Upload folder using huggingface_hub

checkpoint-best/config.json

@@ -0,0 +1,58 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-best/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1647013c2386c7332d8c5a453a5754b962e2b9cc9cd720ec1a46cbb08e6a0bef
+size 498643560

checkpoint-best/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e604eb30607a1c6c5d699d27147cbe658d3cf8b79ced30952588da1047888a34
+size 997407371

checkpoint-best/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec915f1da89aac770fc5b8b366d141682cb77b5ab2811b579155b37d57965c46
+size 1465

checkpoint-best/training_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852b5aaa668dac28d8536d757d845e00abd76dd2d5bdd6f292138d02ec6d6cf1
+size 2751

checkpoint-best/training_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9b4043f10ccedbf03d590bd8276954de1d91ea42e8c9bc1c67f4a44c9e5899
+size 2751

checkpoint-best/training_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6118d3923e5b9e702e644ed15c24fbf56af57ef4cde4aa3e72366120e2c2d2
+size 2751

checkpoint-best/training_3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b717e2b13511249e0d9a919d4f4e4eb3fa45a4fdd997c2fc748decd9fbf8c4
+size 2751

checkpoint-best/training_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e26c8ea9b59eb56f8b9af8766804aa4842dc17ec6179635e3aeced03881d44
+size 2751

checkpoint-best/training_5.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197569d03b3128dad3b30bbbc5251b60046d04a5f1fcc30afa7a5de14ffd9c61
+size 2751

checkpoint-best/training_6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5eb7da893bffe94fb8e98fc6a106c94e2a5baac88472e9a8315dd432bacf93
+size 2751

checkpoint-best/training_7.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71e40f781d2f2c947ce6ff158849c08411e7018ea47b581858970844b7c8660
+size 2751

checkpoint-best/training_9.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf94d4a6ba91903cb465c55057dc4e1997407ca68ce3b95e3593c50eeac8180
+size 2751

checkpoint-last/config.json

@@ -0,0 +1,58 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-last/idx_file.txt

@@ -0,0 +1 @@
+19

checkpoint-last/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9adac64aeceb4e7543247c7ce2015582e82e848b28ff8bbfa1133b30622368
+size 498643560

checkpoint-last/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4776e5c0161c3d1f0880e2b6db6ef9096e97a67eb08a5fe7d1bc8624bd6e136a
+size 997407371

checkpoint-last/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e76e52367e79e89b041385a265bc5780c9847a9b960325998159f1e57606e9
+size 1465

