947280883789,
+      "grad_norm": 15.242578506469727,
       "learning_rate": 1.16e-05,
-      "loss": 0.2169,
+      "loss": 0.2033,
       "step": 290
     },
     {
       "epoch": 0.7326007326007326,
-      "grad_norm": 20.323959350585938,
+      "grad_norm": 13.12796688079834,
       "learning_rate": 1.2e-05,
-      "loss": 0.2099,
+      "loss": 0.2409,
       "step": 300
     },
     {
       "epoch": 0.7326007326007326,
-      "eval_accuracy": 0.9114233353695785,
-      "eval_accuracy_label_negative": 0.8964646464646465,
-      "eval_accuracy_label_positive": 0.9254437869822485,
-      "eval_f1": 0.9113780300690499,
-      "eval_loss": 0.2412199079990387,
-      "eval_precision": 0.9115789422424927,
-      "eval_recall": 0.9114233353695785,
-      "eval_runtime": 6.209,
-      "eval_samples_per_second": 263.65,
-      "eval_steps_per_second": 16.589,
+      "eval_accuracy": 0.8992058643860721,
+      "eval_accuracy_label_negative": 0.8232323232323232,
+      "eval_accuracy_label_positive": 0.9704142011834319,
+      "eval_f1": 0.8984714462637845,
+      "eval_loss": 0.31721410155296326,
+      "eval_precision": 0.9068565405127066,
+      "eval_recall": 0.8992058643860721,
+      "eval_runtime": 7.2344,
+      "eval_samples_per_second": 226.279,
+      "eval_steps_per_second": 14.237,
       "step": 300
     },
     {
       "epoch": 0.757020757020757,
-      "grad_norm": 13.649131774902344,
+      "grad_norm": 108.63019561767578,
       "learning_rate": 1.2400000000000002e-05,
-      "loss": 0.2337,
+      "loss": 0.3153,
       "step": 310
     },
     {
       "epoch": 0.7814407814407814,
-      "grad_norm": 18.731950759887695,
+      "grad_norm": 3.575650453567505,
       "learning_rate": 1.2800000000000001e-05,
-      "loss": 0.202,
+      "loss": 0.2238,
       "step": 320
     },
     {
       "epoch": 0.8058608058608059,
-      "grad_norm": 2.1580898761749268,
+      "grad_norm": 1.4278050661087036,
       "learning_rate": 1.3200000000000002e-05,
-      "loss": 0.1882,
+      "loss": 0.2762,
       "step": 330
     },
     {
       "epoch": 0.8302808302808303,
-      "grad_norm": 17.960113525390625,
+      "grad_norm": 12.686599731445312,
       "learning_rate": 1.3600000000000002e-05,
-      "loss": 0.2176,
+      "loss": 0.2433,
       "step": 340
     },
     {
       "epoch": 0.8547008547008547,
-      "grad_norm": 19.708494186401367,
+      "grad_norm": 8.050217628479004,
       "learning_rate": 1.4e-05,
-      "loss": 0.2565,
+      "loss": 0.2258,
       "step": 350
     },
     {
       "epoch": 0.8791208791208791,
-      "grad_norm": 15.667474746704102,
+      "grad_norm": 23.091922760009766,
       "learning_rate": 1.4400000000000001e-05,
-      "loss": 0.2572,
+      "loss": 0.2986,
       "step": 360
     },
     {
       "epoch": 0.9035409035409036,
-      "grad_norm": 38.89118194580078,
+      "grad_norm": 20.166908264160156,
       "learning_rate": 1.48e-05,
-      "loss": 0.2842,
+      "loss": 0.29,
       "step": 370
     },
     {
       "epoch": 0.927960927960928,
-      "grad_norm": 25.795814514160156,
+      "grad_norm": 19.215978622436523,
       "learning_rate": 1.5200000000000002e-05,
-      "loss": 0.1919,
+      "loss": 0.1558,
       "step": 380
     },
     {
       "epoch": 0.9523809523809523,
-      "grad_norm": 57.172943115234375,
+      "grad_norm": 24.995752334594727,
       "learning_rate": 1.5600000000000003e-05,
-      "loss": 0.1728,
+      "loss": 0.168,
       "step": 390
     },
     {
       "epoch": 0.9768009768009768,
-      "grad_norm": 12.05911922454834,
+      "grad_norm": 14.634511947631836,
       "learning_rate": 1.6000000000000003e-05,
       "loss": 0.2717,
       "step": 400
     },
     {
       "epoch": 0.9768009768009768,
-      "eval_accuracy": 0.9132559560171044,
-      "eval_accuracy_label_negative": 0.9318181818181818,
-      "eval_accuracy_label_positive": 0.8958579881656805,
-      "eval_f1": 0.9132768698355349,
-      "eval_loss": 0.25323960185050964,
-      "eval_precision": 0.9140857692521688,
-      "eval_recall": 0.9132559560171044,
-      "eval_runtime": 6.6576,
-      "eval_samples_per_second": 245.883,
-      "eval_steps_per_second": 15.471,
