Frenz/modelsent_test

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 license: apache-2.0
 base_model: albert/albert-base-v2
 tags:
@@ -18,15 +19,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # modelsent_test
 
-This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
+This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on the None dataset.
 It achieves the following results on the evaluation set:
-- 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
+- Loss: 0.2374
+- Accuracy: 0.9255
+- F1: 0.9255
+- Precision: 0.9255
+- Recall: 0.9255
+- Accuracy Label Negative: 0.9268
+- Accuracy Label Positive: 0.9243
 
 ## Model description
 
@@ -51,7 +52,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 32
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 3
@@ -60,23 +61,23 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Accuracy Label Negative | Accuracy Label Positive |
 |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-----------------------:|:-----------------------:|
-| 0.5427        | 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                  |
+| 1.0862        | 0.2442 | 100  | 0.5049          | 0.7789   | 0.7786 | 0.7832    | 0.7789 | 0.8295                  | 0.7314                  |
+| 0.5271        | 0.4884 | 200  | 0.2858          | 0.9023   | 0.9023 | 0.9040    | 0.9023 | 0.9306                  | 0.8757                  |
+| 0.4448        | 0.7326 | 300  | 0.2418          | 0.9163   | 0.9163 | 0.9163    | 0.9163 | 0.9091                  | 0.9231                  |
+| 0.5582        | 0.9768 | 400  | 0.2191          | 0.9236   | 0.9237 | 0.9237    | 0.9236 | 0.9268                  | 0.9207                  |
+| 0.4054        | 1.2198 | 500  | 0.2682          | 0.9145   | 0.9144 | 0.9178    | 0.9145 | 0.9558                  | 0.8757                  |
+| 0.3433        | 1.4640 | 600  | 0.2552          | 0.9151   | 0.9150 | 0.9157    | 0.9151 | 0.8902                  | 0.9385                  |
+| 0.5589        | 1.7082 | 700  | 0.2087          | 0.9133   | 0.9131 | 0.9144    | 0.9133 | 0.8813                  | 0.9432                  |
+| 0.2343        | 1.9524 | 800  | 0.2110          | 0.9181   | 0.9181 | 0.9188    | 0.9181 | 0.8939                  | 0.9408                  |
+| 0.2403        | 2.1954 | 900  | 0.2314          | 0.9224   | 0.9224 | 0.9227    | 0.9224 | 0.9318                  | 0.9136                  |
+| 0.2643        | 2.4396 | 1000 | 0.2996          | 0.9041   | 0.9039 | 0.9102    | 0.9041 | 0.9621                  | 0.8497                  |
+| 0.1856        | 2.6838 | 1100 | 0.2395          | 0.9218   | 0.9218 | 0.9222    | 0.9218 | 0.9343                  | 0.9101                  |
+| 0.3018        | 2.9280 | 1200 | 0.2376          | 0.9261   | 0.9261 | 0.9261    | 0.9261 | 0.9242                  | 0.9278                  |
 
 
 ### Framework versions
 
-- Transformers 4.41.2
-- Pytorch 2.3.0+cu121
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -36,7 +36,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.47.1",
   "type_vocab_size": 2,
   "vocab_size": 30000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7658f279f86ab2384500a655e07375ddbae1aedf7d189dd07a1bbf49bbd867ca
+oid sha256:53bc6e9afc36255a6f3245c393a03dc0544a202734f36f5493f5dc6955e177ad
 size 46743912

runs/Dec19_20-58-22_bd1bb20444ea/events.out.tfevents.1734641916.bd1bb20444ea.1518.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2011bb7c07cbdcbcec9250fedd1e17bb0819a33fc9dc86d54d6ae40aeff5c296
+size 5334

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9963369963369964,
+  "epoch": 2.993894993894994,
   "eval_steps": 100,
   "global_step": 1227,
   "is_hyper_param_search": false,
@@ -10,1047 +10,1047 @@
   "log_history": [
     {
       "epoch": 0.02442002442002442,
-      "grad_norm": 20.259180068969727,
+      "grad_norm": 43.265899658203125,
       "learning_rate": 4.0000000000000003e-07,
-      "loss": 0.7339,
+      "loss": 1.5045,
       "step": 10
     },
     {
       "epoch": 0.04884004884004884,
-      "grad_norm": 14.779166221618652,
+      "grad_norm": 37.62464141845703,
       "learning_rate": 8.000000000000001e-07,
-      "loss": 0.7128,
+      "loss": 1.4611,
       "step": 20
     },
     {
       "epoch": 0.07326007326007326,
-      "grad_norm": 14.740580558776855,
+      "grad_norm": 34.83750534057617,
       "learning_rate": 1.2000000000000002e-06,
-      "loss": 0.6777,
+      "loss": 1.3954,
       "step": 30
     },
     {
       "epoch": 0.09768009768009768,
-      "grad_norm": 15.626840591430664,
+      "grad_norm": 28.517704010009766,
       "learning_rate": 1.6000000000000001e-06,
-      "loss": 0.6666,
+      "loss": 1.3351,
       "step": 40
     },
     {
       "epoch": 0.1221001221001221,
-      "grad_norm": 15.19382095336914,
+      "grad_norm": 28.224279403686523,
       "learning_rate": 2.0000000000000003e-06,
-      "loss": 0.6723,
+      "loss": 1.3337,
       "step": 50
     },
     {
       "epoch": 0.14652014652014653,
-      "grad_norm": 18.021406173706055,
+      "grad_norm": 33.45441818237305,
       "learning_rate": 2.4000000000000003e-06,
-      "loss": 0.6702,
+      "loss": 1.3357,
       "step": 60
     },
     {
       "epoch": 0.17094017094017094,
-      "grad_norm": 14.912147521972656,
+      "grad_norm": 28.07544708251953,
       "learning_rate": 2.8000000000000003e-06,
-      "loss": 0.6382,
+      "loss": 1.2805,
       "step": 70
     },
     {
       "epoch": 0.19536019536019536,
-      "grad_norm": 18.795974731445312,
