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:e6a2086b747c10e9284a84cd28096a42071e818d8802baf8ed166a449b1235bd
+size 498643560

checkpoint-best/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c7cd0b2ea308cc8e4ef2b6ee1cc53f60fd9b4f7d0cd2687685e4ece5a69654
+size 997407371

checkpoint-best/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b328dd6ed6a20038d77cac9a82d302e753835970cd3f7f4da7d3794e697697b6
+size 1465

checkpoint-best/training_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb667493a2c4d579246e7a33203b23b093d954cb0114cfb9efefad13830e59d
+size 2751

checkpoint-best/training_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7dc0b1348472b6eeab3ecffa5abdcd7d468174663379185f3b99e2ef486d36
+size 2751

checkpoint-best/training_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c764fdce7d116407d49bf3a714cae2c6fb842faffbb9215f8056d26c5cdd259
+size 2751

checkpoint-best/training_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee73cbb4583db21f0805d150f844a43947bc6cc7086fc318666234d270bd106c
+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 @@
+9

checkpoint-last/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77dfba06b405bbcab0d4fbc8d8d3b35118198a4333ad7535c0ba3ea43b5ff5d5
+size 498643560

checkpoint-last/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b522efbbe08541eb4a1a9ce942e10e8ee67d632c3786ade58b08a1af0077e2
+size 997407371