+      "eval_accuracy": 0.916310323762981,
+      "eval_accuracy_label_negative": 0.9305555555555556,
+      "eval_accuracy_label_positive": 0.9029585798816568,
+      "eval_f1": 0.916332252883291,
+      "eval_loss": 0.23408986628055573,
+      "eval_precision": 0.9168527142824153,
+      "eval_recall": 0.916310323762981,
+      "eval_runtime": 7.2206,
+      "eval_samples_per_second": 226.712,
+      "eval_steps_per_second": 14.265,
       "step": 400
     },
     {
       "epoch": 1.0012210012210012,
-      "grad_norm": 175.93984985351562,
+      "grad_norm": 4.358543872833252,
       "learning_rate": 1.64e-05,
-      "loss": 0.2158,
+      "loss": 0.152,
       "step": 410
     },
     {
       "epoch": 1.0256410256410255,
-      "grad_norm": 4.0570220947265625,
+      "grad_norm": 12.582831382751465,
       "learning_rate": 1.6800000000000002e-05,
-      "loss": 0.1614,
+      "loss": 0.1771,
       "step": 420
     },
     {
       "epoch": 1.05006105006105,
-      "grad_norm": 20.152868270874023,
+      "grad_norm": 70.92117309570312,
       "learning_rate": 1.72e-05,
-      "loss": 0.1849,
+      "loss": 0.2099,
       "step": 430
     },
     {
       "epoch": 1.0744810744810744,
-      "grad_norm": 15.713109970092773,
+      "grad_norm": 17.06641387939453,
       "learning_rate": 1.76e-05,
-      "loss": 0.1128,
+      "loss": 0.1686,
       "step": 440
     },
     {
       "epoch": 1.098901098901099,
-      "grad_norm": 6.342801094055176,
+      "grad_norm": 23.57867431640625,
       "learning_rate": 1.8e-05,
-      "loss": 0.1914,
+      "loss": 0.3161,
       "step": 450
     },
     {
       "epoch": 1.1233211233211233,
-      "grad_norm": 35.65519714355469,
+      "grad_norm": 7.516932487487793,
       "learning_rate": 1.8400000000000003e-05,
-      "loss": 0.2143,
+      "loss": 0.2111,
       "step": 460
     },
     {
       "epoch": 1.1477411477411477,
-      "grad_norm": 61.438838958740234,
+      "grad_norm": 24.830093383789062,
       "learning_rate": 1.88e-05,
-      "loss": 0.2332,
+      "loss": 0.1837,
       "step": 470
     },
     {
       "epoch": 1.1721611721611722,
-      "grad_norm": 21.36277961730957,
+      "grad_norm": 25.01032257080078,
       "learning_rate": 1.9200000000000003e-05,
-      "loss": 0.2433,
+      "loss": 0.1845,
       "step": 480
     },
     {
       "epoch": 1.1965811965811965,
-      "grad_norm": 6.238389015197754,
+      "grad_norm": 8.994218826293945,
       "learning_rate": 1.9600000000000002e-05,
-      "loss": 0.131,
+      "loss": 0.1015,
       "step": 490
     },
     {
       "epoch": 1.221001221001221,
-      "grad_norm": 44.72506332397461,
+      "grad_norm": 33.930198669433594,
       "learning_rate": 2e-05,
-      "loss": 0.2076,
+      "loss": 0.2178,
       "step": 500
     },
     {
       "epoch": 1.221001221001221,
-      "eval_accuracy": 0.9083689676237019,
-      "eval_accuracy_label_negative": 0.9457070707070707,
-      "eval_accuracy_label_positive": 0.8733727810650888,
-      "eval_f1": 0.9083448942204814,
-      "eval_loss": 0.25875234603881836,
-      "eval_precision": 0.9111034284789092,
-      "eval_recall": 0.9083689676237019,
-      "eval_runtime": 6.2625,
-      "eval_samples_per_second": 261.397,
-      "eval_steps_per_second": 16.447,
+      "eval_accuracy": 0.9169211973121564,
+      "eval_accuracy_label_negative": 0.922979797979798,
+      "eval_accuracy_label_positive": 0.9112426035502958,
+      "eval_f1": 0.9169381341403617,
+      "eval_loss": 0.2670413851737976,
+      "eval_precision": 0.9170892193228738,
+      "eval_recall": 0.9169211973121564,
+      "eval_runtime": 7.2472,
+      "eval_samples_per_second": 225.88,
+      "eval_steps_per_second": 14.212,
       "step": 500
     },
     {
       "epoch": 1.2454212454212454,
-      "grad_norm": 24.117422103881836,
+      "grad_norm": 3.4228224754333496,
       "learning_rate": 1.9724896836313617e-05,
-      "loss": 0.217,
+      "loss": 0.185,
       "step": 510
     },
     {
       "epoch": 1.2698412698412698,
-      "grad_norm": 15.197860717773438,
+      "grad_norm": 7.5374298095703125,
       "learning_rate": 1.9449793672627236e-05,
-      "loss": 0.2137,