+      "grad_norm": 28.925960540771484,
       "learning_rate": 3.2000000000000003e-06,
-      "loss": 0.6014,
+      "loss": 1.2157,
       "step": 80
     },
     {
       "epoch": 0.21978021978021978,
-      "grad_norm": 14.359152793884277,
+      "grad_norm": 29.959428787231445,
       "learning_rate": 3.6000000000000003e-06,
-      "loss": 0.5685,
+      "loss": 1.1112,
       "step": 90
     },
     {
       "epoch": 0.2442002442002442,
-      "grad_norm": 16.193758010864258,
+      "grad_norm": 33.78961181640625,
       "learning_rate": 4.000000000000001e-06,
-      "loss": 0.5427,
+      "loss": 1.0862,
       "step": 100
     },
     {
       "epoch": 0.2442002442002442,
-      "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,
+      "eval_accuracy": 0.7788637751985339,
+      "eval_accuracy_label_negative": 0.8295454545454546,
+      "eval_accuracy_label_positive": 0.7313609467455622,
+      "eval_f1": 0.7785675230312261,
+      "eval_loss": 0.5048791766166687,
+      "eval_precision": 0.7832195543584349,
+      "eval_recall": 0.7788637751985339,
+      "eval_runtime": 6.4624,
+      "eval_samples_per_second": 253.312,
+      "eval_steps_per_second": 15.938,
       "step": 100
     },
     {
       "epoch": 0.2686202686202686,
-      "grad_norm": 15.085676193237305,
+      "grad_norm": 224.80953979492188,
       "learning_rate": 4.4e-06,
-      "loss": 0.5023,
+      "loss": 0.9569,
       "step": 110
     },
     {
       "epoch": 0.29304029304029305,
-      "grad_norm": 19.296276092529297,
+      "grad_norm": 29.302122116088867,
       "learning_rate": 4.800000000000001e-06,
-      "loss": 0.4881,
+      "loss": 0.9296,
       "step": 120
     },
     {
       "epoch": 0.31746031746031744,
-      "grad_norm": 29.949970245361328,
+      "grad_norm": 50.676483154296875,
       "learning_rate": 5.2e-06,
-      "loss": 0.3837,
+      "loss": 0.7184,
       "step": 130
     },
     {
       "epoch": 0.3418803418803419,
-      "grad_norm": 22.738380432128906,
+      "grad_norm": 58.53715896606445,
       "learning_rate": 5.600000000000001e-06,
-      "loss": 0.352,
+      "loss": 0.6639,
       "step": 140
     },
     {
       "epoch": 0.3663003663003663,
-      "grad_norm": 62.512149810791016,
+      "grad_norm": 46.839027404785156,
       "learning_rate": 6e-06,
-      "loss": 0.3676,
+      "loss": 0.7018,
       "step": 150
     },
     {
       "epoch": 0.3907203907203907,
-      "grad_norm": 28.634130477905273,
+      "grad_norm": 65.95608520507812,
       "learning_rate": 6.4000000000000006e-06,
-      "loss": 0.306,
+      "loss": 0.5796,
       "step": 160
     },
     {
       "epoch": 0.41514041514041516,
-      "grad_norm": 27.88077735900879,
+      "grad_norm": 51.919952392578125,
       "learning_rate": 6.800000000000001e-06,
-      "loss": 0.2976,
+      "loss": 0.6001,
       "step": 170
     },
     {
       "epoch": 0.43956043956043955,
-      "grad_norm": 26.289413452148438,
+      "grad_norm": 55.32732009887695,
       "learning_rate": 7.2000000000000005e-06,
-      "loss": 0.3203,
+      "loss": 0.5641,
       "step": 180
     },
     {
       "epoch": 0.463980463980464,
-      "grad_norm": 38.563026428222656,
+      "grad_norm": 74.93069458007812,
       "learning_rate": 7.600000000000001e-06,
-      "loss": 0.2835,
+      "loss": 0.5436,
       "step": 190
     },
     {
       "epoch": 0.4884004884004884,
-      "grad_norm": 19.998462677001953,
+      "grad_norm": 25.58298110961914,
       "learning_rate": 8.000000000000001e-06,
-      "loss": 0.2745,
+      "loss": 0.5271,
       "step": 200
     },
     {
       "epoch": 0.4884004884004884,
-      "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,
+      "eval_accuracy": 0.9022602321319487,
+      "eval_accuracy_label_negative": 0.9305555555555556,
+      "eval_accuracy_label_positive": 0.8757396449704142,
+      "eval_f1": 0.9022657031312846,
+      "eval_loss": 0.2857775390148163,
+      "eval_precision": 0.9039560384223848,
+      "eval_recall": 0.9022602321319487,
+      "eval_runtime": 6.6059,
+      "eval_samples_per_second": 247.808,
+      "eval_steps_per_second": 15.592,
       "step": 200
     },
     {
       "epoch": 0.5128205128205128,
-      "grad_norm": 28.719772338867188,
+      "grad_norm": 46.91861343383789,
       "learning_rate": 8.400000000000001e-06,
-      "loss": 0.2126,
+      "loss": 0.4353,
       "step": 210
     },
     {
       "epoch": 0.5372405372405372,
-      "grad_norm": 18.826200485229492,
+      "grad_norm": 84.31887817382812,
       "learning_rate": 8.8e-06,
-      "loss": 0.226,
+      "loss": 0.4125,
       "step": 220
     },
     {
       "epoch": 0.5616605616605617,
-      "grad_norm": 10.376764297485352,
+      "grad_norm": 12.006002426147461,
       "learning_rate": 9.200000000000002e-06,
-      "loss": 0.285,
+      "loss": 0.5151,
       "step": 230
     },
     {
       "epoch": 0.5860805860805861,
-      "grad_norm": 8.594544410705566,
+      "grad_norm": 9.51772403717041,
       "learning_rate": 9.600000000000001e-06,
-      "loss": 0.2463,
+      "loss": 0.5596,
       "step": 240
     },
     {
       "epoch": 0.6105006105006106,
-      "grad_norm": 37.928585052490234,
+      "grad_norm": 49.31715393066406,
       "learning_rate": 1e-05,
-      "loss": 0.2655,
+      "loss": 0.5192,
       "step": 250
     },
     {
       "epoch": 0.6349206349206349,
-      "grad_norm": 15.18250560760498,
+      "grad_norm": 99.71334838867188,
       "learning_rate": 1.04e-05,
-      "loss": 0.2481,
+      "loss": 0.4906,
       "step": 260
