Upload folder using huggingface_hub

checkpoint-best/config.json

@@ -0,0 +1,59 @@
+{
+  "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,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-best/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4e3e38414b5d2c5a596e0ab5c8a5f5acc78ef632ffc14bfcc0df565a52171b
+size 1112235744

checkpoint-best/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29802fbac574a6343d6590c324e85b19359e6021e7e707365fea8af24e09370a
+size 2224591499

checkpoint-best/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d46ebbe86cc296e0659ad6d70cc71025895e9b0ca50bf4d999e099e27ebec81
+size 1465

checkpoint-best/training_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b727449fefeba793fb9580f65c60481a8c179df5700a35433e0a1c57958712
+size 2751

checkpoint-best/training_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6825ff2f41b152453471580a04ec5538eeaf4dd13698bbd4de415e5f8f2d21
+size 2751

checkpoint-best/training_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685e4ad908898fc6dabeb9f80917014c1ceb588a7d791e708b50fda4ab315b81
+size 2751

checkpoint-best/training_3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee72edb116c9d6d1a49c7124a650269090702b2b5d51afab86b2f86b4a94175f
+size 2751

checkpoint-best/training_6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9daa462e2ce2191fc68c3f55ca61ae27f52fddaf0bf225dd7541ba6ab39251a1
+size 2751

checkpoint-last/config.json

@@ -0,0 +1,59 @@
+{
+  "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,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-last/idx_file.txt

@@ -0,0 +1 @@
+9

checkpoint-last/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c17da51ee001d45bde6fa33740a0130fb17c72c4c137b2bc371dab3e1e08f4b
+size 1112235744

checkpoint-last/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a581158cea338dac724a1c78fd8a760b94b7d862818b923520ce9665f1d9ccd8
+size 2224591499

checkpoint-last/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad9d3d814422fc24594f9e6de16e4af7ee16238cef70fe96e25680c409c7157
+size 1465

checkpoint-last/step_file.txt

@@ -0,0 +1 @@
+3660

config.json

@@ -0,0 +1,59 @@
+{
+  "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,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.txt