+      "loss": 0.2113,
       "step": 520
     },
     {
       "epoch": 1.2942612942612943,
-      "grad_norm": 15.89400577545166,
+      "grad_norm": 24.314939498901367,
       "learning_rate": 1.9174690508940855e-05,
-      "loss": 0.2309,
+      "loss": 0.2134,
       "step": 530
     },
     {
       "epoch": 1.3186813186813187,
-      "grad_norm": 15.406135559082031,
+      "grad_norm": 13.505054473876953,
       "learning_rate": 1.889958734525447e-05,
-      "loss": 0.2548,
+      "loss": 0.2561,
       "step": 540
     },
     {
       "epoch": 1.3431013431013432,
-      "grad_norm": 20.590370178222656,
+      "grad_norm": 23.86240577697754,
       "learning_rate": 1.862448418156809e-05,
-      "loss": 0.1266,
+      "loss": 0.1341,
       "step": 550
     },
     {
       "epoch": 1.3675213675213675,
-      "grad_norm": 19.7510929107666,
+      "grad_norm": 16.486339569091797,
       "learning_rate": 1.8349381017881708e-05,
-      "loss": 0.3163,
+      "loss": 0.2968,
       "step": 560
     },
     {
       "epoch": 1.3919413919413919,
-      "grad_norm": 43.13203048706055,
+      "grad_norm": 24.227453231811523,
       "learning_rate": 1.8074277854195327e-05,
-      "loss": 0.19,
+      "loss": 0.2631,
       "step": 570
     },
     {
       "epoch": 1.4163614163614164,
-      "grad_norm": 9.15944766998291,
+      "grad_norm": 11.713160514831543,
       "learning_rate": 1.7799174690508942e-05,
-      "loss": 0.2279,
+      "loss": 0.3079,
       "step": 580
     },
     {
       "epoch": 1.4407814407814408,
-      "grad_norm": 8.235884666442871,
+      "grad_norm": 18.98057746887207,
       "learning_rate": 1.7524071526822558e-05,
-      "loss": 0.1793,
+      "loss": 0.1686,
       "step": 590
     },
     {
       "epoch": 1.4652014652014653,
-      "grad_norm": 15.345870018005371,
+      "grad_norm": 22.216732025146484,
       "learning_rate": 1.7248968363136177e-05,
-      "loss": 0.1745,
+      "loss": 0.2011,
       "step": 600
     },
     {
       "epoch": 1.4652014652014653,
-      "eval_accuracy": 0.9132559560171044,
-      "eval_accuracy_label_negative": 0.9027777777777778,
-      "eval_accuracy_label_positive": 0.9230769230769231,
-      "eval_f1": 0.9132306675694815,
-      "eval_loss": 0.2216513752937317,
-      "eval_precision": 0.9133037139258499,
-      "eval_recall": 0.9132559560171044,
-      "eval_runtime": 6.2687,
-      "eval_samples_per_second": 261.138,
-      "eval_steps_per_second": 16.431,
+      "eval_accuracy": 0.9144777031154551,
+      "eval_accuracy_label_negative": 0.8813131313131313,
+      "eval_accuracy_label_positive": 0.9455621301775148,
+      "eval_f1": 0.914322392557606,
+      "eval_loss": 0.2633679211139679,
+      "eval_precision": 0.9157513070515966,
+      "eval_recall": 0.9144777031154551,
+      "eval_runtime": 7.238,
+      "eval_samples_per_second": 226.168,
+      "eval_steps_per_second": 14.23,
       "step": 600
     },
     {
       "epoch": 1.4896214896214897,
-      "grad_norm": 11.133660316467285,
+      "grad_norm": 5.728968620300293,
       "learning_rate": 1.6973865199449796e-05,
-      "loss": 0.1678,
+      "loss": 0.2781,
       "step": 610
     },
     {
       "epoch": 1.514041514041514,
-      "grad_norm": 19.868358612060547,
+      "grad_norm": 7.4687724113464355,
       "learning_rate": 1.669876203576341e-05,
-      "loss": 0.1957,
+      "loss": 0.2233,
       "step": 620
     },
     {
       "epoch": 1.5384615384615383,
-      "grad_norm": 12.538798332214355,
+      "grad_norm": 18.378847122192383,
       "learning_rate": 1.642365887207703e-05,
-      "loss": 0.1615,
+      "loss": 0.2147,
       "step": 630
     },
     {
       "epoch": 1.5628815628815629,
-      "grad_norm": 44.59722900390625,
+      "grad_norm": 18.625051498413086,
       "learning_rate": 1.614855570839065e-05,
-      "loss": 0.239,
+      "loss": 0.196,
       "step": 640
     },
     {
       "epoch": 1.5873015873015874,
-      "grad_norm": 21.872129440307617,
+      "grad_norm": 19.89263343811035,
       "learning_rate": 1.5873452544704268e-05,
-      "loss": 0.2026,
+      "loss": 0.1782,
       "step": 650
     },
     {
       "epoch": 1.6117216117216118,