     },
     {
       "epoch": 0.6593406593406593,
-      "grad_norm": 22.519500732421875,
+      "grad_norm": 18.97690773010254,
       "learning_rate": 1.0800000000000002e-05,
-      "loss": 0.2731,
+      "loss": 0.5602,
       "step": 270
     },
     {
       "epoch": 0.6837606837606838,
-      "grad_norm": 17.65134620666504,
+      "grad_norm": 51.922142028808594,
       "learning_rate": 1.1200000000000001e-05,
-      "loss": 0.1948,
+      "loss": 0.4599,
       "step": 280
     },
     {
       "epoch": 0.7081807081807082,
-      "grad_norm": 15.242578506469727,
+      "grad_norm": 26.68296241760254,
       "learning_rate": 1.16e-05,
-      "loss": 0.2033,
+      "loss": 0.4887,
       "step": 290
     },
     {
       "epoch": 0.7326007326007326,
-      "grad_norm": 13.12796688079834,
+      "grad_norm": 42.840782165527344,
       "learning_rate": 1.2e-05,
-      "loss": 0.2409,
+      "loss": 0.4448,
       "step": 300
     },
     {
       "epoch": 0.7326007326007326,
-      "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,
+      "eval_accuracy": 0.916310323762981,
+      "eval_accuracy_label_negative": 0.9090909090909091,
+      "eval_accuracy_label_positive": 0.9230769230769231,
+      "eval_f1": 0.9162971894414865,
+      "eval_loss": 0.24179790914058685,
+      "eval_precision": 0.916317612377141,
+      "eval_recall": 0.916310323762981,
+      "eval_runtime": 6.1349,
+      "eval_samples_per_second": 266.833,
+      "eval_steps_per_second": 16.789,
       "step": 300
     },
     {
       "epoch": 0.757020757020757,
-      "grad_norm": 108.63019561767578,
+      "grad_norm": 42.57475280761719,
       "learning_rate": 1.2400000000000002e-05,
-      "loss": 0.3153,
+      "loss": 0.5235,
       "step": 310
     },
     {
       "epoch": 0.7814407814407814,
-      "grad_norm": 3.575650453567505,
+      "grad_norm": 15.34103775024414,
       "learning_rate": 1.2800000000000001e-05,
-      "loss": 0.2238,
+      "loss": 0.3713,
       "step": 320
     },
     {
       "epoch": 0.8058608058608059,
-      "grad_norm": 1.4278050661087036,
+      "grad_norm": 5.413728713989258,
       "learning_rate": 1.3200000000000002e-05,
-      "loss": 0.2762,
+      "loss": 0.5713,
       "step": 330
     },
     {
       "epoch": 0.8302808302808303,
-      "grad_norm": 12.686599731445312,
+      "grad_norm": 13.065258026123047,
       "learning_rate": 1.3600000000000002e-05,
-      "loss": 0.2433,
+      "loss": 0.5092,
       "step": 340
     },
     {
       "epoch": 0.8547008547008547,
-      "grad_norm": 8.050217628479004,
+      "grad_norm": 29.859405517578125,
       "learning_rate": 1.4e-05,
-      "loss": 0.2258,
+      "loss": 0.5218,
       "step": 350
     },
     {
       "epoch": 0.8791208791208791,
-      "grad_norm": 23.091922760009766,
+      "grad_norm": 76.65414428710938,
       "learning_rate": 1.4400000000000001e-05,
-      "loss": 0.2986,
+      "loss": 0.5731,
       "step": 360
     },
     {
       "epoch": 0.9035409035409036,
-      "grad_norm": 20.166908264160156,
+      "grad_norm": 38.61219024658203,
       "learning_rate": 1.48e-05,
-      "loss": 0.29,
+      "loss": 0.5184,
       "step": 370
     },
     {
       "epoch": 0.927960927960928,
-      "grad_norm": 19.215978622436523,
+      "grad_norm": 30.961179733276367,
       "learning_rate": 1.5200000000000002e-05,
-      "loss": 0.1558,
+      "loss": 0.3836,
       "step": 380
     },
     {
       "epoch": 0.9523809523809523,
-      "grad_norm": 24.995752334594727,
+      "grad_norm": 162.6136016845703,
       "learning_rate": 1.5600000000000003e-05,
-      "loss": 0.168,
+      "loss": 0.4617,
       "step": 390
     },
     {
       "epoch": 0.9768009768009768,
-      "grad_norm": 14.634511947631836,
+      "grad_norm": 14.536166191101074,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.2717,
+      "loss": 0.5582,
       "step": 400
     },
     {
       "epoch": 0.9768009768009768,
-      "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,
+      "eval_accuracy": 0.9236408063530849,
+      "eval_accuracy_label_negative": 0.9267676767676768,
+      "eval_accuracy_label_positive": 0.9207100591715977,
+      "eval_f1": 0.9236520984092678,
+      "eval_loss": 0.21909849345684052,
+      "eval_precision": 0.9237192468386612,
+      "eval_recall": 0.9236408063530849,
+      "eval_runtime": 6.071,
+      "eval_samples_per_second": 269.644,
+      "eval_steps_per_second": 16.966,
       "step": 400
     },
     {
-      "epoch": 1.0012210012210012,
-      "grad_norm": 4.358543872833252,
+      "epoch": 1.0,
+      "grad_norm": 8.102620124816895,
       "learning_rate": 1.64e-05,
-      "loss": 0.152,
+      "loss": 0.3272,
       "step": 410
     },
     {
-      "epoch": 1.0256410256410255,
-      "grad_norm": 12.582831382751465,
+      "epoch": 1.0244200244200243,
+      "grad_norm": 102.95278930664062,
       "learning_rate": 1.6800000000000002e-05,
-      "loss": 0.1771,
+      "loss": 0.354,
       "step": 420
     },
     {
-      "epoch": 1.05006105006105,
-      "grad_norm": 70.92117309570312,
+      "epoch": 1.0488400488400489,
+      "grad_norm": 19.004304885864258,
       "learning_rate": 1.72e-05,
-      "loss": 0.2099,
+      "loss": 0.4163,
       "step": 430
     },
     {
-      "epoch": 1.0744810744810744,
-      "grad_norm": 17.06641387939453,
+      "epoch": 1.0732600732600732,
+      "grad_norm": 3.0345256328582764,
       "learning_rate": 1.76e-05,
-      "loss": 0.1686,
+      "loss": 0.2336,
       "step": 440
     },
     {
