Upload roberta-base model files

RoBERTa model and tokenizer files for intent detection

checkpoint-best/config.json

@@ -0,0 +1,55 @@
+{
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "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,
+  "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 sha256:4b43d88cca0c56d2e97971d49889aca66230ee20e1141466767aaffe1a58abf9
+size 498640484

checkpoint-best/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e925cd459dc9c3390463ce62bdbe8d4ccd21a108e81e138831374ef3547e91
+size 997401227

checkpoint-best/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49877f883a73acf0e98bcd1698c8a54677f7577b5fc7c5b0d23842207458f607
+size 1465

checkpoint-best/training_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ec65133ed17b44a22639b276d219fc64ee2e270abde49ad236332f6ad42d36
+size 2751

checkpoint-best/training_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87cac335688338d7f585fb42522a1563c6cc2d84e0e3e0765c7836264f10754f
+size 2751

checkpoint-best/training_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121ab9fc2a9417288737e79067f80ac928ad8aa1d7d04506f7f2501e4944c3d1
+size 2751

checkpoint-last/config.json

@@ -0,0 +1,55 @@
+{
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "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,
+  "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 sha256:76ffdd1acf85d3e695fc365682b9e38b0d4ff61f1c531df5e0579b4792fd8dbf
+size 498640484

checkpoint-last/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2237ea8ca40adf381486668ae9b107472d6bf61d51806ae36c23f50b5970250
+size 997401227

checkpoint-last/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855783c4a305fdbf382f9b519098423354c83b4be8827dd8a14eb9d04ab16548
+size 1465