-      "grad_norm": 69.74796295166016,
+      "grad_norm": 46.03261184692383,
       "learning_rate": 1.5598349381017883e-05,
-      "loss": 0.1606,
+      "loss": 0.1666,
       "step": 660
     },
     {
       "epoch": 1.636141636141636,
-      "grad_norm": 18.729034423828125,
+      "grad_norm": 18.096025466918945,
       "learning_rate": 1.53232462173315e-05,
-      "loss": 0.1394,
+      "loss": 0.1648,
       "step": 670
     },
     {
       "epoch": 1.6605616605616604,
-      "grad_norm": 34.83360290527344,
+      "grad_norm": 23.694866180419922,
       "learning_rate": 1.5048143053645119e-05,
-      "loss": 0.2067,
+      "loss": 0.2266,
       "step": 680
     },
     {
       "epoch": 1.684981684981685,
-      "grad_norm": 26.961673736572266,
+      "grad_norm": 19.052383422851562,
       "learning_rate": 1.4773039889958736e-05,
-      "loss": 0.2053,
+      "loss": 0.2008,
       "step": 690
     },
     {
       "epoch": 1.7094017094017095,
-      "grad_norm": 11.258790969848633,
+      "grad_norm": 16.585542678833008,
       "learning_rate": 1.4497936726272352e-05,
-      "loss": 0.21,
+      "loss": 0.2179,
       "step": 700
     },
     {
       "epoch": 1.7094017094017095,
-      "eval_accuracy": 0.9156994502138057,
-      "eval_accuracy_label_negative": 0.9078282828282829,
-      "eval_accuracy_label_positive": 0.9230769230769231,
-      "eval_f1": 0.9156840772951227,
-      "eval_loss": 0.21606621146202087,
-      "eval_precision": 0.9157125089385034,
-      "eval_recall": 0.9156994502138057,
-      "eval_runtime": 6.2326,
-      "eval_samples_per_second": 262.649,
-      "eval_steps_per_second": 16.526,
+      "eval_accuracy": 0.9016493585827734,
+      "eval_accuracy_label_negative": 0.8699494949494949,
+      "eval_accuracy_label_positive": 0.9313609467455621,
+      "eval_f1": 0.9014869243030004,
+      "eval_loss": 0.2657208740711212,
+      "eval_precision": 0.9026963282009316,
+      "eval_recall": 0.9016493585827734,
+      "eval_runtime": 7.1809,
+      "eval_samples_per_second": 227.967,
+      "eval_steps_per_second": 14.344,
       "step": 700
     },
     {
       "epoch": 1.7338217338217339,
-      "grad_norm": 11.965163230895996,
+      "grad_norm": 16.8792667388916,
       "learning_rate": 1.4222833562585972e-05,
-      "loss": 0.1675,
+      "loss": 0.1802,
       "step": 710
     },
     {
       "epoch": 1.7582417582417582,
-      "grad_norm": 9.539685249328613,
+      "grad_norm": 10.43722915649414,
       "learning_rate": 1.3947730398899588e-05,
-      "loss": 0.1617,
+      "loss": 0.1609,
       "step": 720
     },
     {
       "epoch": 1.7826617826617825,
-      "grad_norm": 13.261054039001465,
+      "grad_norm": 15.472962379455566,
       "learning_rate": 1.3672627235213205e-05,
-      "loss": 0.1469,
+      "loss": 0.1702,
       "step": 730
     },
     {
       "epoch": 1.807081807081807,
-      "grad_norm": 9.91487979888916,
+      "grad_norm": 3.905959367752075,
       "learning_rate": 1.3397524071526824e-05,
-      "loss": 0.1807,
+      "loss": 0.184,
       "step": 740
     },
     {
       "epoch": 1.8315018315018317,
-      "grad_norm": 4.809123992919922,
+      "grad_norm": 4.598665237426758,
       "learning_rate": 1.3122420907840441e-05,
-      "loss": 0.1937,
+      "loss": 0.1866,
       "step": 750
     },
     {
       "epoch": 1.855921855921856,
-      "grad_norm": 10.304144859313965,
+      "grad_norm": 25.891942977905273,
       "learning_rate": 1.284731774415406e-05,
-      "loss": 0.1712,
+      "loss": 0.16,
       "step": 760
     },
     {
       "epoch": 1.8803418803418803,
-      "grad_norm": 9.22486400604248,
+      "grad_norm": 24.572216033935547,
       "learning_rate": 1.2572214580467677e-05,
-      "loss": 0.1429,
+      "loss": 0.1498,
       "step": 770
     },
     {
       "epoch": 1.9047619047619047,
-      "grad_norm": 25.931554794311523,
+      "grad_norm": 21.231639862060547,
       "learning_rate": 1.2297111416781292e-05,
-      "loss": 0.1961,
+      "loss": 0.1992,
       "step": 780
     },
     {
       "epoch": 1.9291819291819292,
-      "grad_norm": 21.258495330810547,
+      "grad_norm": 11.721719741821289,
       "learning_rate": 1.2022008253094913e-05,