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 +1,58 @@
+{
+  "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 +1,190 @@
+evaluate 0
+acc = 0.6875331564986737
+acc_and_f1_macro = 0.6383337888957222
+acc_and_f1_weighted = 0.6730215562756439
+class_f1 = [np.float64(nan), np.float64(0.5664488017429193), np.float64(0.7132530120481927), np.float64(0.07100591715976332), np.float64(0.551094890510949), np.float64(0.6151142355008787), np.float64(0.8875), np.float64(0.8367346938775511), np.float64(0.905511811023622), np.float64(0.7446808510638298)]
+class_p = [np.float64(nan), np.float64(0.5263157894736842), np.float64(0.6607142857142857), np.float64(1.0), np.float64(0.4870967741935484), np.float64(0.5737704918032787), np.float64(0.8875), np.float64(0.803921568627451), np.float64(0.9249329758713136), np.float64(0.625)]
+class_r = [np.float64(0.0), np.float64(0.6132075471698113), np.float64(0.774869109947644), np.float64(0.03680981595092025), np.float64(0.634453781512605), np.float64(0.6628787878787878), np.float64(0.8875), np.float64(0.8723404255319149), np.float64(0.8868894601542416), np.float64(0.9210526315789473)]
+confusion_matrix = [[  0   8   0   0  14  20   0   0   0   0]
+ [  0 130  66   0   4   8   0   0   0   4]
+ [  0  35 148   0   6   2   0   0   0   0]
+ [  0  19   6   6  79  49   0   0   0   4]
+ [  0  30   2   0 151  49   0   0   0   6]
+ [  0  24   2   0  56 175   0   0   0   7]
+ [  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  34 345   0]
+ [  0   1   0   0   0   2   0   0   0  35]]
+f1_macro = 0.5891344212927707
+f1_weighted = 0.6585099560526139
+evaluate 1
+acc = 0.7283819628647215
+acc_and_f1_macro = 0.6955297991154487
+acc_and_f1_weighted = 0.724209590530397
+class_f1 = [np.float64(nan), np.float64(0.7328918322295807), np.float64(0.7867036011080333), np.float64(0.49082568807339444), np.float64(0.4705882352941177), np.float64(0.6236559139784946), np.float64(0.9316770186335404), np.float64(0.8453608247422681), np.float64(0.9136125654450262), np.float64(0.8314606741573034)]
+class_p = [np.float64(nan), np.float64(0.6887966804979253), np.float64(0.8352941176470589), np.float64(0.39194139194139194), np.float64(0.7058823529411765), np.float64(0.5918367346938775), np.float64(0.9259259259259259), np.float64(0.82), np.float64(0.9306666666666666), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.0), np.float64(0.7830188679245284), np.float64(0.743455497382199), np.float64(0.656441717791411), np.float64(0.35294117647058826), np.float64(0.6590909090909091), np.float64(0.9375), np.float64(0.8723404255319149), np.float64(0.897172236503856), np.float64(0.9736842105263158)]
+confusion_matrix = [[  0   4   0  28   0  10   0   0   0   0]
+ [  0 166  16   0   4  26   0   0   0   0]
+ [  0  34 142   4   7   4   0   0   0   0]
+ [  0   9   6 107  16  23   0   0   0   2]
+ [  0  20   4  70  84  56   0   0   0   4]
+ [  0   8   2  64   8 174   0   0   0   8]
+ [  0   0   0   0   0   0 150   2   8   0]
+ [  0   0   0   0   0   0   6 164  18   0]
+ [  0   0   0   0   0   0   6  34 349   0]
+ [  0   0   0   0   0   1   0   0   0  37]]
+f1_macro = 0.6626776353661759
+f1_weighted = 0.7200372181960726
+evaluate 2
+acc = 0.7342175066312997
+acc_and_f1_macro = 0.7111411661238423
+acc_and_f1_weighted = 0.7320419634758704
+class_f1 = [np.float64(0.17391304347826084), np.float64(0.6826923076923077), np.float64(0.7745358090185676), np.float64(0.5000000000000001), np.float64(0.5230024213075061), np.float64(0.6505190311418685), np.float64(0.925925925925926), np.float64(0.8592592592592592), np.float64(0.9127516778523489), np.float64(0.8780487804878049)]
+class_p = [np.float64(1.0), np.float64(0.696078431372549), np.float64(0.7849462365591398), np.float64(0.4343891402714932), np.float64(0.6171428571428571), np.float64(0.5987261146496815), np.float64(0.9146341463414634), np.float64(0.8018433179723502), np.float64(0.9550561797752809), np.float64(0.8181818181818182)]