checkpoint-last/step_file.txt

@@ -0,0 +1 @@
+8470

config.json

@@ -0,0 +1,55 @@
+{
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "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,
+  "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 +1,180 @@
+evaluate 0
+acc = 0.7303735787763942
+acc_and_f1_macro = 0.6964044280843411
+acc_and_f1_weighted = 0.7272904268085286
+class_f1 = [np.float64(0.16326530612244897), np.float64(0.7260579064587973), np.float64(0.7904509283819627), np.float64(0.42553191489361697), np.float64(0.5753424657534246), np.float64(0.5092592592592593), np.float64(0.9316770186335404), np.float64(0.8947368421052632), np.float64(0.9455958549222798)]
+class_p = [np.float64(0.5714285714285714), np.float64(0.6877637130801688), np.float64(0.8010752688172043), np.float64(0.42168674698795183), np.float64(0.48554913294797686), np.float64(0.6547619047619048), np.float64(0.9259259259259259), np.float64(0.8854166666666666), np.float64(0.9530026109660574)]
+class_r = [np.float64(0.09523809523809523), np.float64(0.7688679245283019), np.float64(0.7801047120418848), np.float64(0.4294478527607362), np.float64(0.7058823529411765), np.float64(0.4166666666666667), np.float64(0.9375), np.float64(0.9042553191489362), np.float64(0.9383033419023136)]
+confusion_matrix = [[  4   8   0  16   4  10   0   0   0]
+ [  0 163  21   0  18  10   0   0   0]
+ [  0  34 149   2   6   0   0   0   0]
+ [  3  12   6  70  62  10   0   0   0]
+ [  0  10   6  26 168  28   0   0   0]
+ [  0  10   4  52  88 110   0   0   0]
+ [  0   0   0   0   0   0 150   8   2]
+ [  0   0   0   0   0   0   2 170  16]
+ [  0   0   0   0   0   0  10  14 365]]
+f1_macro = 0.6624352773922881
+f1_weighted = 0.724207274840663
+evaluate 1
+acc = 0.7563616675690309
+acc_and_f1_macro = 0.7330873058383998
+acc_and_f1_weighted = 0.7565365056216706
+class_f1 = [np.float64(0.3855421686746988), np.float64(0.7427293064876959), np.float64(0.8), np.float64(0.49390243902439024), np.float64(0.5932203389830509), np.float64(0.6704761904761904), np.float64(0.8813559322033899), np.float64(0.8802228412256267), np.float64(0.9408672798948752)]
+class_p = [np.float64(0.3902439024390244), np.float64(0.7063829787234043), np.float64(0.8390804597701149), np.float64(0.4909090909090909), np.float64(0.5982905982905983), np.float64(0.6743295019157088), np.float64(0.8041237113402062), np.float64(0.9239766081871345), np.float64(0.9623655913978495)]
+class_r = [np.float64(0.38095238095238093), np.float64(0.7830188679245284), np.float64(0.7643979057591623), np.float64(0.49693251533742333), np.float64(0.5882352941176471), np.float64(0.6666666666666666), np.float64(0.975), np.float64(0.8404255319148937), np.float64(0.9203084832904884)]
+confusion_matrix = [[ 16   6   0   8   2  10   0   0   0]
+ [  4 166  12   0  16  14   0   0   0]
+ [  0  37 146   2   6   0   0   0   0]
+ [  9   8   8  81  34  23   0   0   0]
+ [  2   8   4  46 140  38   0   0   0]
+ [ 10  10   4  28  36 176   0   0   0]
+ [  0   0   0   0   0   0 156   0   4]
+ [  0   0   0   0   0   0  20 158  10]
+ [  0   0   0   0   0   0  18  13 358]]
+f1_macro = 0.7098129441077687
+f1_weighted = 0.7567113436743105
+evaluate 2
+acc = 0.7698971304818625
+acc_and_f1_macro = 0.7509621830084688
+acc_and_f1_weighted = 0.7699789106634821
+class_f1 = [np.float64(0.47058823529411764), np.float64(0.733644859813084), np.float64(0.8126649076517151), np.float64(0.49025069637883006), np.float64(0.6057906458797327), np.float64(0.707635009310987), np.float64(0.9447852760736196), np.float64(0.8924731182795699), np.float64(0.9304123711340206)]
+class_p = [np.float64(0.6153846153846154), np.float64(0.7268518518518519), np.float64(0.8191489361702128), np.float64(0.4489795918367347), np.float64(0.6445497630331753), np.float64(0.6959706959706959), np.float64(0.927710843373494), np.float64(0.9021739130434783), np.float64(0.9328165374677002)]