@@ -0,0 +1,190 @@
+evaluate 0
+acc = 0.553315649867374
+acc_and_f1_macro = 0.5036680015396735
+acc_and_f1_weighted = 0.5436802384152634
+class_f1 = [np.float64(nan), np.float64(0.3319148936170213), np.float64(0.419047619047619), np.float64(0.12972972972972974), np.float64(0.3037383177570093), np.float64(0.483221476510067), np.float64(0.8322147651006713), np.float64(0.7777777777777779), np.float64(0.8772378516624041), np.float64(0.38532110091743127)]
+class_p = [np.float64(nan), np.float64(0.3023255813953488), np.float64(0.532258064516129), np.float64(0.5454545454545454), np.float64(0.34210526315789475), np.float64(0.37422037422037424), np.float64(0.8985507246376812), np.float64(0.7403846153846154), np.float64(0.8727735368956743), np.float64(0.29577464788732394)]
+class_r = [np.float64(0.0), np.float64(0.36792452830188677), np.float64(0.34554973821989526), np.float64(0.0736196319018405), np.float64(0.27310924369747897), np.float64(0.6818181818181818), np.float64(0.775), np.float64(0.8191489361702128), np.float64(0.8817480719794345), np.float64(0.5526315789473685)]
+confusion_matrix = [[  0   4   0   4   4  27   0   0   2   1]
+ [  0  78  44   2  40  42   0   0   0   6]
+ [  0  87  66   0  22  13   0   0   0   3]
+ [  0  14   6  12  27  94   0   0   0  10]
+ [  0  45   2   0  65 108   0   0   0  18]
+ [  0  30   6   4  32 180   0   0   0  12]
+ [  0   0   0   0   0   0 124  18  18   0]
+ [  0   0   0   0   0   0   4 154  30   0]
+ [  0   0   0   0   0   0  10  36 343   0]
+ [  0   0   0   0   0  17   0   0   0  21]]
+f1_macro = 0.45402035321197304
+f1_weighted = 0.5340448269631527
+evaluate 1
+acc = 0.6477453580901856
+acc_and_f1_macro = 0.6109098715451384
+acc_and_f1_weighted = 0.6440256663564747
+class_f1 = [np.float64(nan), np.float64(0.5021645021645021), np.float64(0.7002652519893899), np.float64(0.41775456919060056), np.float64(0.41884816753926707), np.float64(0.5066666666666666), np.float64(0.8834355828220859), np.float64(0.8167539267015708), np.float64(0.8932291666666669), np.float64(0.6016260162601627)]
+class_p = [np.float64(nan), np.float64(0.464), np.float64(0.7096774193548387), np.float64(0.36363636363636365), np.float64(0.5555555555555556), np.float64(0.5095785440613027), np.float64(0.8674698795180723), np.float64(0.8041237113402062), np.float64(0.9050131926121372), np.float64(0.43529411764705883)]
+class_r = [np.float64(0.0), np.float64(0.5471698113207547), np.float64(0.6910994764397905), np.float64(0.49079754601226994), np.float64(0.33613445378151263), np.float64(0.5037878787878788), np.float64(0.9), np.float64(0.8297872340425532), np.float64(0.8817480719794345), np.float64(0.9736842105263158)]
+confusion_matrix = [[  0   6   0  20   3  11   0   0   2   0]
+ [  0 116  42   8  16  26   0   0   0   4]
+ [  0  47 132   2   2   4   0   0   0   4]
+ [  0  13   2  80  31  28   0   0   0   9]
+ [  0  34   4  48  80  58   0   0   0  14]
+ [  0  34   6  62  12 133   0   0   0  17]
+ [  0   0   0   0   0   0 144   8   8   0]
+ [  0   0   0   0   0   0   6 156  26   0]
+ [  0   0   0   0   0   0  16  30 343   0]
+ [  0   0   0   0   0   1   0   0   0  37]]
+f1_macro = 0.5740743850000912
+f1_weighted = 0.6403059746227637
+evaluate 2
+acc = 0.6525198938992043
+acc_and_f1_macro = 0.6231816753120988
+acc_and_f1_weighted = 0.6521421608321463
+class_f1 = [np.float64(nan), np.float64(0.46796657381615603), np.float64(0.6862745098039216), np.float64(0.39316239316239315), np.float64(0.445916114790287), np.float64(0.5543859649122808), np.float64(0.8917197452229298), np.float64(0.835978835978836), np.float64(0.907928388746803), np.float64(0.7551020408163265)]
+class_p = [np.float64(nan), np.float64(0.5714285714285714), np.float64(0.9130434782608695), np.float64(0.3016393442622951), np.float64(0.4697674418604651), np.float64(0.5163398692810458), np.float64(0.9090909090909091), np.float64(0.8315789473684211), np.float64(0.9033078880407125), np.float64(0.6166666666666667)]
+class_r = [np.float64(0.0), np.float64(0.39622641509433965), np.float64(0.5497382198952879), np.float64(0.5644171779141104), np.float64(0.42436974789915966), np.float64(0.5984848484848485), np.float64(0.875), np.float64(0.8404255319148937), np.float64(0.9125964010282777), np.float64(0.9736842105263158)]