-      "epoch": 1.098901098901099,
-      "grad_norm": 23.57867431640625,
+      "epoch": 1.0976800976800978,
+      "grad_norm": 6.5663604736328125,
       "learning_rate": 1.8e-05,
-      "loss": 0.3161,
+      "loss": 0.4468,
       "step": 450
     },
     {
-      "epoch": 1.1233211233211233,
-      "grad_norm": 7.516932487487793,
+      "epoch": 1.122100122100122,
+      "grad_norm": 15.335294723510742,
       "learning_rate": 1.8400000000000003e-05,
-      "loss": 0.2111,
+      "loss": 0.5378,
       "step": 460
     },
     {
-      "epoch": 1.1477411477411477,
-      "grad_norm": 24.830093383789062,
+      "epoch": 1.1465201465201464,
+      "grad_norm": 23.567869186401367,
       "learning_rate": 1.88e-05,
-      "loss": 0.1837,
+      "loss": 0.4598,
       "step": 470
     },
     {
-      "epoch": 1.1721611721611722,
-      "grad_norm": 25.01032257080078,
+      "epoch": 1.170940170940171,
+      "grad_norm": 119.62120819091797,
       "learning_rate": 1.9200000000000003e-05,
-      "loss": 0.1845,
+      "loss": 0.4447,
       "step": 480
     },
     {
-      "epoch": 1.1965811965811965,
-      "grad_norm": 8.994218826293945,
+      "epoch": 1.1953601953601953,
+      "grad_norm": 5.290420055389404,
       "learning_rate": 1.9600000000000002e-05,
-      "loss": 0.1015,
+      "loss": 0.214,
       "step": 490
     },
     {
-      "epoch": 1.221001221001221,
-      "grad_norm": 33.930198669433594,
+      "epoch": 1.2197802197802199,
+      "grad_norm": 220.08334350585938,
       "learning_rate": 2e-05,
-      "loss": 0.2178,
+      "loss": 0.4054,
       "step": 500
     },
     {
-      "epoch": 1.221001221001221,
-      "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,
+      "epoch": 1.2197802197802199,
+      "eval_accuracy": 0.9144777031154551,
+      "eval_accuracy_label_negative": 0.9558080808080808,
+      "eval_accuracy_label_positive": 0.8757396449704142,
+      "eval_f1": 0.9144397212931268,
+      "eval_loss": 0.26820144057273865,
+      "eval_precision": 0.9177552790543617,
+      "eval_recall": 0.9144777031154551,
+      "eval_runtime": 6.1069,
+      "eval_samples_per_second": 268.058,
+      "eval_steps_per_second": 16.866,
       "step": 500
     },
     {
-      "epoch": 1.2454212454212454,
-      "grad_norm": 3.4228224754333496,
+      "epoch": 1.2442002442002442,
+      "grad_norm": 25.83207893371582,
       "learning_rate": 1.9724896836313617e-05,
-      "loss": 0.185,
+      "loss": 0.461,
       "step": 510
     },
     {
-      "epoch": 1.2698412698412698,
-      "grad_norm": 7.5374298095703125,
+      "epoch": 1.2686202686202686,
+      "grad_norm": 33.92952346801758,
       "learning_rate": 1.9449793672627236e-05,
-      "loss": 0.2113,
+      "loss": 0.4965,
       "step": 520
     },
     {
-      "epoch": 1.2942612942612943,
-      "grad_norm": 24.314939498901367,
+      "epoch": 1.293040293040293,
+      "grad_norm": 82.4642105102539,
       "learning_rate": 1.9174690508940855e-05,
-      "loss": 0.2134,
+      "loss": 0.5272,
       "step": 530
     },
     {
-      "epoch": 1.3186813186813187,
-      "grad_norm": 13.505054473876953,
+      "epoch": 1.3174603174603174,
+      "grad_norm": 15.041220664978027,
       "learning_rate": 1.889958734525447e-05,
-      "loss": 0.2561,
+      "loss": 0.5795,
       "step": 540
     },
     {
-      "epoch": 1.3431013431013432,
-      "grad_norm": 23.86240577697754,
+      "epoch": 1.341880341880342,
+      "grad_norm": 51.05344009399414,
       "learning_rate": 1.862448418156809e-05,
-      "loss": 0.1341,
+      "loss": 0.3848,
       "step": 550
     },
     {
-      "epoch": 1.3675213675213675,
-      "grad_norm": 16.486339569091797,
+      "epoch": 1.3663003663003663,
+      "grad_norm": 363.78424072265625,
       "learning_rate": 1.8349381017881708e-05,
-      "loss": 0.2968,
+      "loss": 0.5898,
       "step": 560
     },
     {
-      "epoch": 1.3919413919413919,
-      "grad_norm": 24.227453231811523,
+      "epoch": 1.3907203907203907,
+      "grad_norm": 118.15901947021484,
       "learning_rate": 1.8074277854195327e-05,
-      "loss": 0.2631,
+      "loss": 0.4777,
       "step": 570
     },
     {
-      "epoch": 1.4163614163614164,
-      "grad_norm": 11.713160514831543,
+      "epoch": 1.4151404151404152,
+      "grad_norm": 20.32166862487793,
       "learning_rate": 1.7799174690508942e-05,
-      "loss": 0.3079,
+      "loss": 0.4722,
       "step": 580
     },
     {
-      "epoch": 1.4407814407814408,
-      "grad_norm": 18.98057746887207,
+      "epoch": 1.4395604395604396,
+      "grad_norm": 12.633702278137207,
       "learning_rate": 1.7524071526822558e-05,
-      "loss": 0.1686,
+      "loss": 0.3581,
       "step": 590
     },
     {
-      "epoch": 1.4652014652014653,
-      "grad_norm": 22.216732025146484,
+      "epoch": 1.463980463980464,
+      "grad_norm": 29.648452758789062,
       "learning_rate": 1.7248968363136177e-05,
-      "loss": 0.2011,
+      "loss": 0.3433,
       "step": 600
     },
     {
-      "epoch": 1.4652014652014653,
-      "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,
+      "epoch": 1.463980463980464,
+      "eval_accuracy": 0.9150885766646304,
+      "eval_accuracy_label_negative": 0.8901515151515151,
+      "eval_accuracy_label_positive": 0.9384615384615385,
+      "eval_f1": 0.9149907006403145,
+      "eval_loss": 0.25520163774490356,
+      "eval_precision": 0.91573365916924,
+      "eval_recall": 0.9150885766646304,
+      "eval_runtime": 6.0849,
+      "eval_samples_per_second": 269.025,