checkpoint-last/step_file.txt

@@ -0,0 +1 @@
+7320

config.json

@@ -0,0 +1,58 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.txt

@@ -0,0 +1,380 @@
+evaluate 0
+acc = 0.6806366047745358
+acc_and_f1_macro = 0.6333078408252777
+acc_and_f1_weighted = 0.6665327086776933
+class_f1 = [np.float64(nan), np.float64(0.5639913232104121), np.float64(0.7104622871046229), np.float64(0.07100591715976332), np.float64(0.5421903052064633), np.float64(0.5886524822695035), np.float64(0.8875), np.float64(0.83248730964467), np.float64(0.9026315789473686), np.float64(0.7608695652173912)]
+class_p = [np.float64(nan), np.float64(0.5220883534136547), np.float64(0.6636363636363637), np.float64(1.0), np.float64(0.47335423197492166), np.float64(0.5533333333333333), np.float64(0.8875), np.float64(0.7961165048543689), np.float64(0.9245283018867925), np.float64(0.6481481481481481)]
+class_r = [np.float64(0.0), np.float64(0.6132075471698113), np.float64(0.7643979057591623), np.float64(0.03680981595092025), np.float64(0.634453781512605), np.float64(0.6287878787878788), np.float64(0.8875), np.float64(0.8723404255319149), np.float64(0.8817480719794345), np.float64(0.9210526315789473)]
+confusion_matrix = [[  0   8   0   0  14  20   0   0   0   0]
+ [  0 130  64   0   4  10   0   0   0   4]
+ [  0  37 146   0   6   2   0   0   0   0]
+ [  0  19   6   6  80  49   0   0   0   3]
+ [  0  30   2   0 151  51   0   0   0   4]
+ [  0  24   2   0  64 166   0   0   0   8]
+ [  0   0   0   0   0   0 142   6  12   0]
+ [  0   0   0   0   0   0   8 164  16   0]
+ [  0   0   0   0   0   0  10  36 343   0]
+ [  0   1   0   0   0   2   0   0   0  35]]
+f1_macro = 0.5859790768760196
+f1_weighted = 0.6524288125808508
+evaluate 1
+acc = 0.7310344827586207
+acc_and_f1_macro = 0.697348297855418
+acc_and_f1_weighted = 0.7271787706287073
+class_f1 = [np.float64(nan), np.float64(0.7256637168141593), np.float64(0.7867036011080333), np.float64(0.4977168949771689), np.float64(0.4875346260387812), np.float64(0.6376811594202899), np.float64(0.9240506329113924), np.float64(0.8426395939086295), np.float64(0.9164490861618799), np.float64(0.8181818181818181)]
+class_p = [np.float64(nan), np.float64(0.6833333333333333), np.float64(0.8352941176470589), np.float64(0.39636363636363636), np.float64(0.7154471544715447), np.float64(0.6111111111111112), np.float64(0.9358974358974359), np.float64(0.8058252427184466), np.float64(0.9310344827586207), np.float64(0.72)]
+class_r = [np.float64(0.0), np.float64(0.7735849056603774), np.float64(0.743455497382199), np.float64(0.6687116564417178), np.float64(0.3697478991596639), np.float64(0.6666666666666666), np.float64(0.9125), np.float64(0.8829787234042553), np.float64(0.9023136246786633), np.float64(0.9473684210526315)]
+confusion_matrix = [[  0   4   0  30   0   8   0   0   0   0]
+ [  0 164  16   2   4  26   0   0   0   0]
+ [  0  34 142   4   7   4   0   0   0   0]
+ [  0   9   6 109  16  21   0   0   0   2]
+ [  0  20   4  68  88  52   0   2   0   4]
+ [  0   8   2  62   8 176   0   0   0   8]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   4 166  18   0]
+ [  0   0   0   0   0   0   6  32 351   0]
+ [  0   1   0   0   0   1   0   0   0  36]]
+f1_macro = 0.6636621129522153
+f1_weighted = 0.7233230584987939
+evaluate 2
+acc = 0.7326259946949603
+acc_and_f1_macro = 0.7081346759194237
+acc_and_f1_weighted = 0.7308115745754664
+class_f1 = [np.float64(0.08695652173913042), np.float64(0.6926829268292682), np.float64(0.7713498622589532), np.float64(0.4972972972972972), np.float64(0.5315315315315315), np.float64(0.6519524617996605), np.float64(0.920245398773006), np.float64(0.8571428571428571), np.float64(0.9083557951482479), np.float64(0.918918918918919)]
+class_p = [np.float64(0.5), np.float64(0.7171717171717171), np.float64(0.813953488372093), np.float64(0.4444444444444444), np.float64(0.5728155339805825), np.float64(0.5907692307692308), np.float64(0.9036144578313253), np.float64(0.7981651376146789), np.float64(0.9546742209631728), np.float64(0.9444444444444444)]
+class_r = [np.float64(0.047619047619047616), np.float64(0.6698113207547169), np.float64(0.7329842931937173), np.float64(0.5644171779141104), np.float64(0.4957983193277311), np.float64(0.7272727272727273), np.float64(0.9375), np.float64(0.925531914893617), np.float64(0.8663239074550129), np.float64(0.8947368421052632)]
+confusion_matrix = [[  2   4   0  22   0  14   0   0   0   0]
+ [  0 142  20   4  14  32   0   0   0   0]
+ [  0  26 140   6  11   8   0   0   0   0]