+class_r = [np.float64(0.38095238095238093), np.float64(0.7405660377358491), np.float64(0.806282722513089), np.float64(0.5398773006134969), np.float64(0.5714285714285714), np.float64(0.7196969696969697), np.float64(0.9625), np.float64(0.8829787234042553), np.float64(0.9280205655526992)]
+confusion_matrix = [[ 16   4   0  12   2   8   0   0   0]
+ [  2 157  17   4  20  12   0   0   0]
+ [  0  27 154   2   8   0   0   0   0]
+ [  2   9   9  88  26  29   0   0   0]
+ [  2   8   4  54 136  34   0   0   0]
+ [  4  11   4  36  19 190   0   0   0]
+ [  0   0   0   0   0   0 154   0   6]
+ [  0   0   0   0   0   0   2 166  20]
+ [  0   0   0   0   0   0  10  18 361]]
+f1_macro = 0.7320272355350752
+f1_weighted = 0.7700606908451018
+evaluate 3
+acc = 0.7574445046020574
+acc_and_f1_macro = 0.7289343823474163
+acc_and_f1_weighted = 0.7556290940626524
+class_f1 = [np.float64(0.2962962962962963), np.float64(0.7600950118764846), np.float64(0.8042328042328042), np.float64(0.4280936454849498), np.float64(0.6113207547169812), np.float64(0.6468401486988847), np.float64(0.9325153374233127), np.float64(0.8947368421052632), np.float64(0.9296874999999999)]
+class_p = [np.float64(0.6666666666666666), np.float64(0.7655502392344498), np.float64(0.8128342245989305), np.float64(0.47058823529411764), np.float64(0.5547945205479452), np.float64(0.635036496350365), np.float64(0.9156626506024096), np.float64(0.8854166666666666), np.float64(0.941952506596306)]
+class_r = [np.float64(0.19047619047619047), np.float64(0.7547169811320755), np.float64(0.7958115183246073), np.float64(0.39263803680981596), np.float64(0.680672268907563), np.float64(0.6590909090909091), np.float64(0.95), np.float64(0.9042553191489362), np.float64(0.9177377892030848)]
+confusion_matrix = [[  8   4   0  12   4  14   0   0   0]
+ [  0 160  16   2  20  14   0   0   0]
+ [  0  27 152   4   8   0   0   0   0]
+ [  2   5   9  64  47  36   0   0   0]
+ [  0   6   4  30 162  36   0   0   0]
+ [  2   7   6  24  51 174   0   0   0]
+ [  0   0   0   0   0   0 152   2   6]
+ [  0   0   0   0   0   0   2 170  16]
+ [  0   0   0   0   0   0  12  20 357]]
+f1_macro = 0.7004242600927751
+f1_weighted = 0.7538136835232475
+evaluate 4
+acc = 0.7628586897671901
+acc_and_f1_macro = 0.737212156890211
+acc_and_f1_weighted = 0.7611269408184007
+class_f1 = [np.float64(0.37288135593220334), np.float64(0.745920745920746), np.float64(0.8105263157894737), np.float64(0.42857142857142855), np.float64(0.6252354048964218), np.float64(0.6502835538752363), np.float64(0.9440993788819876), np.float64(0.8852459016393442), np.float64(0.9413265306122449)]
+class_p = [np.float64(0.6470588235294118), np.float64(0.7373271889400922), np.float64(0.8148148148148148), np.float64(0.48091603053435117), np.float64(0.5665529010238908), np.float64(0.6490566037735849), np.float64(0.9382716049382716), np.float64(0.9101123595505618), np.float64(0.9341772151898734)]
+class_r = [np.float64(0.2619047619047619), np.float64(0.7547169811320755), np.float64(0.806282722513089), np.float64(0.38650306748466257), np.float64(0.6974789915966386), np.float64(0.6515151515151515), np.float64(0.95), np.float64(0.8617021276595744), np.float64(0.9485861182519281)]
+confusion_matrix = [[ 11   4   0   8   3  16   0   0   0]
+ [  0 160  18   0  20  14   0   0   0]
+ [  0  29 154   2   6   0   0   0   0]
+ [  2   7   9  63  47  35   0   0   0]
+ [  2   8   4  30 166  28   0   0   0]
+ [  2   9   4  28  49 172   0   0   0]
+ [  0   0   0   0   0   0 152   2   6]
+ [  0   0   0   0   0   0   6 162  20]
+ [  0   0   0   0   2   0   4  14 369]]
+f1_macro = 0.7115656240132319