+      "eval_steps_per_second": 16.927,
       "step": 600
     },
     {
-      "epoch": 1.4896214896214897,
-      "grad_norm": 5.728968620300293,
+      "epoch": 1.4884004884004884,
+      "grad_norm": 48.567466735839844,
       "learning_rate": 1.6973865199449796e-05,
-      "loss": 0.2781,
+      "loss": 0.3987,
       "step": 610
     },
     {
-      "epoch": 1.514041514041514,
-      "grad_norm": 7.4687724113464355,
+      "epoch": 1.5128205128205128,
+      "grad_norm": 17.67637825012207,
       "learning_rate": 1.669876203576341e-05,
-      "loss": 0.2233,
+      "loss": 0.4218,
       "step": 620
     },
     {
-      "epoch": 1.5384615384615383,
-      "grad_norm": 18.378847122192383,
+      "epoch": 1.537240537240537,
+      "grad_norm": 40.53282928466797,
       "learning_rate": 1.642365887207703e-05,
-      "loss": 0.2147,
+      "loss": 0.386,
       "step": 630
     },
     {
-      "epoch": 1.5628815628815629,
-      "grad_norm": 18.625051498413086,
+      "epoch": 1.5616605616605617,
+      "grad_norm": 116.74990844726562,
       "learning_rate": 1.614855570839065e-05,
-      "loss": 0.196,
+      "loss": 0.4431,
       "step": 640
     },
     {
-      "epoch": 1.5873015873015874,
-      "grad_norm": 19.89263343811035,
+      "epoch": 1.5860805860805862,
+      "grad_norm": 20.529993057250977,
       "learning_rate": 1.5873452544704268e-05,
-      "loss": 0.1782,
+      "loss": 0.4856,
       "step": 650
     },
     {
-      "epoch": 1.6117216117216118,
-      "grad_norm": 46.03261184692383,
+      "epoch": 1.6105006105006106,
+      "grad_norm": 16.94083595275879,
       "learning_rate": 1.5598349381017883e-05,
-      "loss": 0.1666,
+      "loss": 0.2793,
       "step": 660
     },
     {
-      "epoch": 1.636141636141636,
-      "grad_norm": 18.096025466918945,
+      "epoch": 1.6349206349206349,
+      "grad_norm": 43.13039779663086,
       "learning_rate": 1.53232462173315e-05,
-      "loss": 0.1648,
+      "loss": 0.338,
       "step": 670
     },
     {
-      "epoch": 1.6605616605616604,
-      "grad_norm": 23.694866180419922,
+      "epoch": 1.6593406593406592,
+      "grad_norm": 56.50369644165039,
       "learning_rate": 1.5048143053645119e-05,
-      "loss": 0.2266,
+      "loss": 0.4709,
       "step": 680
     },
     {
-      "epoch": 1.684981684981685,
-      "grad_norm": 19.052383422851562,
+      "epoch": 1.6837606837606838,
+      "grad_norm": 13.253159523010254,
       "learning_rate": 1.4773039889958736e-05,
-      "loss": 0.2008,
+      "loss": 0.3916,
       "step": 690
     },
     {
-      "epoch": 1.7094017094017095,
-      "grad_norm": 16.585542678833008,
+      "epoch": 1.7081807081807083,
+      "grad_norm": 25.500383377075195,
       "learning_rate": 1.4497936726272352e-05,
-      "loss": 0.2179,
+      "loss": 0.5589,
       "step": 700
     },
     {
-      "epoch": 1.7094017094017095,
-      "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,
+      "epoch": 1.7081807081807083,
+      "eval_accuracy": 0.9132559560171044,
+      "eval_accuracy_label_negative": 0.8813131313131313,
+      "eval_accuracy_label_positive": 0.9431952662721893,
+      "eval_f1": 0.9131080020430126,
+      "eval_loss": 0.20865951478481293,
+      "eval_precision": 0.9144124548952469,
+      "eval_recall": 0.9132559560171044,
+      "eval_runtime": 6.1693,
+      "eval_samples_per_second": 265.344,
+      "eval_steps_per_second": 16.695,
       "step": 700
     },
     {
-      "epoch": 1.7338217338217339,
-      "grad_norm": 16.8792667388916,
+      "epoch": 1.7326007326007327,
+      "grad_norm": 26.2749080657959,
       "learning_rate": 1.4222833562585972e-05,
-      "loss": 0.1802,
+      "loss": 0.3424,
       "step": 710
     },
     {
-      "epoch": 1.7582417582417582,
-      "grad_norm": 10.43722915649414,
+      "epoch": 1.757020757020757,
+      "grad_norm": 24.71459197998047,
       "learning_rate": 1.3947730398899588e-05,
-      "loss": 0.1609,
+      "loss": 0.3582,
       "step": 720
     },
     {
-      "epoch": 1.7826617826617825,
-      "grad_norm": 15.472962379455566,
+      "epoch": 1.7814407814407813,
+      "grad_norm": 16.336734771728516,
       "learning_rate": 1.3672627235213205e-05,
-      "loss": 0.1702,
+      "loss": 0.3334,
       "step": 730
     },
     {
-      "epoch": 1.807081807081807,
-      "grad_norm": 3.905959367752075,
+      "epoch": 1.8058608058608059,
+      "grad_norm": 11.974506378173828,
       "learning_rate": 1.3397524071526824e-05,
-      "loss": 0.184,
+      "loss": 0.3375,
       "step": 740
     },
     {
-      "epoch": 1.8315018315018317,
-      "grad_norm": 4.598665237426758,
+      "epoch": 1.8302808302808304,
+      "grad_norm": 35.09166717529297,
       "learning_rate": 1.3122420907840441e-05,
-      "loss": 0.1866,
+      "loss": 0.4735,
       "step": 750
     },
     {
-      "epoch": 1.855921855921856,
-      "grad_norm": 25.891942977905273,
+      "epoch": 1.8547008547008548,
+      "grad_norm": 23.616647720336914,
       "learning_rate": 1.284731774415406e-05,
-      "loss": 0.16,
+      "loss": 0.3001,
       "step": 760
     },
     {
-      "epoch": 1.8803418803418803,
-      "grad_norm": 24.572216033935547,
+      "epoch": 1.879120879120879,
+      "grad_norm": 31.474788665771484,
       "learning_rate": 1.2572214580467677e-05,
-      "loss": 0.1498,
+      "loss": 0.2949,
       "step": 770
     },
     {
-      "epoch": 1.9047619047619047,
-      "grad_norm": 21.231639862060547,
+      "epoch": 1.9035409035409034,
+      "grad_norm": 41.20528793334961,