+ [  0   6   6  92  32  27   0   0   0   0]
+ [  2  14   4  49 118  49   0   0   0   2]
+ [  0   6   2  34  30 192   0   0   0   0]
+ [  0   0   0   0   0   0 150   2   8   0]
+ [  0   0   0   0   0   0   6 174   8   0]
+ [  0   0   0   0   0   0  10  42 337   0]
+ [  0   0   0   0   1   3   0   0   0  34]]
+f1_macro = 0.6836433571438871
+f1_weighted = 0.7289971544559726
+evaluate 3
+acc = 0.7336870026525198
+acc_and_f1_macro = 0.7121637477914753
+acc_and_f1_weighted = 0.7307644212152906
+class_f1 = [np.float64(0.25396825396825395), np.float64(0.7017543859649122), np.float64(0.7977207977207976), np.float64(0.4697986577181208), np.float64(0.5409090909090909), np.float64(0.6599999999999999), np.float64(0.9182389937106918), np.float64(0.7987987987987988), np.float64(0.9015795868772782), np.float64(0.8636363636363636)]
+class_p = [np.float64(0.38095238095238093), np.float64(0.6557377049180327), np.float64(0.875), np.float64(0.5185185185185185), np.float64(0.5891089108910891), np.float64(0.5892857142857143), np.float64(0.9240506329113924), np.float64(0.9172413793103448), np.float64(0.8548387096774194), np.float64(0.76)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7547169811320755), np.float64(0.7329842931937173), np.float64(0.4294478527607362), np.float64(0.5), np.float64(0.75), np.float64(0.9125), np.float64(0.7074468085106383), np.float64(0.9537275064267352), np.float64(1.0)]
+confusion_matrix = [[  8   4   0   8   4  18   0   0   0   0]
+ [  2 160  10   0  12  28   0   0   0   0]
+ [  0  38 140   0   5   6   0   0   0   2]
+ [  7  10   6  70  36  34   0   0   0   0]
+ [  2  24   2  35 119  52   0   0   0   4]
+ [  2   8   2  22  26 198   0   0   0   6]
+ [  0   0   0   0   0   0 146   2  12   0]
+ [  0   0   0   0   0   0   4 133  51   0]
+ [  0   0   0   0   0   0   8  10 371   0]
+ [  0   0   0   0   0   0   0   0   0  38]]
+f1_macro = 0.6906404929304307
+f1_weighted = 0.7278418397780613
+evaluate 4
+acc = 0.7347480106100795
+acc_and_f1_macro = 0.7102660878593708
+acc_and_f1_weighted = 0.7308570794214094
+class_f1 = [np.float64(0.21428571428571427), np.float64(0.6879271070615034), np.float64(0.7570332480818416), np.float64(0.44280442804428044), np.float64(0.5466377440347071), np.float64(0.6610455311973019), np.float64(0.9240506329113924), np.float64(0.8404255319148938), np.float64(0.9130434782608695), np.float64(0.8705882352941177)]
+class_p = [np.float64(0.42857142857142855), np.float64(0.6651982378854625), np.float64(0.74), np.float64(0.5555555555555556), np.float64(0.5650224215246636), np.float64(0.5957446808510638), np.float64(0.9358974358974359), np.float64(0.8404255319148937), np.float64(0.9083969465648855), np.float64(0.7872340425531915)]
+class_r = [np.float64(0.14285714285714285), np.float64(0.7122641509433962), np.float64(0.774869109947644), np.float64(0.36809815950920244), np.float64(0.5294117647058824), np.float64(0.7424242424242424), np.float64(0.9125), np.float64(0.8404255319148937), np.float64(0.9177377892030848), np.float64(0.9736842105263158)]
+confusion_matrix = [[  6   3   1  10   2  20   0   0   0   0]
+ [  0 151  31   0  10  20   0   0   0   0]
+ [  0  30 148   0   9   2   0   0   0   2]
+ [  2  10   8  60  46  37   0   0   0   0]
+ [  4  26   6  18 126  54   0   0   0   4]
+ [  2   6   6  20  30 196   0   0   0   4]
+ [  0   0   0   0   0   0 146   4  10   0]
+ [  0   0   0   0   0   0   4 158  26   0]
+ [  0   0   0   0   0   0   6  26 357   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6857841651086621
+f1_weighted = 0.7269661482327393
+evaluate 5
+acc = 0.7389920424403184
+acc_and_f1_macro = 0.7199796152721372
+acc_and_f1_weighted = 0.7370592832918494
+class_f1 = [np.float64(0.3174603174603175), np.float64(0.7111111111111111), np.float64(0.8), np.float64(0.4794520547945205), np.float64(0.5632653061224491), np.float64(0.6446886446886447), np.float64(0.9171974522292993), np.float64(0.8268156424581007), np.float64(0.9052369077306732), np.float64(0.8444444444444443)]
+class_p = [np.float64(0.47619047619047616), np.float64(0.6722689075630253), np.float64(0.8390804597701149), np.float64(0.5426356589147286), np.float64(0.5476190476190477), np.float64(0.624113475177305), np.float64(0.935064935064935), np.float64(0.8705882352941177), np.float64(0.8789346246973365), np.float64(0.7307692307692307)]
+class_r = [np.float64(0.23809523809523808), np.float64(0.7547169811320755), np.float64(0.7643979057591623), np.float64(0.4294478527607362), np.float64(0.5798319327731093), np.float64(0.6666666666666666), np.float64(0.9), np.float64(0.7872340425531915), np.float64(0.9331619537275064), np.float64(1.0)]