+class_r = [np.float64(0.09523809523809523), np.float64(0.6698113207547169), np.float64(0.7643979057591623), np.float64(0.588957055214724), np.float64(0.453781512605042), np.float64(0.7121212121212122), np.float64(0.9375), np.float64(0.925531914893617), np.float64(0.8740359897172236), np.float64(0.9473684210526315)]
+confusion_matrix = [[  4   4   0  22   0  12   0   0   0   0]
+ [  0 142  28   4   8  30   0   0   0   0]
+ [  0  24 146   8   7   4   0   0   0   2]
+ [  0   6   6  96  28  27   0   0   0   0]
+ [  0  20   4  53 108  51   0   0   0   2]
+ [  0   8   2  38  24 188   0   0   0   4]
+ [  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   8  41 340   0]
+ [  0   0   0   0   0   2   0   0   0  36]]
+f1_macro = 0.6880648256163849
+f1_weighted = 0.7298664203204411
+evaluate 3
+acc = 0.729973474801061
+acc_and_f1_macro = 0.7098114861443297
+acc_and_f1_weighted = 0.7276156001573959
+class_f1 = [np.float64(0.2909090909090909), np.float64(0.6960556844547564), np.float64(0.7837837837837838), np.float64(0.4931506849315069), np.float64(0.5477178423236515), np.float64(0.627177700348432), np.float64(0.9240506329113924), np.float64(0.8068181818181819), np.float64(0.9007444168734492), np.float64(0.8260869565217391)]
+class_p = [np.float64(0.6153846153846154), np.float64(0.684931506849315), np.float64(0.8100558659217877), np.float64(0.5581395348837209), np.float64(0.5409836065573771), np.float64(0.5806451612903226), np.float64(0.9358974358974359), np.float64(0.8658536585365854), np.float64(0.8705035971223022), np.float64(0.7037037037037037)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7075471698113207), np.float64(0.7591623036649214), np.float64(0.44171779141104295), np.float64(0.5546218487394958), np.float64(0.6818181818181818), np.float64(0.9125), np.float64(0.7553191489361702), np.float64(0.9331619537275064), np.float64(1.0)]
+confusion_matrix = [[  8   4   0  10   2  18   0   0   0   0]
+ [  2 150  18   0  14  26   0   0   0   2]
+ [  0  28 145   0  12   4   0   0   0   2]
+ [  1  10   6  72  42  32   0   0   0   0]
+ [  2  23   4  23 132  50   0   0   0   4]
+ [  0   4   6  24  42 180   0   0   0   8]
+ [  0   0   0   0   0   0 146   2  12   0]
+ [  0   0   0   0   0   0   4 142  42   0]
+ [  0   0   0   0   0   0   6  20 363   0]
+ [  0   0   0   0   0   0   0   0   0  38]]
+f1_macro = 0.6896494974875984
+f1_weighted = 0.7252577255137307
+evaluate 4
+acc = 0.7405835543766578
+acc_and_f1_macro = 0.7200472430586796
+acc_and_f1_weighted = 0.7380717972188013
+class_f1 = [np.float64(0.22641509433962262), np.float64(0.7111111111111111), np.float64(0.7741935483870968), np.float64(0.5), np.float64(0.5450733752620545), np.float64(0.6511627906976745), np.float64(0.9240506329113924), np.float64(0.8351648351648351), np.float64(0.9143576826196473), np.float64(0.9135802469135803)]
+class_p = [np.float64(0.5454545454545454), np.float64(0.6722689075630253), np.float64(0.7955801104972375), np.float64(0.5390070921985816), np.float64(0.5439330543933054), np.float64(0.6169491525423729), np.float64(0.9358974358974359), np.float64(0.8636363636363636), np.float64(0.8962962962962963), np.float64(0.8604651162790697)]
+class_r = [np.float64(0.14285714285714285), np.float64(0.7547169811320755), np.float64(0.7539267015706806), np.float64(0.4662576687116564), np.float64(0.5462184873949579), np.float64(0.6893939393939394), np.float64(0.9125), np.float64(0.8085106382978723), np.float64(0.9331619537275064), np.float64(0.9736842105263158)]
+confusion_matrix = [[  6   3   1   8   4  20   0   0   0   0]
+ [  0 160  20   2  14  16   0   0   0   0]
+ [  0  36 144   0   7   4   0   0   0   0]
+ [  1  10   6  76  46  24   0   0   0   0]
+ [  4  22   4  27 130  49   0   0   0   2]
+ [  0   6   6  28  38 182   0   0   0   4]
+ [  0   0   0   0   0   0 146   4  10   0]
+ [  0   0   0   0   0   0   4 152  32   0]
+ [  0   0   0   0   0   0   6  20 363   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6995109317407014
+f1_weighted = 0.7355600400609448
+evaluate 5
+acc = 0.7384615384615385
+acc_and_f1_macro = 0.7161019342885856
+acc_and_f1_weighted = 0.7361572547232091