       "learning_rate": 1.2297111416781292e-05,
-      "loss": 0.1992,
+      "loss": 0.5207,
       "step": 780
     },
     {
-      "epoch": 1.9291819291819292,
-      "grad_norm": 11.721719741821289,
+      "epoch": 1.927960927960928,
+      "grad_norm": 12.699962615966797,
       "learning_rate": 1.2022008253094913e-05,
-      "loss": 0.2038,
+      "loss": 0.4461,
       "step": 790
     },
     {
-      "epoch": 1.9536019536019538,
-      "grad_norm": 27.692150115966797,
+      "epoch": 1.9523809523809523,
+      "grad_norm": 23.412885665893555,
       "learning_rate": 1.1746905089408529e-05,
-      "loss": 0.1465,
+      "loss": 0.2343,
       "step": 800
     },
     {
-      "epoch": 1.9536019536019538,
-      "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,
+      "epoch": 1.9523809523809523,
+      "eval_accuracy": 0.918142944410507,
+      "eval_accuracy_label_negative": 0.8939393939393939,
+      "eval_accuracy_label_positive": 0.9408284023668639,
+      "eval_f1": 0.9180523324913266,
+      "eval_loss": 0.21100710332393646,
+      "eval_precision": 0.918757729196307,
+      "eval_recall": 0.918142944410507,
+      "eval_runtime": 6.1463,
+      "eval_samples_per_second": 266.338,
+      "eval_steps_per_second": 16.758,
       "step": 800
     },
     {
-      "epoch": 1.978021978021978,
-      "grad_norm": 16.974834442138672,
+      "epoch": 1.9768009768009769,
+      "grad_norm": 23.129348754882812,
       "learning_rate": 1.1471801925722146e-05,
-      "loss": 0.2372,
+      "loss": 0.402,
       "step": 810
     },
     {
-      "epoch": 2.0024420024420024,
-      "grad_norm": 11.423258781433105,
+      "epoch": 2.0,
+      "grad_norm": 82.90428161621094,
       "learning_rate": 1.1196698762035765e-05,
-      "loss": 0.1668,
+      "loss": 0.3556,
       "step": 820
     },
     {
-      "epoch": 2.0268620268620268,
-      "grad_norm": 4.174540996551514,
+      "epoch": 2.0244200244200243,
+      "grad_norm": 28.78835678100586,
       "learning_rate": 1.0921595598349382e-05,
-      "loss": 0.1013,
+      "loss": 0.2684,
       "step": 830
     },
     {
-      "epoch": 2.051282051282051,
-      "grad_norm": 15.53784465789795,
+      "epoch": 2.0488400488400487,
+      "grad_norm": 7.678134918212891,
       "learning_rate": 1.0646492434663e-05,
-      "loss": 0.1242,
+      "loss": 0.2465,
       "step": 840
     },
     {
-      "epoch": 2.075702075702076,
-      "grad_norm": 17.660886764526367,
+      "epoch": 2.0732600732600734,
+      "grad_norm": 10.281868934631348,
       "learning_rate": 1.0371389270976618e-05,
-      "loss": 0.1352,
+      "loss": 0.2608,
       "step": 850
     },
     {
-      "epoch": 2.1001221001221,
-      "grad_norm": 21.627826690673828,
+      "epoch": 2.0976800976800978,
+      "grad_norm": 44.59360122680664,
       "learning_rate": 1.0096286107290235e-05,
-      "loss": 0.1283,
+      "loss": 0.2796,
       "step": 860
     },
     {
-      "epoch": 2.1245421245421245,
-      "grad_norm": 8.318380355834961,
+      "epoch": 2.122100122100122,
+      "grad_norm": 71.7291259765625,
       "learning_rate": 9.821182943603852e-06,
-      "loss": 0.0804,
+      "loss": 0.1796,
       "step": 870
     },
     {
-      "epoch": 2.148962148962149,
-      "grad_norm": 1.088057279586792,
+      "epoch": 2.1465201465201464,
+      "grad_norm": 58.75422668457031,
       "learning_rate": 9.54607977991747e-06,
-      "loss": 0.0708,
+      "loss": 0.2029,
       "step": 880
     },
     {
-      "epoch": 2.173382173382173,
-      "grad_norm": 17.630653381347656,
+      "epoch": 2.1709401709401708,
+      "grad_norm": 24.300424575805664,
       "learning_rate": 9.270976616231088e-06,
-      "loss": 0.162,
+      "loss": 0.4012,
       "step": 890
     },
     {
-      "epoch": 2.197802197802198,
-      "grad_norm": 11.629766464233398,
+      "epoch": 2.1953601953601956,
+      "grad_norm": 17.3212833404541,
       "learning_rate": 8.995873452544705e-06,
-      "loss": 0.1602,
+      "loss": 0.2403,
       "step": 900
     },
     {
-      "epoch": 2.197802197802198,
-      "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,
+      "epoch": 2.1953601953601956,
+      "eval_accuracy": 0.9224190592547342,
+      "eval_accuracy_label_negative": 0.9318181818181818,
+      "eval_accuracy_label_positive": 0.9136094674556213,
+      "eval_f1": 0.9224377694184351,
+      "eval_loss": 0.23138785362243652,
+      "eval_precision": 0.9227050113183035,
+      "eval_recall": 0.9224190592547342,
+      "eval_runtime": 6.1138,
+      "eval_samples_per_second": 267.756,
+      "eval_steps_per_second": 16.847,
       "step": 900
     },
     {
-      "epoch": 2.2222222222222223,
-      "grad_norm": 26.855487823486328,
+      "epoch": 2.21978021978022,
+      "grad_norm": 41.47114944458008,
       "learning_rate": 8.720770288858322e-06,
-      "loss": 0.181,
+      "loss": 0.3843,
       "step": 910
     },
     {
-      "epoch": 2.2466422466422467,
-      "grad_norm": 8.824442863464355,
+      "epoch": 2.244200244200244,
+      "grad_norm": 34.233089447021484,
       "learning_rate": 8.44566712517194e-06,
-      "loss": 0.1423,
+      "loss": 0.2175,
       "step": 920
     },
     {
-      "epoch": 2.271062271062271,
-      "grad_norm": 12.806025505065918,
+      "epoch": 2.2686202686202686,
+      "grad_norm": 63.74410629272461,
       "learning_rate": 8.170563961485558e-06,
-      "loss": 0.1352,
+      "loss": 0.3676,
       "step": 930
     },
     {
-      "epoch": 2.2954822954822953,
-      "grad_norm": 12.534196853637695,