+confusion_matrix = [[ 10   4   0  12   2  14   0   0   0   0]
+ [  2 160  14   0  12  22   0   0   0   2]
+ [  0  32 146   0   9   2   0   0   0   2]
+ [  3  12   6  70  47  25   0   0   0   0]
+ [  6  22   4  21 138  43   0   0   0   4]
+ [  0   8   4  26  44 176   0   0   0   6]
+ [  0   0   0   0   0   0 144   2  14   0]
+ [  0   0   0   0   0   0   4 148  36   0]
+ [  0   0   0   0   0   0   6  20 363   0]
+ [  0   0   0   0   0   0   0   0   0  38]]
+f1_macro = 0.700967188103956
+f1_weighted = 0.7351265241433806
+evaluate 6
+acc = 0.7405835543766578
+acc_and_f1_macro = 0.7229261910246172
+acc_and_f1_weighted = 0.7388530712580481
+class_f1 = [np.float64(0.35714285714285715), np.float64(0.7216035634743876), np.float64(0.7872340425531915), np.float64(0.5), np.float64(0.5347368421052632), np.float64(0.6429906542056075), np.float64(0.9240506329113924), np.float64(0.8404255319148938), np.float64(0.9130434782608695), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.7142857142857143), np.float64(0.6835443037974683), np.float64(0.8), np.float64(0.5163398692810458), np.float64(0.5358649789029536), np.float64(0.6346863468634686), np.float64(0.9358974358974359), np.float64(0.8404255319148937), np.float64(0.9083969465648855), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.23809523809523808), np.float64(0.7641509433962265), np.float64(0.774869109947644), np.float64(0.48466257668711654), np.float64(0.5336134453781513), np.float64(0.6515151515151515), np.float64(0.9125), np.float64(0.8404255319148937), np.float64(0.9177377892030848), np.float64(0.9736842105263158)]
+confusion_matrix = [[ 10   3   1  12   0  16   0   0   0   0]
+ [  0 162  18   0  12  18   0   0   0   2]
+ [  0  30 148   0   9   2   0   0   0   2]
+ [  0  11   8  79  45  20   0   0   0   0]
+ [  4  24   4  32 127  43   0   0   0   4]
+ [  0   6   6  30  44 172   0   0   0   6]
+ [  0   0   0   0   0   0 146   4  10   0]
+ [  0   0   0   0   0   0   4 158  26   0]
+ [  0   0   0   0   0   0   6  26 357   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.7052688276725765
+f1_weighted = 0.7371225881394384
+evaluate 7
+acc = 0.7416445623342175
+acc_and_f1_macro = 0.7243061135649642
+acc_and_f1_weighted = 0.7398550905547492
+class_f1 = [np.float64(0.37037037037037035), np.float64(0.7142857142857143), np.float64(0.7893333333333332), np.float64(0.5015873015873016), np.float64(0.5366876310272536), np.float64(0.6394052044609665), np.float64(0.920245398773006), np.float64(0.8493150684931507), np.float64(0.9169859514687101), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8333333333333334), np.float64(0.6779661016949152), np.float64(0.8043478260869565), np.float64(0.5197368421052632), np.float64(0.5355648535564853), np.float64(0.6277372262773723), np.float64(0.9036144578313253), np.float64(0.8757062146892656), np.float64(0.9111675126903553), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.23809523809523808), np.float64(0.7547169811320755), np.float64(0.774869109947644), np.float64(0.48466257668711654), np.float64(0.5378151260504201), np.float64(0.6515151515151515), np.float64(0.9375), np.float64(0.824468085106383), np.float64(0.922879177377892), np.float64(0.9736842105263158)]
+confusion_matrix = [[ 10   4   0  11   1  16   0   0   0   0]
+ [  0 160  18   0  12  20   0   0   0   2]
+ [  0  30 148   0   9   2   0   0   0   2]
+ [  0  11   8  79  45  20   0   0   0   0]
+ [  2  24   4  32 128  44   0   0   0   4]
+ [  0   6   6  30  44 172   0   0   0   6]
+ [  0   0   0   0   0   0 150   2   8   0]
+ [  0   0   0   0   0   0   6 155  27   0]
+ [  0   0   0   0   0   0  10  20 359   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.706967664795711
+f1_weighted = 0.7380656187752809
+evaluate 8
+acc = 0.7389920424403184
+acc_and_f1_macro = 0.7191612753022021
+acc_and_f1_weighted = 0.7371708026775668
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7142857142857143), np.float64(0.7851458885941645), np.float64(0.48543689320388356), np.float64(0.5327868852459017), np.float64(0.6303939962476547), np.float64(0.9182389937106918), np.float64(0.8682926829268293), np.float64(0.9195710455764076), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8), np.float64(0.6779661016949152), np.float64(0.7956989247311828), np.float64(0.5136986301369864), np.float64(0.52), np.float64(0.6245353159851301), np.float64(0.9240506329113924), np.float64(0.8018018018018018), np.float64(0.9607843137254902), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7547169811320755), np.float64(0.774869109947644), np.float64(0.4601226993865031), np.float64(0.5462184873949579), np.float64(0.6363636363636364), np.float64(0.9125), np.float64(0.9468085106382979), np.float64(0.8817480719794345), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   4   0  11   1  18   0   0   0   0]