+class_f1 = [np.float64(0.21428571428571427), np.float64(0.7075471698113207), np.float64(0.7938931297709924), np.float64(0.5422740524781341), np.float64(0.5560344827586207), np.float64(0.6502835538752363), np.float64(0.9171974522292993), np.float64(0.8068181818181819), np.float64(0.8985148514851486), np.float64(0.8505747126436782)]
+class_p = [np.float64(0.42857142857142855), np.float64(0.7075471698113207), np.float64(0.7722772277227723), np.float64(0.5166666666666667), np.float64(0.5707964601769911), np.float64(0.6490566037735849), np.float64(0.935064935064935), np.float64(0.8658536585365854), np.float64(0.8663484486873508), np.float64(0.7551020408163265)]
+class_r = [np.float64(0.14285714285714285), np.float64(0.7075471698113207), np.float64(0.8167539267015707), np.float64(0.5705521472392638), np.float64(0.542016806722689), np.float64(0.6515151515151515), np.float64(0.9), np.float64(0.7553191489361702), np.float64(0.9331619537275064), np.float64(0.9736842105263158)]
+confusion_matrix = [[  6   2   2  10   2  20   0   0   0   0]
+ [  4 150  26   2  10  18   0   0   0   2]
+ [  0  24 156   0   7   2   0   0   0   2]
+ [  0  11   8  93  40  11   0   0   0   0]
+ [  4  20   4  37 129  42   0   0   0   2]
+ [  0   4   6  38  38 172   0   0   0   6]
+ [  0   0   0   0   0   0 144   2  14   0]
+ [  0   0   0   0   0   0   4 142  42   0]
+ [  0   0   0   0   0   0   6  20 363   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6937423301156327
+f1_weighted = 0.7338529709848797
+evaluate 6
+acc = 0.7320954907161804
+acc_and_f1_macro = 0.7068304857149419
+acc_and_f1_weighted = 0.7294098619916184
+class_f1 = [np.float64(0.24), np.float64(0.6952595936794582), np.float64(0.7757255936675462), np.float64(0.49840255591054317), np.float64(0.5384615384615384), np.float64(0.639853747714808), np.float64(0.9171974522292993), np.float64(0.8306010928961749), np.float64(0.9093198992443325), np.float64(0.7708333333333335)]
+class_p = [np.float64(0.75), np.float64(0.6666666666666666), np.float64(0.7819148936170213), np.float64(0.52), np.float64(0.5478260869565217), np.float64(0.6183745583038869), np.float64(0.935064935064935), np.float64(0.8539325842696629), np.float64(0.891358024691358), np.float64(0.6379310344827587)]
+class_r = [np.float64(0.14285714285714285), np.float64(0.7264150943396226), np.float64(0.7696335078534031), np.float64(0.4785276073619632), np.float64(0.5294117647058824), np.float64(0.6628787878787878), np.float64(0.9), np.float64(0.8085106382978723), np.float64(0.9280205655526992), np.float64(0.9736842105263158)]
+confusion_matrix = [[  6   3   1  10   2  20   0   0   0   0]
+ [  0 154  24   2  10  18   0   0   0   4]
+ [  0  33 147   0   7   2   0   0   0   2]
+ [  0  11   6  78  45  23   0   0   0   0]
+ [  2  23   4  32 126  45   0   0   0   6]
+ [  0   6   6  28  40 175   0   0   0   9]
+ [  0   0   0   0   0   0 144   4  12   0]
+ [  0   0   0   0   0   0   4 152  32   0]
+ [  0   0   0   0   0   0   6  22 361   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6815654807137034
+f1_weighted = 0.7267242332670564
+evaluate 7
+acc = 0.7384615384615385
+acc_and_f1_macro = 0.7153263245059038
+acc_and_f1_weighted = 0.7361837089103094
+class_f1 = [np.float64(0.23076923076923073), np.float64(0.7123287671232876), np.float64(0.7821522309711286), np.float64(0.5093167701863354), np.float64(0.542016806722689), np.float64(0.6468401486988847), np.float64(0.9113924050632911), np.float64(0.8449197860962566), np.float64(0.9107142857142857), np.float64(0.8314606741573034)]
+class_p = [np.float64(0.6), np.float64(0.6902654867256637), np.float64(0.7842105263157895), np.float64(0.5157232704402516), np.float64(0.542016806722689), np.float64(0.635036496350365), np.float64(0.9230769230769231), np.float64(0.8494623655913979), np.float64(0.9037974683544304), np.float64(0.7254901960784313)]
+class_r = [np.float64(0.14285714285714285), np.float64(0.7358490566037735), np.float64(0.7801047120418848), np.float64(0.5030674846625767), np.float64(0.542016806722689), np.float64(0.6590909090909091), np.float64(0.9), np.float64(0.8404255319148937), np.float64(0.9177377892030848), np.float64(0.9736842105263158)]