+confusion_matrix = [[  0   0   0  26   6  10   0   0   0   0]
+ [  0  84   8  18  44  52   0   0   0   6]
+ [  0  40 105  27  11   8   0   0   0   0]
+ [  0   4   0  92  32  30   0   0   0   5]
+ [  0   8   0  76 101  47   0   0   0   6]
+ [  0  11   2  66  21 158   0   0   0   6]
+ [  0   0   0   0   0   0 140  10  10   0]
+ [  0   0   0   0   0   0   2 158  28   0]
+ [  0   0   0   0   0   0  12  22 355   0]
+ [  0   0   0   0   0   1   0   0   0  37]]
+f1_macro = 0.5938434567249933
+f1_weighted = 0.6517644277650883
+evaluate 3
+acc = 0.6970822281167108
+acc_and_f1_macro = 0.665524574862322
+acc_and_f1_weighted = 0.6927153195289348
+class_f1 = [np.float64(0.0909090909090909), np.float64(0.6120689655172414), np.float64(0.7507002801120448), np.float64(0.390625), np.float64(0.5487603305785124), np.float64(0.5104602510460251), np.float64(0.8944099378881988), np.float64(0.861878453038674), np.float64(0.9189873417721519), np.float64(0.7608695652173912)]
+class_p = [np.float64(1.0), np.float64(0.5634920634920635), np.float64(0.8072289156626506), np.float64(0.5376344086021505), np.float64(0.45231607629427795), np.float64(0.5700934579439252), np.float64(0.8888888888888888), np.float64(0.896551724137931), np.float64(0.9052369077306733), np.float64(0.6481481481481481)]
+class_r = [np.float64(0.047619047619047616), np.float64(0.6698113207547169), np.float64(0.7015706806282722), np.float64(0.3067484662576687), np.float64(0.6974789915966386), np.float64(0.4621212121212121), np.float64(0.9), np.float64(0.8297872340425532), np.float64(0.9331619537275064), np.float64(0.9210526315789473)]
+confusion_matrix = [[  2   1   2  10  14  13   0   0   0   0]
+ [  0 142  14   2  38  16   0   0   0   0]
+ [  0  45 134   2   6   4   0   0   0   0]
+ [  0  12   6  50  67  23   0   0   0   5]
+ [  0  18   4  10 166  34   0   0   0   6]
+ [  0  34   6  18  76 122   0   0   0   8]
+ [  0   0   0   0   0   0 144   6  10   0]
+ [  0   0   0   0   0   0   4 156  28   0]
+ [  0   0   0   0   0   0  14  12 363   0]
+ [  0   0   0   1   0   2   0   0   0  35]]
+f1_macro = 0.633966921607933
+f1_weighted = 0.688348410941159
+evaluate 4
+acc = 0.673209549071618
+acc_and_f1_macro = 0.6450619507162738
+acc_and_f1_weighted = 0.6715050760798013
+class_f1 = [np.float64(0.1791044776119403), np.float64(0.5851528384279476), np.float64(0.7611548556430446), np.float64(0.44880174291939), np.float64(0.46361185983827496), np.float64(0.502283105022831), np.float64(0.8819875776397514), np.float64(0.8255813953488371), np.float64(0.8985148514851486), np.float64(0.6229508196721312)]
+class_p = [np.float64(0.24), np.float64(0.5447154471544715), np.float64(0.7631578947368421), np.float64(0.34797297297297297), np.float64(0.6466165413533834), np.float64(0.632183908045977), np.float64(0.8765432098765432), np.float64(0.9102564102564102), np.float64(0.8663484486873508), np.float64(0.4523809523809524)]
+class_r = [np.float64(0.14285714285714285), np.float64(0.6320754716981132), np.float64(0.7591623036649214), np.float64(0.6319018404907976), np.float64(0.36134453781512604), np.float64(0.4166666666666667), np.float64(0.8875), np.float64(0.7553191489361702), np.float64(0.9331619537275064), np.float64(1.0)]
+confusion_matrix = [[  6   5   0  18   3  10   0   0   0   0]
+ [  4 134  30  10  10  18   0   0   0   6]
+ [  0  36 145   4   2   0   0   0   0   4]
+ [  3  11   7 103  20  14   0   0   0   5]
+ [  8  22   4  80  86  22   0   0   0  16]
+ [  4  38   4  81  12 110   0   0   0  15]
+ [  0   0   0   0   0   0 142   4  14   0]
+ [  0   0   0   0   0   0   4 142  42   0]
+ [  0   0   0   0   0   0  16  10 363   0]
+ [  0   0   0   0   0   0   0   0   0  38]]
+f1_macro = 0.6169143523609297
+f1_weighted = 0.6698006030879845
+evaluate 5
+acc = 0.6923076923076923
+acc_and_f1_macro = 0.6701551641026473
+acc_and_f1_weighted = 0.6913225727110167