+ [  0 160  20   0  12  18   0   0   0   2]
+ [  0  30 148   0   9   2   0   0   0   2]
+ [  0  11   8  75  50  19   0   0   0   0]
+ [  2  24   4  30 130  44   0   0   0   4]
+ [  0   6   6  30  48 168   0   0   0   6]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   4 178   6   0]
+ [  0   0   0   0   0   0   8  38 343   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6993305081640858
+f1_weighted = 0.7353495629148153
+evaluate 9
+acc = 0.7469496021220159
+acc_and_f1_macro = 0.7279048663503407
+acc_and_f1_weighted = 0.7449777723566162
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7207207207207208), np.float64(0.7830687830687831), np.float64(0.5236593059936907), np.float64(0.5481171548117155), np.float64(0.6420664206642066), np.float64(0.9068322981366459), np.float64(0.8602150537634409), np.float64(0.9256410256410256), np.float64(0.8705882352941177)]
+class_p = [np.float64(0.8), np.float64(0.6896551724137931), np.float64(0.7914438502673797), np.float64(0.538961038961039), np.float64(0.5458333333333333), np.float64(0.6258992805755396), np.float64(0.9012345679012346), np.float64(0.8695652173913043), np.float64(0.9232736572890026), np.float64(0.7872340425531915)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7547169811320755), np.float64(0.774869109947644), np.float64(0.50920245398773), np.float64(0.5504201680672269), np.float64(0.6590909090909091), np.float64(0.9125), np.float64(0.851063829787234), np.float64(0.9280205655526992), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  11   3  16   0   0   0   0]
+ [  0 160  18   2  10  22   0   0   0   0]
+ [  0  30 148   0   9   2   0   0   0   2]
+ [  0  11   8  83  41  20   0   0   0   0]
+ [  2  21   6  30 131  44   0   0   0   4]
+ [  0   6   6  28  46 174   0   0   0   4]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   6 160  22   0]
+ [  0   0   0   0   0   0  10  18 361   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.7088601305786655
+f1_weighted = 0.7430059425912167
+evaluate 10
+acc = 0.7442970822281167
+acc_and_f1_macro = 0.7248709434383627
+acc_and_f1_weighted = 0.742373022464857
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7174887892376682), np.float64(0.7789473684210527), np.float64(0.5142857142857143), np.float64(0.5416666666666666), np.float64(0.6268656716417911), np.float64(0.9182389937106918), np.float64(0.8717948717948718), np.float64(0.926892950391645), np.float64(0.8505747126436782)]
+class_p = [np.float64(0.8), np.float64(0.6837606837606838), np.float64(0.783068783068783), np.float64(0.5328947368421053), np.float64(0.5371900826446281), np.float64(0.6176470588235294), np.float64(0.9240506329113924), np.float64(0.8415841584158416), np.float64(0.9416445623342176), np.float64(0.7551020408163265)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7547169811320755), np.float64(0.774869109947644), np.float64(0.49693251533742333), np.float64(0.5462184873949579), np.float64(0.6363636363636364), np.float64(0.9125), np.float64(0.9042553191489362), np.float64(0.9125964010282777), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  11   1  18   0   0   0   0]
+ [  0 160  20   0  12  20   0   0   0   0]
+ [  0  31 148   0   8   2   0   0   0   2]
+ [  0  11   8  81  43  20   0   0   0   0]
+ [  2  22   6  30 130  44   0   0   0   4]
+ [  0   6   6  30  48 168   0   0   0   6]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   4 170  14   0]
+ [  0   0   0   0   0   0   8  26 355   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.7054448046486087
+f1_weighted = 0.7404489627015973
+evaluate 11
+acc = 0.7395225464190981
+acc_and_f1_macro = 0.7198168000805315
+acc_and_f1_weighted = 0.737551448876673