-      "loss": 0.2019,
+      "loss": 0.2038,
       "step": 790
     },
     {
       "epoch": 1.9536019536019538,
-      "grad_norm": 6.851562023162842,
+      "grad_norm": 27.692150115966797,
       "learning_rate": 1.1746905089408529e-05,
-      "loss": 0.1349,
+      "loss": 0.1465,
       "step": 800
     },
     {
       "epoch": 1.9536019536019538,
-      "eval_accuracy": 0.9242516799022602,
-      "eval_accuracy_label_negative": 0.9078282828282829,
-      "eval_accuracy_label_positive": 0.9396449704142011,
-      "eval_f1": 0.9242049416831661,
-      "eval_loss": 0.2092478722333908,
-      "eval_precision": 0.9244931103347949,
-      "eval_recall": 0.9242516799022602,
-      "eval_runtime": 6.2401,
-      "eval_samples_per_second": 262.338,
-      "eval_steps_per_second": 16.506,
+      "eval_accuracy": 0.9211973121563837,
+      "eval_accuracy_label_negative": 0.88510101010101,
+      "eval_accuracy_label_positive": 0.9550295857988166,
+      "eval_f1": 0.9210314107040481,
+      "eval_loss": 0.2150096446275711,
+      "eval_precision": 0.9228133900964925,
+      "eval_recall": 0.9211973121563837,
+      "eval_runtime": 7.2024,
+      "eval_samples_per_second": 227.286,
+      "eval_steps_per_second": 14.301,
       "step": 800
     },
     {
       "epoch": 1.978021978021978,
-      "grad_norm": 27.77749252319336,
+      "grad_norm": 16.974834442138672,
       "learning_rate": 1.1471801925722146e-05,
-      "loss": 0.2208,
+      "loss": 0.2372,
       "step": 810
     },
     {
       "epoch": 2.0024420024420024,
-      "grad_norm": 9.1483154296875,
+      "grad_norm": 11.423258781433105,
       "learning_rate": 1.1196698762035765e-05,
-      "loss": 0.1494,
+      "loss": 0.1668,
       "step": 820
     },
     {
       "epoch": 2.0268620268620268,
-      "grad_norm": 7.372486591339111,
+      "grad_norm": 4.174540996551514,
       "learning_rate": 1.0921595598349382e-05,
-      "loss": 0.1161,
+      "loss": 0.1013,
       "step": 830
     },
     {
       "epoch": 2.051282051282051,
-      "grad_norm": 9.255379676818848,
+      "grad_norm": 15.53784465789795,
       "learning_rate": 1.0646492434663e-05,
-      "loss": 0.1054,
+      "loss": 0.1242,
       "step": 840
     },
     {
       "epoch": 2.075702075702076,
-      "grad_norm": 14.69979476928711,
+      "grad_norm": 17.660886764526367,
       "learning_rate": 1.0371389270976618e-05,
-      "loss": 0.127,
+      "loss": 0.1352,
       "step": 850
     },
     {
       "epoch": 2.1001221001221,
-      "grad_norm": 5.8154473304748535,
+      "grad_norm": 21.627826690673828,
       "learning_rate": 1.0096286107290235e-05,
-      "loss": 0.1329,
+      "loss": 0.1283,
       "step": 860
     },
     {
       "epoch": 2.1245421245421245,
-      "grad_norm": 8.349048614501953,
+      "grad_norm": 8.318380355834961,
       "learning_rate": 9.821182943603852e-06,
-      "loss": 0.0872,
+      "loss": 0.0804,
       "step": 870
     },
     {
       "epoch": 2.148962148962149,
-      "grad_norm": 7.116409778594971,
+      "grad_norm": 1.088057279586792,
       "learning_rate": 9.54607977991747e-06,
-      "loss": 0.0743,
+      "loss": 0.0708,
       "step": 880
     },
     {
       "epoch": 2.173382173382173,
-      "grad_norm": 2.7027432918548584,
+      "grad_norm": 17.630653381347656,
       "learning_rate": 9.270976616231088e-06,
-      "loss": 0.1437,
+      "loss": 0.162,
       "step": 890
     },
     {
       "epoch": 2.197802197802198,
-      "grad_norm": 13.962987899780273,
+      "grad_norm": 11.629766464233398,
       "learning_rate": 8.995873452544705e-06,
-      "loss": 0.1795,
+      "loss": 0.1602,
       "step": 900
     },
     {
       "epoch": 2.197802197802198,
-      "eval_accuracy": 0.9175320708613317,
-      "eval_accuracy_label_negative": 0.9431818181818182,
-      "eval_accuracy_label_positive": 0.893491124260355,
-      "eval_f1": 0.9175431498623747,
-      "eval_loss": 0.24922694265842438,
-      "eval_precision": 0.918941636944056,
-      "eval_recall": 0.9175320708613317,
-      "eval_runtime": 6.239,
-      "eval_samples_per_second": 262.38,
-      "eval_steps_per_second": 16.509,
+      "eval_accuracy": 0.9260843005497862,