+f1_weighted = 0.7593951918696112
+evaluate 5
+acc = 0.7661072008662696
+acc_and_f1_macro = 0.7427259572257612
+acc_and_f1_weighted = 0.7649645956371721
+class_f1 = [np.float64(0.4), np.float64(0.7453703703703703), np.float64(0.8148148148148147), np.float64(0.4615384615384615), np.float64(0.6132264529058116), np.float64(0.6679035250463821), np.float64(0.9433962264150944), np.float64(0.891304347826087), np.float64(0.9365482233502538)]
+class_p = [np.float64(0.6666666666666666), np.float64(0.7318181818181818), np.float64(0.8235294117647058), np.float64(0.48322147651006714), np.float64(0.5862068965517241), np.float64(0.6545454545454545), np.float64(0.9493670886075949), np.float64(0.9111111111111111), np.float64(0.924812030075188)]
+class_r = [np.float64(0.2857142857142857), np.float64(0.7594339622641509), np.float64(0.806282722513089), np.float64(0.44171779141104295), np.float64(0.6428571428571429), np.float64(0.6818181818181818), np.float64(0.9375), np.float64(0.8723404255319149), np.float64(0.9485861182519281)]
+confusion_matrix = [[ 12   4   0  10   2  14   0   0   0]
+ [  0 161  17   0  20  14   0   0   0]
+ [  0  29 154   2   6   0   0   0   0]
+ [  2   8   8  72  40  33   0   0   0]
+ [  2   8   4  37 153  34   0   0   0]
+ [  2  10   4  28  40 180   0   0   0]
+ [  0   0   0   0   0   0 150   2   8]
+ [  0   0   0   0   0   0   2 164  22]
+ [  0   0   0   0   0   0   6  14 369]]
+f1_macro = 0.7193447135852529
+f1_weighted = 0.7638219904080746
+evaluate 6
+acc = 0.7682728749323227
+acc_and_f1_macro = 0.7443272819935483
+acc_and_f1_weighted = 0.7677134096600673
+class_f1 = [np.float64(0.37499999999999994), np.float64(0.7623529411764706), np.float64(0.8275862068965517), np.float64(0.4652567975830815), np.float64(0.6150712830957229), np.float64(0.6691729323308271), np.float64(0.9382716049382716), np.float64(0.8938547486033519), np.float64(0.9368686868686869)]
+class_p = [np.float64(0.5454545454545454), np.float64(0.7605633802816901), np.float64(0.8387096774193549), np.float64(0.4583333333333333), np.float64(0.5968379446640316), np.float64(0.664179104477612), np.float64(0.926829268292683), np.float64(0.9411764705882353), np.float64(0.9205955334987593)]
+class_r = [np.float64(0.2857142857142857), np.float64(0.7641509433962265), np.float64(0.8167539267015707), np.float64(0.4723926380368098), np.float64(0.634453781512605), np.float64(0.6742424242424242), np.float64(0.95), np.float64(0.851063829787234), np.float64(0.9537275064267352)]
+confusion_matrix = [[ 12   4   0  12   2  12   0   0   0]
+ [  0 162  14   2  20  14   0   0   0]
+ [  0  25 156   2   8   0   0   0   0]
+ [  2   8   8  77  34  34   0   0   0]
+ [  2   8   4  43 151  30   0   0   0]
+ [  6   6   4  32  38 178   0   0   0]
+ [  0   0   0   0   0   0 152   0   8]
+ [  0   0   0   0   0   0   4 160  24]
+ [  0   0   0   0   0   0   8  10 371]]
+f1_macro = 0.7203816890547738
+f1_weighted = 0.7671539443878119
+evaluate 7
+acc = 0.7650243638332431
+acc_and_f1_macro = 0.738707225890205
+acc_and_f1_weighted = 0.7636431511337718
+class_f1 = [np.float64(0.3448275862068965), np.float64(0.7517401392111369), np.float64(0.8086253369272237), np.float64(0.44594594594594594), np.float64(0.6067415730337079), np.float64(0.6377358490566037), np.float64(0.9454545454545454), np.float64(0.9190600522193213), np.float64(0.9513797634691195)]
+class_p = [np.float64(0.625), np.float64(0.7397260273972602), np.float64(0.8333333333333334), np.float64(0.49624060150375937), np.float64(0.5472972972972973), np.float64(0.6353383458646616), np.float64(0.9176470588235294), np.float64(0.9025641025641026), np.float64(0.9731182795698925)]