+confusion_matrix = [[  6   3   1  10   2  20   0   0   0   0]
+ [  0 156  24   2  10  18   0   0   0   2]
+ [  0  31 149   0   7   2   0   0   0   2]
+ [  0  11   6  82  46  18   0   0   0   0]
+ [  4  20   4  35 129  42   0   0   0   4]
+ [  0   4   6  30  44 174   0   0   0   6]
+ [  0   0   0   0   0   0 144   4  12   0]
+ [  0   0   0   0   0   0   4 158  26   0]
+ [  0   0   0   0   0   0   8  24 357   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6921911105502693
+f1_weighted = 0.7339058793590801
+evaluate 8
+acc = 0.7395225464190981
+acc_and_f1_macro = 0.71706822879427
+acc_and_f1_weighted = 0.7371859461558783
+class_f1 = [np.float64(0.24), np.float64(0.7149321266968325), np.float64(0.7821522309711286), np.float64(0.49367088607594933), np.float64(0.5352697095435685), np.float64(0.6394052044609665), np.float64(0.9113924050632911), np.float64(0.8586387434554974), np.float64(0.9201030927835051), np.float64(0.8505747126436782)]
+class_p = [np.float64(0.75), np.float64(0.6869565217391305), np.float64(0.7842105263157895), np.float64(0.5098039215686274), np.float64(0.5286885245901639), np.float64(0.6277372262773723), np.float64(0.9230769230769231), np.float64(0.845360824742268), np.float64(0.9224806201550387), np.float64(0.7551020408163265)]
+class_r = [np.float64(0.14285714285714285), np.float64(0.7452830188679245), np.float64(0.7801047120418848), np.float64(0.4785276073619632), np.float64(0.542016806722689), np.float64(0.6515151515151515), np.float64(0.9), np.float64(0.8723404255319149), np.float64(0.9177377892030848), np.float64(0.9736842105263158)]
+confusion_matrix = [[  6   3   1  10   2  20   0   0   0   0]
+ [  0 158  24   2  10  16   0   0   0   2]
+ [  0  31 149   0   7   2   0   0   0   2]
+ [  0  11   6  78  50  18   0   0   0   0]
+ [  2  22   4  33 129  46   0   0   0   2]
+ [  0   4   6  30  46 172   0   0   0   6]
+ [  0   0   0   0   0   0 144   6  10   0]
+ [  0   0   0   0   0   0   4 164  20   0]
+ [  0   0   0   0   0   0   8  24 357   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6946139111694418
+f1_weighted = 0.7348493458926586
+evaluate 9
+acc = 0.7405835543766578
+acc_and_f1_macro = 0.718416663044384
+acc_and_f1_weighted = 0.7381677794788776
+class_f1 = [np.float64(0.24), np.float64(0.7181818181818183), np.float64(0.7885117493472585), np.float64(0.5093167701863354), np.float64(0.5358649789029536), np.float64(0.6444444444444444), np.float64(0.9171974522292993), np.float64(0.8449197860962566), np.float64(0.9134860050890585), np.float64(0.8505747126436782)]
+class_p = [np.float64(0.75), np.float64(0.6929824561403509), np.float64(0.7864583333333334), np.float64(0.5157232704402516), np.float64(0.538135593220339), np.float64(0.6304347826086957), np.float64(0.935064935064935), np.float64(0.8494623655913979), np.float64(0.9042821158690176), np.float64(0.7551020408163265)]
+class_r = [np.float64(0.14285714285714285), np.float64(0.7452830188679245), np.float64(0.7905759162303665), np.float64(0.5030674846625767), np.float64(0.5336134453781513), np.float64(0.6590909090909091), np.float64(0.9), np.float64(0.8404255319148937), np.float64(0.922879177377892), np.float64(0.9736842105263158)]
+confusion_matrix = [[  6   3   1  10   2  20   0   0   0   0]
+ [  0 158  24   2  10  16   0   0   0   2]
+ [  0  29 151   0   7   2   0   0   0   2]
+ [  0  11   6  82  46  18   0   0   0   0]
+ [  2  22   4  35 127  46   0   0   0   2]
+ [  0   4   6  30  44 174   0   0   0   6]
+ [  0   0   0   0   0   0 144   4  12   0]
+ [  0   0   0   0   0   0   4 158  26   0]
+ [  0   0   0   0   0   0   6  24 359   0]
+ [  0   1   0   0   0   0   0   0   0  37]]
+f1_macro = 0.6962497717121103
+f1_weighted = 0.7357520045810974

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77dfba06b405bbcab0d4fbc8d8d3b35118198a4333ad7535c0ba3ea43b5ff5d5
+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 sha256:1975a55dc91d4a2197dbc3ff407105ad5e7314f71fdd2e76a21cee1ea9aac6a4
+size 2769