+      "eval_accuracy_label_negative": 0.9356060606060606,
+      "eval_accuracy_label_positive": 0.9171597633136095,
+      "eval_f1": 0.9261021267687455,
+      "eval_loss": 0.24208489060401917,
+      "eval_precision": 0.9263694729331046,
+      "eval_recall": 0.9260843005497862,
+      "eval_runtime": 7.1999,
+      "eval_samples_per_second": 227.363,
+      "eval_steps_per_second": 14.306,
       "step": 900
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 1.1736209392547607,
+      "grad_norm": 26.855487823486328,
       "learning_rate": 8.720770288858322e-06,
-      "loss": 0.1549,
+      "loss": 0.181,
       "step": 910
     },
     {
       "epoch": 2.2466422466422467,
-      "grad_norm": 9.85667610168457,
+      "grad_norm": 8.824442863464355,
       "learning_rate": 8.44566712517194e-06,
-      "loss": 0.1192,
+      "loss": 0.1423,
       "step": 920
     },
     {
       "epoch": 2.271062271062271,
-      "grad_norm": 22.14609146118164,
+      "grad_norm": 12.806025505065918,
       "learning_rate": 8.170563961485558e-06,
-      "loss": 0.144,
+      "loss": 0.1352,
       "step": 930
     },
     {
       "epoch": 2.2954822954822953,
-      "grad_norm": 1.3833993673324585,
+      "grad_norm": 12.534196853637695,
       "learning_rate": 7.895460797799176e-06,
-      "loss": 0.1299,
+      "loss": 0.1318,
       "step": 940
     },
     {
       "epoch": 2.3199023199023197,
-      "grad_norm": 18.047609329223633,
+      "grad_norm": 25.678712844848633,
       "learning_rate": 7.620357634112793e-06,
-      "loss": 0.1161,
+      "loss": 0.1166,
       "step": 950
     },
     {
       "epoch": 2.3443223443223444,
-      "grad_norm": 26.69508171081543,
+      "grad_norm": 12.111174583435059,
       "learning_rate": 7.345254470426411e-06,
-      "loss": 0.0901,
+      "loss": 0.0941,
       "step": 960
     },
     {
       "epoch": 2.3687423687423688,
-      "grad_norm": 2.519742965698242,
+      "grad_norm": 1.4796338081359863,
       "learning_rate": 7.070151306740029e-06,
-      "loss": 0.0839,
+      "loss": 0.0864,
       "step": 970
     },
     {
       "epoch": 2.393162393162393,
-      "grad_norm": 51.8133659362793,
+      "grad_norm": 2.2377712726593018,
       "learning_rate": 6.795048143053645e-06,
-      "loss": 0.156,
+      "loss": 0.1344,
       "step": 980
     },
     {
       "epoch": 2.4175824175824174,
-      "grad_norm": 31.978530883789062,
+      "grad_norm": 20.148027420043945,
       "learning_rate": 6.519944979367263e-06,
-      "loss": 0.1026,
+      "loss": 0.135,
       "step": 990
     },
     {
       "epoch": 2.442002442002442,
-      "grad_norm": 35.09687042236328,
+      "grad_norm": 35.98054504394531,
       "learning_rate": 6.244841815680881e-06,
-      "loss": 0.107,
+      "loss": 0.1293,
       "step": 1000
     },
     {
       "epoch": 2.442002442002442,
-      "eval_accuracy": 0.9120342089187539,
-      "eval_accuracy_label_negative": 0.9595959595959596,
-      "eval_accuracy_label_positive": 0.8674556213017751,
-      "eval_f1": 0.911963285711659,
-      "eval_loss": 0.274323433637619,
-      "eval_precision": 0.9162668443060722,
-      "eval_recall": 0.9120342089187539,
-      "eval_runtime": 6.2476,
-      "eval_samples_per_second": 262.022,
-      "eval_steps_per_second": 16.486,
+      "eval_accuracy": 0.918142944410507,
+      "eval_accuracy_label_negative": 0.952020202020202,
+      "eval_accuracy_label_positive": 0.8863905325443787,
+      "eval_f1": 0.9181340858978576,
+      "eval_loss": 0.26929038763046265,
+      "eval_precision": 0.9204337690751875,
+      "eval_recall": 0.918142944410507,
+      "eval_runtime": 7.2331,
+      "eval_samples_per_second": 226.321,
+      "eval_steps_per_second": 14.24,
       "step": 1000
     },
     {
       "epoch": 2.4664224664224665,
-      "grad_norm": 63.01274108886719,
+      "grad_norm": 5.845112323760986,
       "learning_rate": 5.969738651994499e-06,
-      "loss": 0.1913,
+      "loss": 0.1468,
       "step": 1010
     },
     {
       "epoch": 2.490842490842491,
-      "grad_norm": 59.207305908203125,
+      "grad_norm": 37.39576721191406,
       "learning_rate": 5.6946354883081155e-06,