+class_f1 = [np.float64(0.2985074626865672), np.float64(0.5936254980079683), np.float64(0.7551622418879056), np.float64(0.45925925925925926), np.float64(0.5292929292929293), np.float64(0.5220729366602688), np.float64(0.8674698795180723), np.float64(0.859504132231405), np.float64(0.9088575096277278), np.float64(0.6862745098039216)]
+class_p = [np.float64(0.4), np.float64(0.5137931034482759), np.float64(0.8648648648648649), np.float64(0.5794392523364486), np.float64(0.5097276264591439), np.float64(0.5291828793774319), np.float64(0.8372093023255814), np.float64(0.8914285714285715), np.float64(0.9076923076923077), np.float64(0.546875)]
+class_r = [np.float64(0.23809523809523808), np.float64(0.7028301886792453), np.float64(0.6701570680628273), np.float64(0.3803680981595092), np.float64(0.5504201680672269), np.float64(0.5151515151515151), np.float64(0.9), np.float64(0.8297872340425532), np.float64(0.910025706940874), np.float64(0.9210526315789473)]
+confusion_matrix = [[ 10   3   0  11   6  12   0   0   0   0]
+ [  0 149  12   4  22  21   0   0   0   4]
+ [  0  51 128   0   6   4   0   0   0   2]
+ [  1  20   2  62  40  33   0   0   0   5]
+ [  4  29   2  14 131  50   0   0   0   8]
+ [ 10  38   4  15  51 136   0   0   0  10]
+ [  0   0   0   0   0   0 144   6  10   0]
+ [  0   0   0   0   0   0   6 156  26   0]
+ [  0   0   0   0   0   0  22  13 354   0]
+ [  0   0   0   1   1   1   0   0   0  35]]
+f1_macro = 0.6480026358976024
+f1_weighted = 0.6903374531143411
+evaluate 6
+acc = 0.6997347480106101
+acc_and_f1_macro = 0.6746040583246593
+acc_and_f1_weighted = 0.6982406833442424
+class_f1 = [np.float64(0.2318840579710145), np.float64(0.6133909287257019), np.float64(0.7774798927613941), np.float64(0.48765432098765427), np.float64(0.5436105476673427), np.float64(0.5356371490280778), np.float64(0.8834355828220859), np.float64(0.8369565217391304), np.float64(0.8999999999999999), np.float64(0.6846846846846847)]
+class_p = [np.float64(0.2962962962962963), np.float64(0.5657370517928287), np.float64(0.7967032967032966), np.float64(0.4906832298136646), np.float64(0.5254901960784314), np.float64(0.6231155778894473), np.float64(0.8674698795180723), np.float64(0.8555555555555555), np.float64(0.8976982097186701), np.float64(0.5205479452054794)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.6698113207547169), np.float64(0.7591623036649214), np.float64(0.48466257668711654), np.float64(0.5630252100840336), np.float64(0.4696969696969697), np.float64(0.9), np.float64(0.8191489361702128), np.float64(0.9023136246786633), np.float64(1.0)]
+confusion_matrix = [[  8   2   0  12   8  12   0   0   0   0]
+ [  2 142  18   6  26  14   0   0   0   4]
+ [  0  32 145   2   8   4   0   0   0   0]
+ [  1  17   7  79  35  19   0   0   0   5]
+ [  8  20   8  28 134  26   0   0   0  14]
+ [  8  38   4  34  44 124   0   0   0  12]
+ [  0   0   0   0   0   0 144   6  10   0]
+ [  0   0   0   0   0   0   4 154  30   0]
+ [  0   0   0   0   0   0  18  20 351   0]
+ [  0   0   0   0   0   0   0   0   0  38]]
+f1_macro = 0.6494733686387086
+f1_weighted = 0.6967466186778747
+evaluate 7
+acc = 0.6949602122015915
+acc_and_f1_macro = 0.6736449120606118
+acc_and_f1_weighted = 0.6941753333487539
+class_f1 = [np.float64(0.2222222222222222), np.float64(0.5967741935483871), np.float64(0.7543859649122806), np.float64(0.4745762711864407), np.float64(0.5376782077393076), np.float64(0.5404339250493096), np.float64(0.8795180722891567), np.float64(0.8421052631578947), np.float64(0.9014084507042253), np.float64(0.7741935483870966)]
+class_p = [np.float64(0.26666666666666666), np.float64(0.5211267605633803), np.float64(0.8543046357615894), np.float64(0.5303030303030303), np.float64(0.5217391304347826), np.float64(0.5637860082304527), np.float64(0.8488372093023255), np.float64(0.8786127167630058), np.float64(0.8979591836734694), np.float64(0.6545454545454545)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.6981132075471698), np.float64(0.675392670157068), np.float64(0.4294478527607362), np.float64(0.5546218487394958), np.float64(0.5189393939393939), np.float64(0.9125), np.float64(0.8085106382978723), np.float64(0.9048843187660668), np.float64(0.9473684210526315)]