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7117117117117115), np.float64(0.7830687830687831), np.float64(0.5123456790123456), np.float64(0.5285412262156448), np.float64(0.6268656716417911), np.float64(0.9240506329113924), np.float64(0.8540540540540541), np.float64(0.9213197969543147), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8), np.float64(0.6810344827586207), np.float64(0.7914438502673797), np.float64(0.515527950310559), np.float64(0.5319148936170213), np.float64(0.6176470588235294), np.float64(0.9358974358974359), np.float64(0.8681318681318682), np.float64(0.9097744360902256), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7452830188679245), np.float64(0.774869109947644), np.float64(0.50920245398773), np.float64(0.5252100840336135), np.float64(0.6363636363636364), np.float64(0.9125), np.float64(0.8404255319148937), np.float64(0.9331619537275064), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  11   1  18   0   0   0   0]
+ [  0 158  18   2  12  20   0   0   0   2]
+ [  0  31 148   0   8   2   0   0   0   2]
+ [  0  11   8  83  41  20   0   0   0   0]
+ [  2  22   6  35 125  44   0   0   0   4]
+ [  0   6   6  30  48 168   0   0   0   6]
+ [  0   0   0   0   0   0 146   4  10   0]
+ [  0   0   0   0   0   0   4 158  26   0]
+ [  0   0   0   0   0   0   6  20 363   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.7001110537419649
+f1_weighted = 0.7355803513342478
+evaluate 12
+acc = 0.7416445623342175
+acc_and_f1_macro = 0.7216230940717716
+acc_and_f1_weighted = 0.739763631216562
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7117117117117115), np.float64(0.7830687830687831), np.float64(0.50920245398773), np.float64(0.5307855626326965), np.float64(0.6268656716417911), np.float64(0.9240506329113924), np.float64(0.8631578947368421), np.float64(0.9280205655526992), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8), np.float64(0.6810344827586207), np.float64(0.7914438502673797), np.float64(0.50920245398773), np.float64(0.5364806866952789), np.float64(0.6176470588235294), np.float64(0.9358974358974359), np.float64(0.8541666666666666), np.float64(0.9280205655526992), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7452830188679245), np.float64(0.774869109947644), np.float64(0.50920245398773), np.float64(0.5252100840336135), np.float64(0.6363636363636364), np.float64(0.9125), np.float64(0.8723404255319149), np.float64(0.9280205655526992), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  11   1  18   0   0   0   0]
+ [  0 158  18   2  12  20   0   0   0   2]
+ [  0  31 148   0   8   2   0   0   0   2]
+ [  0  11   8  83  41  20   0   0   0   0]
+ [  2  22   6  35 125  44   0   0   0   4]
+ [  0   6   6  32  46 168   0   0   0   6]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   4 164  20   0]
+ [  0   0   0   0   0   0   6  22 361   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.7016016258093256
+f1_weighted = 0.7378827000989064
+evaluate 13
+acc = 0.736870026525199
+acc_and_f1_macro = 0.7170271441233107
+acc_and_f1_weighted = 0.7346839338236678
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7174887892376682), np.float64(0.7830687830687831), np.float64(0.49535603715170273), np.float64(0.5341880341880341), np.float64(0.6222222222222223), np.float64(0.9192546583850932), np.float64(0.8444444444444444), np.float64(0.9166666666666666), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8), np.float64(0.6837606837606838), np.float64(0.7914438502673797), np.float64(0.5), np.float64(0.5434782608695652), np.float64(0.6086956521739131), np.float64(0.9135802469135802), np.float64(0.8837209302325582), np.float64(0.9007444168734491), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7547169811320755), np.float64(0.774869109947644), np.float64(0.49079754601226994), np.float64(0.5252100840336135), np.float64(0.6363636363636364), np.float64(0.925), np.float64(0.8085106382978723), np.float64(0.9331619537275064), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  11   1  18   0   0   0   0]
+ [  0 160  18   2  10  20   0   0   0   2]
+ [  0  31 148   0   8   2   0   0   0   2]
+ [  0  11   8  80  40  24   0   0   0   0]
+ [  2  22   6  35 125  44   0   0   0   4]
+ [  0   6   6  32  46 168   0   0   0   6]
+ [  0   0   0   0   0   0 148   2  10   0]
+ [  0   0   0   0   0   0   6 152  30   0]
+ [  0   0   0   0   0   0   8  18 363   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6971842617214226
+f1_weighted = 0.7324978411221367
+evaluate 14
+acc = 0.743236074270557
+acc_and_f1_macro = 0.7227979699249428
+acc_and_f1_weighted = 0.7413519729893219