-      "loss": 0.1108,
+      "loss": 0.0503,
       "step": 1020
     },
     {
       "epoch": 2.515262515262515,
-      "grad_norm": 11.869065284729004,
+      "grad_norm": 4.044558525085449,
       "learning_rate": 5.4195323246217335e-06,
-      "loss": 0.0884,
+      "loss": 0.0569,
       "step": 1030
     },
     {
       "epoch": 2.5396825396825395,
-      "grad_norm": 12.766225814819336,
+      "grad_norm": 0.4750860035419464,
       "learning_rate": 5.1444291609353515e-06,
-      "loss": 0.1491,
+      "loss": 0.1722,
       "step": 1040
     },
     {
       "epoch": 2.564102564102564,
-      "grad_norm": 5.824493408203125,
+      "grad_norm": 19.243858337402344,
       "learning_rate": 4.869325997248969e-06,
-      "loss": 0.1633,
+      "loss": 0.1649,
       "step": 1050
     },
     {
       "epoch": 2.5885225885225887,
-      "grad_norm": 6.6170477867126465,
+      "grad_norm": 64.03276062011719,
       "learning_rate": 4.594222833562587e-06,
-      "loss": 0.1276,
+      "loss": 0.133,
       "step": 1060
     },
     {
       "epoch": 2.612942612942613,
-      "grad_norm": 9.731184959411621,
+      "grad_norm": 17.09507179260254,
       "learning_rate": 4.319119669876204e-06,
-      "loss": 0.1023,
+      "loss": 0.1118,
       "step": 1070
     },
     {
       "epoch": 2.6373626373626373,
-      "grad_norm": 3.0301451683044434,
+      "grad_norm": 3.7031028270721436,
       "learning_rate": 4.044016506189822e-06,
-      "loss": 0.1082,
+      "loss": 0.1125,
       "step": 1080
     },
     {
       "epoch": 2.6617826617826617,
-      "grad_norm": 3.955033779144287,
+      "grad_norm": 6.265291213989258,
       "learning_rate": 3.768913342503439e-06,
-      "loss": 0.1763,
+      "loss": 0.1255,
       "step": 1090
     },
     {
       "epoch": 2.6862026862026864,
-      "grad_norm": 46.200225830078125,
+      "grad_norm": 12.135473251342773,
       "learning_rate": 3.4938101788170562e-06,
-      "loss": 0.08,
+      "loss": 0.1023,
       "step": 1100
     },
     {
       "epoch": 2.6862026862026864,
-      "eval_accuracy": 0.9187538179596824,
-      "eval_accuracy_label_negative": 0.9431818181818182,
-      "eval_accuracy_label_positive": 0.8958579881656805,
-      "eval_f1": 0.9187668553379099,
-      "eval_loss": 0.2606331408023834,
-      "eval_precision": 0.9200482702030894,
-      "eval_recall": 0.9187538179596824,
-      "eval_runtime": 6.2203,
-      "eval_samples_per_second": 263.172,
-      "eval_steps_per_second": 16.559,
+      "eval_accuracy": 0.9236408063530849,
+      "eval_accuracy_label_negative": 0.9343434343434344,
+      "eval_accuracy_label_positive": 0.9136094674556213,
+      "eval_f1": 0.9236599621062943,
+      "eval_loss": 0.2392093390226364,
+      "eval_precision": 0.9239831192044239,
+      "eval_recall": 0.9236408063530849,
+      "eval_runtime": 7.1958,
+      "eval_samples_per_second": 227.494,
+      "eval_steps_per_second": 14.314,
       "step": 1100
     },
     {
       "epoch": 2.7106227106227108,
-      "grad_norm": 42.084537506103516,
+      "grad_norm": 27.403955459594727,
       "learning_rate": 3.2187070151306742e-06,
-      "loss": 0.1241,
+      "loss": 0.1475,
       "step": 1110
     },
     {
       "epoch": 2.735042735042735,
-      "grad_norm": 11.397581100463867,
+      "grad_norm": 11.365577697753906,
       "learning_rate": 2.943603851444292e-06,
-      "loss": 0.0858,
+      "loss": 0.0816,
       "step": 1120
     },
     {
       "epoch": 2.7594627594627594,
-      "grad_norm": 58.64878845214844,
+      "grad_norm": 6.001681327819824,
       "learning_rate": 2.6685006877579094e-06,
-      "loss": 0.1114,
+      "loss": 0.0767,
       "step": 1130
     },
     {
       "epoch": 2.7838827838827838,
-      "grad_norm": 43.395687103271484,
+      "grad_norm": 8.82612133026123,
       "learning_rate": 2.393397524071527e-06,
-      "loss": 0.1682,
+      "loss": 0.1703,
       "step": 1140
     },
     {
       "epoch": 2.808302808302808,
-      "grad_norm": 17.384784698486328,
+      "grad_norm": 8.14811897277832,
       "learning_rate": 2.1182943603851446e-06,
-      "loss": 0.1692,
+      "loss": 0.1812,
       "step": 1150
     },
     {
       "epoch": 2.832722832722833,