+      "epoch": 2.293040293040293,
+      "grad_norm": 52.46253204345703,
       "learning_rate": 7.895460797799176e-06,
-      "loss": 0.1318,
+      "loss": 0.3562,
       "step": 940
     },
     {
-      "epoch": 2.3199023199023197,
-      "grad_norm": 25.678712844848633,
+      "epoch": 2.317460317460317,
+      "grad_norm": 113.09469604492188,
       "learning_rate": 7.620357634112793e-06,
-      "loss": 0.1166,
+      "loss": 0.2521,
       "step": 950
     },
     {
-      "epoch": 2.3443223443223444,
-      "grad_norm": 12.111174583435059,
+      "epoch": 2.341880341880342,
+      "grad_norm": 49.29931640625,
       "learning_rate": 7.345254470426411e-06,
-      "loss": 0.0941,
+      "loss": 0.1803,
       "step": 960
     },
     {
-      "epoch": 2.3687423687423688,
-      "grad_norm": 1.4796338081359863,
+      "epoch": 2.3663003663003663,
+      "grad_norm": 35.607364654541016,
       "learning_rate": 7.070151306740029e-06,
-      "loss": 0.0864,
+      "loss": 0.1935,
       "step": 970
     },
     {
-      "epoch": 2.393162393162393,
-      "grad_norm": 2.2377712726593018,
+      "epoch": 2.3907203907203907,
+      "grad_norm": 59.298606872558594,
       "learning_rate": 6.795048143053645e-06,
-      "loss": 0.1344,
+      "loss": 0.3756,
       "step": 980
     },
     {
-      "epoch": 2.4175824175824174,
-      "grad_norm": 20.148027420043945,
+      "epoch": 2.415140415140415,
+      "grad_norm": 24.38463592529297,
       "learning_rate": 6.519944979367263e-06,
-      "loss": 0.135,
+      "loss": 0.2457,
       "step": 990
     },
     {
-      "epoch": 2.442002442002442,
-      "grad_norm": 35.98054504394531,
+      "epoch": 2.4395604395604398,
+      "grad_norm": 64.04911041259766,
       "learning_rate": 6.244841815680881e-06,
-      "loss": 0.1293,
+      "loss": 0.2643,
       "step": 1000
     },
     {
-      "epoch": 2.442002442002442,
-      "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,
+      "epoch": 2.4395604395604398,
+      "eval_accuracy": 0.9040928527794746,
+      "eval_accuracy_label_negative": 0.9621212121212122,
+      "eval_accuracy_label_positive": 0.8497041420118343,
+      "eval_f1": 0.9039399934696009,
+      "eval_loss": 0.29960158467292786,
+      "eval_precision": 0.9101812880425119,
+      "eval_recall": 0.9040928527794746,
+      "eval_runtime": 6.1028,
+      "eval_samples_per_second": 268.238,
+      "eval_steps_per_second": 16.878,
       "step": 1000
     },
     {
-      "epoch": 2.4664224664224665,
-      "grad_norm": 5.845112323760986,
+      "epoch": 2.463980463980464,
+      "grad_norm": 11.74494457244873,
       "learning_rate": 5.969738651994499e-06,
-      "loss": 0.1468,
+      "loss": 0.3761,
       "step": 1010
     },
     {
-      "epoch": 2.490842490842491,
-      "grad_norm": 37.39576721191406,
+      "epoch": 2.4884004884004884,
+      "grad_norm": 58.20482635498047,
       "learning_rate": 5.6946354883081155e-06,
-      "loss": 0.0503,
+      "loss": 0.2507,
       "step": 1020
     },
     {
-      "epoch": 2.515262515262515,
-      "grad_norm": 4.044558525085449,
+      "epoch": 2.5128205128205128,
+      "grad_norm": 8.351099967956543,
       "learning_rate": 5.4195323246217335e-06,
-      "loss": 0.0569,
+      "loss": 0.1995,
       "step": 1030
     },
     {
-      "epoch": 2.5396825396825395,
-      "grad_norm": 0.4750860035419464,
+      "epoch": 2.537240537240537,
+      "grad_norm": 52.496883392333984,
       "learning_rate": 5.1444291609353515e-06,
-      "loss": 0.1722,
+      "loss": 0.3185,
       "step": 1040
     },
     {
-      "epoch": 2.564102564102564,
-      "grad_norm": 19.243858337402344,
+      "epoch": 2.5616605616605614,
+      "grad_norm": 15.573514938354492,
       "learning_rate": 4.869325997248969e-06,
-      "loss": 0.1649,
+      "loss": 0.3546,
       "step": 1050
     },
     {
-      "epoch": 2.5885225885225887,
-      "grad_norm": 64.03276062011719,
+      "epoch": 2.586080586080586,
+      "grad_norm": 9.369500160217285,
       "learning_rate": 4.594222833562587e-06,
-      "loss": 0.133,
+      "loss": 0.2971,
       "step": 1060
     },
     {
-      "epoch": 2.612942612942613,
-      "grad_norm": 17.09507179260254,
+      "epoch": 2.6105006105006106,
+      "grad_norm": 15.763602256774902,
       "learning_rate": 4.319119669876204e-06,
-      "loss": 0.1118,
+      "loss": 0.2744,
       "step": 1070
     },
     {
-      "epoch": 2.6373626373626373,
-      "grad_norm": 3.7031028270721436,
+      "epoch": 2.634920634920635,
+      "grad_norm": 43.78425979614258,
       "learning_rate": 4.044016506189822e-06,
-      "loss": 0.1125,
+      "loss": 0.2521,
       "step": 1080
     },
     {
-      "epoch": 2.6617826617826617,
-      "grad_norm": 6.265291213989258,
+      "epoch": 2.659340659340659,
+      "grad_norm": 43.655250549316406,
       "learning_rate": 3.768913342503439e-06,
-      "loss": 0.1255,
+      "loss": 0.3189,
       "step": 1090
     },
     {
-      "epoch": 2.6862026862026864,
-      "grad_norm": 12.135473251342773,
+      "epoch": 2.683760683760684,
+      "grad_norm": 21.811946868896484,
       "learning_rate": 3.4938101788170562e-06,
-      "loss": 0.1023,
+      "loss": 0.1856,
       "step": 1100
     },
     {
-      "epoch": 2.6862026862026864,
-      "eval_accuracy": 0.9236408063530849,
+      "epoch": 2.683760683760684,
+      "eval_accuracy": 0.921808185705559,
       "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,
+      "eval_accuracy_label_positive": 0.9100591715976332,
+      "eval_f1": 0.9218285003622981,