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7117117117117115), np.float64(0.7830687830687831), np.float64(0.49535603715170273), np.float64(0.5296610169491526), np.float64(0.6245353159851301), np.float64(0.9240506329113924), np.float64(0.8808290155440415), np.float64(0.9352331606217616), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8), np.float64(0.6810344827586207), np.float64(0.7914438502673797), np.float64(0.5), np.float64(0.5341880341880342), np.float64(0.6131386861313869), np.float64(0.9358974358974359), np.float64(0.8585858585858586), np.float64(0.9425587467362925), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7452830188679245), np.float64(0.774869109947644), np.float64(0.49079754601226994), np.float64(0.5252100840336135), np.float64(0.6363636363636364), np.float64(0.9125), np.float64(0.9042553191489362), np.float64(0.9280205655526992), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  11   1  18   0   0   0   0]
+ [  0 158  18   2  12  20   0   0   0   2]
+ [  0  31 148   0   8   2   0   0   0   2]
+ [  0  11   8  80  42  22   0   0   0   0]
+ [  2  22   6  35 125  44   0   0   0   4]
+ [  0   6   6  32  46 168   0   0   0   6]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   4 170  14   0]
+ [  0   0   0   0   0   0   6  22 361   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.7023598655793286
+f1_weighted = 0.7394678717080866
+evaluate 15
+acc = 0.7421750663129973
+acc_and_f1_macro = 0.7219960586587495
+acc_and_f1_weighted = 0.7403449399172917
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7085201793721974), np.float64(0.7872340425531915), np.float64(0.4984423676012461), np.float64(0.5263157894736843), np.float64(0.6256983240223464), np.float64(0.9240506329113924), np.float64(0.8762886597938143), np.float64(0.9324675324675324), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8), np.float64(0.6752136752136753), np.float64(0.8), np.float64(0.5063291139240507), np.float64(0.5274261603375527), np.float64(0.6153846153846154), np.float64(0.9358974358974359), np.float64(0.85), np.float64(0.9422572178477691), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7452830188679245), np.float64(0.774869109947644), np.float64(0.49079754601226994), np.float64(0.5252100840336135), np.float64(0.6363636363636364), np.float64(0.9125), np.float64(0.9042553191489362), np.float64(0.922879177377892), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  11   1  18   0   0   0   0]
+ [  0 158  18   2  12  20   0   0   0   2]
+ [  0  31 148   0   8   2   0   0   0   2]
+ [  0  11   8  80  43  21   0   0   0   0]
+ [  2  24   4  35 125  44   0   0   0   4]
+ [  0   6   6  30  48 168   0   0   0   6]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   4 170  14   0]
+ [  0   0   0   0   0   0   6  24 359   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.7018170510045015
+f1_weighted = 0.7385148135215859
+evaluate 16
+acc = 0.7421750663129973
+acc_and_f1_macro = 0.7217316250350408
+acc_and_f1_weighted = 0.74027882239806
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7117117117117115), np.float64(0.7830687830687831), np.float64(0.4890282131661442), np.float64(0.5241090146750523), np.float64(0.6256983240223464), np.float64(0.9240506329113924), np.float64(0.8808290155440415), np.float64(0.9352331606217616), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8), np.float64(0.6810344827586207), np.float64(0.7914438502673797), np.float64(0.5), np.float64(0.5230125523012552), np.float64(0.6153846153846154), np.float64(0.9358974358974359), np.float64(0.8585858585858586), np.float64(0.9425587467362925), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7452830188679245), np.float64(0.774869109947644), np.float64(0.4785276073619632), np.float64(0.5252100840336135), np.float64(0.6363636363636364), np.float64(0.9125), np.float64(0.9042553191489362), np.float64(0.9280205655526992), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  11   1  18   0   0   0   0]
+ [  0 158  18   2  12  20   0   0   0   2]
+ [  0  31 148   0   8   2   0   0   0   2]
+ [  0  11   8  78  45  21   0   0   0   0]
+ [  2  22   6  35 125  44   0   0   0   4]
+ [  0   6   6  30  48 168   0   0   0   6]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   4 170  14   0]
+ [  0   0   0   0   0   0   6  22 361   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.7012881837570843
+f1_weighted = 0.7383825784831226
+evaluate 17
+acc = 0.7358090185676393
+acc_and_f1_macro = 0.7159648280369703
+acc_and_f1_weighted = 0.7338408606007674