+class_r = [np.float64(0.23809523809523808), np.float64(0.7641509433962265), np.float64(0.7853403141361257), np.float64(0.4049079754601227), np.float64(0.680672268907563), np.float64(0.6401515151515151), np.float64(0.975), np.float64(0.9361702127659575), np.float64(0.9305912596401028)]
+confusion_matrix = [[ 10   4   0   9   3  16   0   0   0]
+ [  0 162  14   2  20  14   0   0   0]
+ [  0  31 150   2   8   0   0   0   0]
+ [  2   8   8  66  44  35   0   0   0]
+ [  2   8   4  30 162  32   0   0   0]
+ [  2   6   4  24  59 169   0   0   0]
+ [  0   0   0   0   0   0 156   2   2]
+ [  0   0   0   0   0   0   4 176   8]
+ [  0   0   0   0   0   0  10  17 362]]
+f1_macro = 0.7123900879471667
+f1_weighted = 0.7622619384343003
+evaluate 8
+acc = 0.7623172712506767
+acc_and_f1_macro = 0.734596760229649
+acc_and_f1_weighted = 0.7605790096477796
+class_f1 = [np.float64(0.3157894736842105), np.float64(0.7632183908045977), np.float64(0.802168021680217), np.float64(0.4413793103448276), np.float64(0.6078799249530957), np.float64(0.6305970149253731), np.float64(0.9454545454545454), np.float64(0.9095607235142119), np.float64(0.9458388375165125)]
+class_p = [np.float64(0.6), np.float64(0.7443946188340808), np.float64(0.8314606741573034), np.float64(0.5039370078740157), np.float64(0.5491525423728814), np.float64(0.6213235294117647), np.float64(0.9176470588235294), np.float64(0.8844221105527639), np.float64(0.9728260869565217)]
+class_r = [np.float64(0.21428571428571427), np.float64(0.7830188679245284), np.float64(0.774869109947644), np.float64(0.39263803680981596), np.float64(0.680672268907563), np.float64(0.6401515151515151), np.float64(0.975), np.float64(0.9361702127659575), np.float64(0.9203084832904884)]
+confusion_matrix = [[  9   4   0   9   4  16   0   0   0]
+ [  0 166  14   0  18  14   0   0   0]
+ [  0  33 148   2   8   0   0   0   0]
+ [  2   8   8  64  44  37   0   0   0]
+ [  2   6   4  28 162  36   0   0   0]
+ [  2   6   4  24  59 169   0   0   0]
+ [  0   0   0   0   0   0 156   2   2]
+ [  0   0   0   0   0   0   4 176   8]
+ [  0   0   0   0   0   0  10  21 358]]
+f1_macro = 0.7068762492086212
+f1_weighted = 0.7588407480448823
+evaluate 9
+acc = 0.7617758527341635
+acc_and_f1_macro = 0.7358060820649521
+acc_and_f1_weighted = 0.7604888182739137
+class_f1 = [np.float64(0.3448275862068965), np.float64(0.7552447552447552), np.float64(0.8150134048257371), np.float64(0.44000000000000006), np.float64(0.6037735849056604), np.float64(0.6377358490566037), np.float64(0.9390243902439025), np.float64(0.9095607235142119), np.float64(0.9433465085638999)]
+class_p = [np.float64(0.625), np.float64(0.7465437788018433), np.float64(0.8351648351648352), np.float64(0.48175182481751827), np.float64(0.547945205479452), np.float64(0.6353383458646616), np.float64(0.9166666666666666), np.float64(0.8844221105527639), np.float64(0.9675675675675676)]
+class_r = [np.float64(0.23809523809523808), np.float64(0.7641509433962265), np.float64(0.7958115183246073), np.float64(0.4049079754601227), np.float64(0.6722689075630253), np.float64(0.6401515151515151), np.float64(0.9625), np.float64(0.9361702127659575), np.float64(0.9203084832904884)]
+confusion_matrix = [[ 10   4   0   9   3  16   0   0   0]
+ [  0 162  14   2  20  14   0   0   0]
+ [  0  29 152   2   8   0   0   0   0]
+ [  2   8   8  66  44  35   0   0   0]
+ [  2   6   4  34 160  32   0   0   0]
+ [  2   8   4  24  57 169   0   0   0]
+ [  0   0   0   0   0   0 154   2   4]
+ [  0   0   0   0   0   0   4 176   8]
+ [  0   0   0   0   0   0  10  21 358]]
+f1_macro = 0.7098363113957409
+f1_weighted = 0.7592017838136639

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ffdd1acf85d3e695fc365682b9e38b0d4ff61f1c531df5e0579b4792fd8dbf
+size 498640484

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:ab94a8c18cb3f6b61dcbec326bd70cc7c3f3c6b513588ef140b4d58ab1d99cd2
+size 2769