Training in progress, step 1145

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval/binary_classification_evaluation_Qnli-dev-1024_results.csv

@@ -0,0 +1,10 @@
+epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
+0.0994522917267224,115,0.6979166666666666,0.9675614833831787,0.6881720430107527,0.6666666666666666,0.7111111111111111,0.9675614833831787,0.688956658941829,0.3966087176872613
+0.1989045834534448,230,0.7395833333333334,0.867725133895874,0.7291666666666667,0.6862745098039216,0.7777777777777778,0.8537728786468506,0.713229712410124,0.46405228758169936
+0.2983568751801672,345,0.7291666666666666,0.8395562767982483,0.7216494845360825,0.6730769230769231,0.7777777777777778,0.8208398818969727,0.753054394869091,0.44512380090846426
+0.3978091669068896,460,0.75,0.879416823387146,0.7346938775510203,0.6792452830188679,0.8,0.8326764106750488,0.781841863547347,0.4683019469005233
+0.497261458633612,575,0.6979166666666666,0.8905854225158691,0.6909090909090909,0.5846153846153846,0.8444444444444444,0.805380642414093,0.7246322873104885,0.33620907137955974
+0.5967137503603344,690,0.71875,0.868374228477478,0.6938775510204082,0.6415094339622641,0.7555555555555555,0.8440404534339905,0.7082660274050915,0.3843486566998693
+0.6961660420870568,805,0.71875,0.8731638193130493,0.7037037037037037,0.6031746031746031,0.8444444444444444,0.781539261341095,0.724535579920194,0.3721962181491566
+0.7956183338137792,920,0.7604166666666666,0.8248084783554077,0.7628865979381444,0.7115384615384616,0.8222222222222222,0.8248084783554077,0.7343586316206616,0.528911810491234
+0.8950706255405015,1035,0.7083333333333334,0.8668882846832275,0.7090909090909091,0.6,0.8666666666666667,0.7944933772087097,0.6999822477767415,0.3808509397785054

eval/binary_classification_evaluation_Qnli-dev_results.csv

@@ -0,0 +1,10 @@
+epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
+0.0994522917267224,115,0.7395833333333334,0.8765031099319458,0.7272727272727272,0.6666666666666666,0.8,0.8635396957397461,0.760920950345153,0.4497120149145933
+0.1989045834534448,230,0.7291666666666666,0.8137844204902649,0.7222222222222222,0.6190476190476191,0.8666666666666667,0.7686975002288818,0.7513782450871136,0.41614558708189836
+0.2983568751801672,345,0.7291666666666666,0.7856455445289612,0.7169811320754719,0.6229508196721312,0.8444444444444444,0.7426920533180237,0.7529763141762885,0.4079411028893153
+0.3978091669068896,460,0.7291666666666666,0.8109143972396851,0.7346938775510203,0.6792452830188679,0.8,0.742037296295166,0.7568700790587495,0.4683019469005233
+0.497261458633612,575,0.6979166666666666,0.8145653009414673,0.7289719626168225,0.6290322580645161,0.8666666666666667,0.7076575756072998,0.7254668033788828,0.43373226132862797
+0.5967137503603344,690,0.7291666666666666,0.7942297458648682,0.7222222222222222,0.6190476190476191,0.8666666666666667,0.6964967250823975,0.7468079642036429,0.41614558708189836
+0.6961660420870568,805,0.7291666666666666,0.778366208076477,0.7142857142857142,0.660377358490566,0.7777777777777778,0.7083452939987183,0.7396468214578549,0.4263253018001963
+0.7956183338137792,920,0.71875,0.7927051782608032,0.7254901960784313,0.6491228070175439,0.8222222222222222,0.7089404463768005,0.7346717053497452,0.43697448216965834
+0.8950706255405015,1035,0.71875,0.7880457639694214,0.7238095238095237,0.6333333333333333,0.8444444444444444,0.703315019607544,0.7340095878922616,0.42578476395267345

eval/similarity_evaluation_sts-test-1024_results.csv

@@ -0,0 +1,10 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.0994522917267224,115,0.6710405361187501,0.8309834676298848
+0.1989045834534448,230,0.8484219629681994,0.8984444397927454
+0.2983568751801672,345,0.8520971782224942,0.894236476710775
+0.3978091669068896,460,0.8881975899886265,0.9114913957523785
+0.497261458633612,575,0.8845045352861245,0.9123160743907711
+0.5967137503603344,690,0.8687143218667199,0.9060527968336128
+0.6961660420870568,805,0.8671751973788917,0.9100830925358703
+0.7956183338137792,920,0.8700957313588291,0.9050692984403192
+0.8950706255405015,1035,0.8797952712975998,0.9135158587840699

eval/similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,10 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.0994522917267224,115,0.9054066453363472,0.9155824166550393
+0.1989045834534448,230,0.9066337545995211,0.9170443296862147
+0.2983568751801672,345,0.9080363785366253,0.9193020252854658
+0.3978091669068896,460,0.9096311897411768,0.9200152476526354
+0.497261458633612,575,0.9122846955191348,0.920479051307594
+0.5967137503603344,690,0.9081393663808583,0.920736019932914
+0.6961660420870568,805,0.9084514358185803,0.9218648677325396
+0.7956183338137792,920,0.9076253073025099,0.9206752404165891
+0.8950706255405015,1035,0.9084511864603124,0.9222536610997011

eval/triplet_evaluation_allNLI--triplets-1024_results.csv

@@ -0,0 +1,10 @@
+epoch,steps,accuracy_cosine
+0.0994522917267224,115,0.8020833134651184
+0.1989045834534448,230,0.9270833134651184
+0.2983568751801672,345,0.9270833134651184
+0.3978091669068896,460,0.9375
+0.497261458633612,575,0.9479166865348816
+0.5967137503603344,690,0.9375
+0.6961660420870568,805,0.9583333134651184
+0.7956183338137792,920,0.9375
+0.8950706255405015,1035,0.9375

eval/triplet_evaluation_allNLI-triplets_results.csv

@@ -0,0 +1,10 @@
+epoch,steps,accuracy_cosine
+0.0994522917267224,115,0.9791666865348816
+0.1989045834534448,230,0.9791666865348816
+0.2983568751801672,345,0.9791666865348816
+0.3978091669068896,460,0.9791666865348816
+0.497261458633612,575,0.96875
+0.5967137503603344,690,0.96875
+0.6961660420870568,805,0.9791666865348816
+0.7956183338137792,920,0.9583333134651184
+0.8950706255405015,1035,0.9791666865348816

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e969b03be79a3f792216f1febef058e86c2b7f27374fb1e044d87938ceea1ba
+size 2271151270

runs/Apr26_00-11-16_c31ed588ce90/events.out.tfevents.1745626278.c31ed588ce90.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522715cf6b382c8409a959615fb72ffe03fdc5318b5b436b851ff324cb811beb
+size 263343

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a6af42442a3e3e9f05f618eae0bb2d98ca4f6a6406cb80ef7a4fa865204d61
+size 17083052

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd4417bbdb1b05a50fcf0fbc0f0e6cb47be6950e8ca11fb3368064002c6ea02
+size 5880