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7058823529411764), np.float64(0.7789473684210527), np.float64(0.4890282131661442), np.float64(0.5241090146750523), np.float64(0.6256983240223464), np.float64(0.9240506329113924), np.float64(0.8510638297872339), np.float64(0.9232736572890027), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8), np.float64(0.6782608695652174), np.float64(0.783068783068783), np.float64(0.5), np.float64(0.5230125523012552), np.float64(0.6153846153846154), np.float64(0.9358974358974359), np.float64(0.851063829787234), np.float64(0.9185750636132316), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7358490566037735), np.float64(0.774869109947644), np.float64(0.4785276073619632), np.float64(0.5252100840336135), np.float64(0.6363636363636364), np.float64(0.9125), np.float64(0.851063829787234), np.float64(0.9280205655526992), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  11   1  18   0   0   0   0]
+ [  0 156  20   2  12  20   0   0   0   2]
+ [  0  31 148   0   8   2   0   0   0   2]
+ [  0  11   8  78  45  21   0   0   0   0]
+ [  2  22   6  35 125  44   0   0   0   4]
+ [  0   6   6  30  48 168   0   0   0   6]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   4 160  24   0]
+ [  0   0   0   0   0   0   6  22 361   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6961206375063013
+f1_weighted = 0.7318727026338955
+evaluate 18
+acc = 0.7379310344827587
+acc_and_f1_macro = 0.717841202432659
+acc_and_f1_weighted = 0.7359524731168883
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7117117117117115), np.float64(0.7830687830687831), np.float64(0.4840764331210191), np.float64(0.5269709543568464), np.float64(0.6256983240223464), np.float64(0.9240506329113924), np.float64(0.8571428571428572), np.float64(0.9256410256410256), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8), np.float64(0.6810344827586207), np.float64(0.7914438502673797), np.float64(0.5033112582781457), np.float64(0.5204918032786885), np.float64(0.6153846153846154), np.float64(0.9358974358974359), np.float64(0.8526315789473684), np.float64(0.9232736572890026), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7452830188679245), np.float64(0.774869109947644), np.float64(0.4662576687116564), np.float64(0.5336134453781513), np.float64(0.6363636363636364), np.float64(0.9125), np.float64(0.8617021276595744), np.float64(0.9280205655526992), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  10   2  18   0   0   0   0]
+ [  0 158  18   2  12  20   0   0   0   2]
+ [  0  31 148   0   8   2   0   0   0   2]
+ [  0  11   8  76  47  21   0   0   0   0]
+ [  2  22   6  33 127  44   0   0   0   4]
+ [  0   6   6  30  48 168   0   0   0   6]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   4 162  22   0]
+ [  0   0   0   0   0   0   6  22 361   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6977513703825593
+f1_weighted = 0.733973911751018
+evaluate 19
+acc = 0.7379310344827587
+acc_and_f1_macro = 0.717841202432659
+acc_and_f1_weighted = 0.7359524731168883
+class_f1 = [np.float64(0.3076923076923077), np.float64(0.7117117117117115), np.float64(0.7830687830687831), np.float64(0.4840764331210191), np.float64(0.5269709543568464), np.float64(0.6256983240223464), np.float64(0.9240506329113924), np.float64(0.8571428571428572), np.float64(0.9256410256410256), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.8), np.float64(0.6810344827586207), np.float64(0.7914438502673797), np.float64(0.5033112582781457), np.float64(0.5204918032786885), np.float64(0.6153846153846154), np.float64(0.9358974358974359), np.float64(0.8526315789473684), np.float64(0.9232736572890026), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7452830188679245), np.float64(0.774869109947644), np.float64(0.4662576687116564), np.float64(0.5336134453781513), np.float64(0.6363636363636364), np.float64(0.9125), np.float64(0.8617021276595744), np.float64(0.9280205655526992), np.float64(0.9736842105263158)]
+confusion_matrix = [[  8   3   1  10   2  18   0   0   0   0]
+ [  0 158  18   2  12  20   0   0   0   2]
+ [  0  31 148   0   8   2   0   0   0   2]
+ [  0  11   8  76  47  21   0   0   0   0]
+ [  2  22   6  33 127  44   0   0   0   4]
+ [  0   6   6  30  48 168   0   0   0   6]
+ [  0   0   0   0   0   0 146   6   8   0]
+ [  0   0   0   0   0   0   4 162  22   0]
+ [  0   0   0   0   0   0   6  22 361   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6977513703825593
+f1_weighted = 0.733973911751018

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9adac64aeceb4e7543247c7ce2015582e82e848b28ff8bbfa1133b30622368
+size 498643560

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998ddebc3a2a1ed3c604308c3b1f31b9b27c60e564e6f029b514a8f9c2d6984c
+size 2769