+      "eval_loss": 0.23950175940990448,
+      "eval_precision": 0.922245080437082,
+      "eval_recall": 0.921808185705559,
+      "eval_runtime": 6.1632,
+      "eval_samples_per_second": 265.61,
+      "eval_steps_per_second": 16.712,
       "step": 1100
     },
     {
-      "epoch": 2.7106227106227108,
-      "grad_norm": 27.403955459594727,
+      "epoch": 2.7081807081807083,
+      "grad_norm": 15.966821670532227,
       "learning_rate": 3.2187070151306742e-06,
-      "loss": 0.1475,
+      "loss": 0.2284,
       "step": 1110
     },
     {
-      "epoch": 2.735042735042735,
-      "grad_norm": 11.365577697753906,
+      "epoch": 2.7326007326007327,
+      "grad_norm": 34.287715911865234,
       "learning_rate": 2.943603851444292e-06,
-      "loss": 0.0816,
+      "loss": 0.2117,
       "step": 1120
     },
     {
-      "epoch": 2.7594627594627594,
-      "grad_norm": 6.001681327819824,
+      "epoch": 2.757020757020757,
+      "grad_norm": 45.06178665161133,
       "learning_rate": 2.6685006877579094e-06,
-      "loss": 0.0767,
+      "loss": 0.204,
       "step": 1130
     },
     {
-      "epoch": 2.7838827838827838,
-      "grad_norm": 8.82612133026123,
+      "epoch": 2.7814407814407813,
+      "grad_norm": 50.90498733520508,
       "learning_rate": 2.393397524071527e-06,
-      "loss": 0.1703,
+      "loss": 0.3576,
       "step": 1140
     },
     {
-      "epoch": 2.808302808302808,
-      "grad_norm": 8.14811897277832,
+      "epoch": 2.8058608058608057,
+      "grad_norm": 3.0487897396087646,
       "learning_rate": 2.1182943603851446e-06,
-      "loss": 0.1812,
+      "loss": 0.2927,
       "step": 1150
     },
     {
-      "epoch": 2.832722832722833,
-      "grad_norm": 31.67622947692871,
+      "epoch": 2.8302808302808304,
+      "grad_norm": 35.04338836669922,
       "learning_rate": 1.8431911966987622e-06,
-      "loss": 0.1133,
+      "loss": 0.3385,
       "step": 1160
     },
     {
-      "epoch": 2.857142857142857,
-      "grad_norm": 1.591486930847168,
+      "epoch": 2.8547008547008548,
+      "grad_norm": 2.87778902053833,
       "learning_rate": 1.56808803301238e-06,
-      "loss": 0.1374,
+      "loss": 0.3517,
       "step": 1170
     },
     {
-      "epoch": 2.8815628815628815,
-      "grad_norm": 17.23202133178711,
+      "epoch": 2.879120879120879,
+      "grad_norm": 17.577260971069336,
       "learning_rate": 1.2929848693259976e-06,
-      "loss": 0.0764,
+      "loss": 0.1655,
       "step": 1180
     },
     {
-      "epoch": 2.905982905982906,
-      "grad_norm": 34.02734375,
+      "epoch": 2.9035409035409034,
+      "grad_norm": 5.3439106941223145,
       "learning_rate": 1.017881705639615e-06,
-      "loss": 0.1168,
+      "loss": 0.2477,
       "step": 1190
     },
     {
-      "epoch": 2.9304029304029307,
-      "grad_norm": 22.118793487548828,
+      "epoch": 2.927960927960928,
+      "grad_norm": 56.782222747802734,
       "learning_rate": 7.427785419532325e-07,
-      "loss": 0.1663,
+      "loss": 0.3018,
       "step": 1200
     },
     {
-      "epoch": 2.9304029304029307,
-      "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,
+      "epoch": 2.927960927960928,
+      "eval_accuracy": 0.9260843005497862,
+      "eval_accuracy_label_negative": 0.9242424242424242,
+      "eval_accuracy_label_positive": 0.927810650887574,
+      "eval_f1": 0.9260857363073682,
+      "eval_loss": 0.23755837976932526,
+      "eval_precision": 0.9260878637932374,
+      "eval_recall": 0.9260843005497862,
+      "eval_runtime": 6.1684,
+      "eval_samples_per_second": 265.384,
+      "eval_steps_per_second": 16.698,
       "step": 1200
     },
     {
-      "epoch": 2.954822954822955,
-      "grad_norm": 3.313932180404663,
+      "epoch": 2.9523809523809526,
+      "grad_norm": 31.97544288635254,
       "learning_rate": 4.6767537826685014e-07,
-      "loss": 0.1202,
+      "loss": 0.2681,
       "step": 1210
     },
     {
-      "epoch": 2.9792429792429793,
-      "grad_norm": 0.9627939462661743,
+      "epoch": 2.976800976800977,
+      "grad_norm": 24.56979751586914,
       "learning_rate": 1.925722145804677e-07,
-      "loss": 0.1192,
+      "loss": 0.3463,
       "step": 1220
     },
     {
-      "epoch": 2.9963369963369964,
+      "epoch": 2.993894993894994,
       "step": 1227,
-      "total_flos": 157212915612480.0,
-      "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": 0.9279169211973122,
-      "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,
+      "total_flos": 157098652813440.0,
+      "train_loss": 0.4734744669075603,
+      "train_runtime": 674.8973,
+      "train_samples_per_second": 58.187,
+      "train_steps_per_second": 1.818
+    },
+    {
+      "epoch": 2.993894993894994,
+      "eval_accuracy": 0.9254734270006109,
+      "eval_accuracy_label_negative": 0.9267676767676768,
+      "eval_accuracy_label_positive": 0.9242603550295858,
+      "eval_f1": 0.9254812761220444,
+      "eval_loss": 0.23741039633750916,
+      "eval_precision": 0.9255140033647618,
+      "eval_recall": 0.9254734270006109,
+      "eval_runtime": 6.1438,
+      "eval_samples_per_second": 266.449,
+      "eval_steps_per_second": 16.765,
       "step": 1227
     }
   ],
@@ -1066,12 +1066,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 157212915612480.0,
+  "total_flos": 157098652813440.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc4c8c16d0ab515ce7f7755e76edb90e120058b508e8d35ad4fdb7c19fb946f1
-size 5048
+oid sha256:6329715e4875f017daad987374dcbe11cf4d98f0586fc36cf8b34f500c7c3287
+size 5304