+confusion_matrix = [[  8   4   0  12   6  12   0   0   0   0]
+ [  2 148  14   4  24  18   0   0   0   2]
+ [  2  48 129   0   8   4   0   0   0   0]
+ [  1  24   0  70  35  28   0   0   0   5]
+ [  7  24   4  22 132  43   0   0   0   6]
+ [ 10  36   4  23  48 137   0   0   0   6]
+ [  0   0   0   0   0   0 146   4  10   0]
+ [  0   0   0   0   0   0   6 152  30   0]
+ [  0   0   0   0   0   0  20  17 352   0]
+ [  0   0   0   1   0   1   0   0   0  36]]
+f1_macro = 0.652329611919632
+f1_weighted = 0.6933904544959164
+evaluate 8
+acc = 0.6997347480106101
+acc_and_f1_macro = 0.6799997041569643
+acc_and_f1_weighted = 0.6995116358901213
+class_f1 = [np.float64(0.2631578947368421), np.float64(0.6058091286307054), np.float64(0.76878612716763), np.float64(0.4935897435897436), np.float64(0.5210084033613446), np.float64(0.55078125), np.float64(0.8834355828220859), np.float64(0.8510638297872339), np.float64(0.9041450777202072), np.float64(0.7608695652173912)]
+class_p = [np.float64(0.29411764705882354), np.float64(0.5407407407407407), np.float64(0.8580645161290322), np.float64(0.5167785234899329), np.float64(0.5210084033613446), np.float64(0.5685483870967742), np.float64(0.8674698795180723), np.float64(0.851063829787234), np.float64(0.9112271540469974), np.float64(0.6481481481481481)]
+class_r = [np.float64(0.23809523809523808), np.float64(0.6886792452830188), np.float64(0.6963350785340314), np.float64(0.4723926380368098), np.float64(0.5210084033613446), np.float64(0.5340909090909091), np.float64(0.9), np.float64(0.851063829787234), np.float64(0.897172236503856), np.float64(0.9210526315789473)]
+confusion_matrix = [[ 10   2   0  12   6  12   0   0   0   0]
+ [  2 146  14   4  26  18   0   0   0   2]
+ [  0  44 133   2   8   4   0   0   0   0]
+ [  4  22   0  77  30  25   0   0   0   5]
+ [  8  22   4  28 124  46   0   0   0   6]
+ [ 10  34   4  25  44 141   0   0   0   6]
+ [  0   0   0   0   0   0 144   6  10   0]
+ [  0   0   0   0   0   0   4 160  24   0]
+ [  0   0   0   0   0   0  18  22 349   0]
+ [  0   0   0   1   0   2   0   0   0  35]]
+f1_macro = 0.6602646603033184
+f1_weighted = 0.6992885237696326
+evaluate 9
+acc = 0.6944297082228117
+acc_and_f1_macro = 0.6740689450220392
+acc_and_f1_weighted = 0.6939169890732269
+class_f1 = [np.float64(0.2222222222222222), np.float64(0.6033057851239669), np.float64(0.76878612716763), np.float64(0.4838709677419355), np.float64(0.5206611570247934), np.float64(0.5401174168297457), np.float64(0.8727272727272727), np.float64(0.837465564738292), np.float64(0.9014084507042253), np.float64(0.7865168539325842)]
+class_p = [np.float64(0.26666666666666666), np.float64(0.5367647058823529), np.float64(0.8580645161290322), np.float64(0.5102040816326531), np.float64(0.5121951219512195), np.float64(0.5587044534412956), np.float64(0.8470588235294118), np.float64(0.8685714285714285), np.float64(0.8979591836734694), np.float64(0.6862745098039216)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.6886792452830188), np.float64(0.6963350785340314), np.float64(0.4601226993865031), np.float64(0.5294117647058824), np.float64(0.5227272727272727), np.float64(0.9), np.float64(0.8085106382978723), np.float64(0.9048843187660668), np.float64(0.9210526315789473)]
+confusion_matrix = [[  8   2   0  12   6  14   0   0   0   0]
+ [  2 146  14   4  26  18   0   0   0   2]
+ [  0  44 133   2   8   4   0   0   0   0]
+ [  4  22   0  75  32  25   0   0   0   5]
+ [  8  22   4  26 126  46   0   0   0   6]
+ [  8  36   4  27  48 138   0   0   0   3]
+ [  0   0   0   0   0   0 144   6  10   0]
+ [  0   0   0   0   0   0   6 152  30   0]
+ [  0   0   0   0   0   0  20  17 352   0]
+ [  0   0   0   1   0   2   0   0   0  35]]
+f1_macro = 0.6537081818212667
+f1_weighted = 0.6934042699236419

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c17da51ee001d45bde6fa33740a0130fb17c72c4c137b2bc371dab3e1e08f4b
+size 1112235744

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "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 sha256:8326842a5c7bc2e1e489f64889cf28cc938f2cec75e85efaba88b54ffa77d2b0
+size 2769