-      "grad_norm": 24.320571899414062,
+      "grad_norm": 31.67622947692871,
       "learning_rate": 1.8431911966987622e-06,
-      "loss": 0.1473,
+      "loss": 0.1133,
       "step": 1160
     },
     {
       "epoch": 2.857142857142857,
-      "grad_norm": 2.8611717224121094,
+      "grad_norm": 1.591486930847168,
       "learning_rate": 1.56808803301238e-06,
-      "loss": 0.1429,
+      "loss": 0.1374,
       "step": 1170
     },
     {
       "epoch": 2.8815628815628815,
-      "grad_norm": 16.274402618408203,
+      "grad_norm": 17.23202133178711,
       "learning_rate": 1.2929848693259976e-06,
-      "loss": 0.0589,
+      "loss": 0.0764,
       "step": 1180
     },
     {
       "epoch": 2.905982905982906,
-      "grad_norm": 12.312983512878418,
+      "grad_norm": 34.02734375,
       "learning_rate": 1.017881705639615e-06,
-      "loss": 0.113,
+      "loss": 0.1168,
       "step": 1190
     },
     {
       "epoch": 2.9304029304029307,
-      "grad_norm": 2.3755383491516113,
+      "grad_norm": 22.118793487548828,
       "learning_rate": 7.427785419532325e-07,
-      "loss": 0.1275,
+      "loss": 0.1663,
       "step": 1200
     },
     {
       "epoch": 2.9304029304029307,
-      "eval_accuracy": 0.9254734270006109,
-      "eval_accuracy_label_negative": 0.9166666666666666,
-      "eval_accuracy_label_positive": 0.9337278106508876,
-      "eval_f1": 0.9254558801955471,
-      "eval_loss": 0.2550033628940582,
-      "eval_precision": 0.925507524308242,
-      "eval_recall": 0.9254734270006109,
-      "eval_runtime": 6.2179,
-      "eval_samples_per_second": 263.27,
-      "eval_steps_per_second": 16.565,
+      "eval_accuracy": 0.9266951740989615,
+      "eval_accuracy_label_negative": 0.9116161616161617,
+      "eval_accuracy_label_positive": 0.9408284023668639,
+      "eval_f1": 0.9266551563584942,
+      "eval_loss": 0.23257231712341309,
+      "eval_precision": 0.9268925841919743,
+      "eval_recall": 0.9266951740989615,
+      "eval_runtime": 7.2209,
+      "eval_samples_per_second": 226.702,
+      "eval_steps_per_second": 14.264,
       "step": 1200
     },
     {
       "epoch": 2.954822954822955,
-      "grad_norm": 11.446648597717285,
+      "grad_norm": 3.313932180404663,
       "learning_rate": 4.6767537826685014e-07,
-      "loss": 0.0984,
+      "loss": 0.1202,
       "step": 1210
     },
     {
       "epoch": 2.9792429792429793,
-      "grad_norm": 6.963866710662842,
+      "grad_norm": 0.9627939462661743,
       "learning_rate": 1.925722145804677e-07,
-      "loss": 0.1507,
+      "loss": 0.1192,
       "step": 1220
     },
     {
       "epoch": 2.9963369963369964,
       "step": 1227,
       "total_flos": 157212915612480.0,
-      "train_loss": 0.22916113538477803,
-      "train_runtime": 681.0988,
-      "train_samples_per_second": 57.657,
-      "train_steps_per_second": 1.802
+      "train_loss": 0.23136130925009868,
+      "train_runtime": 743.9513,
+      "train_samples_per_second": 52.786,
+      "train_steps_per_second": 1.649
     },
     {
       "epoch": 2.9963369963369964,
-      "eval_accuracy": 0.9260843005497862,
-      "eval_accuracy_label_negative": 0.9255050505050505,
-      "eval_accuracy_label_positive": 0.9266272189349113,
-      "eval_f1": 0.9260884418426176,
-      "eval_loss": 0.25100183486938477,
-      "eval_precision": 0.9260988078725894,
-      "eval_recall": 0.9260843005497862,
-      "eval_runtime": 6.2023,
-      "eval_samples_per_second": 263.933,
-      "eval_steps_per_second": 16.607,
+      "eval_accuracy": 0.9279169211973122,
+      "eval_accuracy_label_negative": 0.9191919191919192,
+      "eval_accuracy_label_positive": 0.936094674556213,
+      "eval_f1": 0.9278999496973325,
+      "eval_loss": 0.23104961216449738,
+      "eval_precision": 0.9279523524296256,
+      "eval_recall": 0.9279169211973122,
+      "eval_runtime": 7.2423,
+      "eval_samples_per_second": 226.035,
+      "eval_steps_per_second": 14.222,
       "step": 1227
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77dd615ba71b2a8d8c66ba94dd7fd0658b87a82877f81bfc34cc2e72b1f9dc5c
+oid sha256:cc4c8c16d0ab515ce7f7755e76edb90e120058b508e8d35ad4fdb7c19fb946f1
 size 5048