Training in progress, step 527

.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/similarity_evaluation_sts-test-1024_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.09398496240601503,50,0.9001737490289153,0.913358387579682
+0.18796992481203006,100,0.8996086094131341,0.914071946442568
+0.2819548872180451,150,0.9000072544243531,0.9145547678017197
+0.37593984962406013,200,0.9014369154728474,0.9158642792125549
+0.4699248120300752,250,0.9008086953101686,0.9153775197424008
+0.5639097744360902,300,0.9000323597244693,0.9162368782148997
+0.6578947368421053,350,0.9032664609316077,0.9181316466222116
+0.7518796992481203,400,0.8991702968527955,0.9174485633683334
+0.8458646616541353,450,0.9024151738171587,0.9166481870583482
+0.9398496240601504,500,0.9074934984822008,0.9182130491666827

eval/similarity_evaluation_sts-test-1280_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.09398496240601503,50,0.9001751171497632,0.9133455887189241
+0.18796992481203006,100,0.8996114667036814,0.9140625486776759
+0.2819548872180451,150,0.9000105142972739,0.9145460860570099
+0.37593984962406013,200,0.9014376697226278,0.9158756460329482
+0.4699248120300752,250,0.9008071588604939,0.9153737158851823
+0.5639097744360902,300,0.9000281200118452,0.9162393842855376
+0.6578947368421053,350,0.903261190428662,0.9181101212654824
+0.7518796992481203,400,0.899162232134754,0.9174606014576475
+0.8458646616541353,450,0.9024051394107033,0.9166922222995573
+0.9398496240601504,500,0.9074909272280929,0.9182151077247066

eval/similarity_evaluation_sts-test-512_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.09398496240601503,50,0.89801885928312,0.9117502957528434
+0.18796992481203006,100,0.8970205686989379,0.9123232014011761
+0.2819548872180451,150,0.8967922549092373,0.9124108243709806
+0.37593984962406013,200,0.8989734750714087,0.9137803472233416
+0.4699248120300752,250,0.8989954925060826,0.913595614016318
+0.5639097744360902,300,0.8981734518979707,0.9143511495623889
+0.6578947368421053,350,0.9002490696708711,0.9164483279249741
+0.7518796992481203,400,0.8962762177120662,0.915137787235127
+0.8458646616541353,450,0.9034025337392552,0.9173902524747404
+0.9398496240601504,500,0.9062832297154773,0.9180905649642541

eval/similarity_evaluation_sts-test-760_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.09398496240601503,50,0.8983629702187792,0.9130246326722251
+0.18796992481203006,100,0.8975729153169623,0.9137202015280316
+0.2819548872180451,150,0.8975479669400709,0.9133563737729194
+0.37593984962406013,200,0.899035552252563,0.9145744583567318
+0.4699248120300752,250,0.8984529046187754,0.9140583868103663
+0.5639097744360902,300,0.8975195986295481,0.9148535719740302
+0.6578947368421053,350,0.9008742248612986,0.9173301067794302
+0.7518796992481203,400,0.8970663329368722,0.9162537046891828
+0.8458646616541353,450,0.9010373056134615,0.9162833300242239
+0.9398496240601504,500,0.9057267653570724,0.9172522395846092

eval/similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.09398496240601503,50,0.9001764198713166,0.9133424561306267
+0.18796992481203006,100,0.8996145648456096,0.9140547172069323
+0.2819548872180451,150,0.9000145065459184,0.9145197723153118
+0.37593984962406013,200,0.90143853711727,0.9158528228896387
+0.4699248120300752,250,0.9008049969790113,0.9153696435203957
+0.5639097744360902,300,0.9000245395073697,0.9162469024974514
+0.6578947368421053,350,0.9032553577987494,0.9181009920081584
+0.7518796992481203,400,0.8991549992060922,0.9174283805494456
+0.8458646616541353,450,0.9023936089136726,0.91669906924255
+0.9398496240601504,500,0.9074876367668167,0.9181634647690607

pytorch_model.bin

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

runs/Apr21_00-19-04_c2de3456501b/events.out.tfevents.1745194758.c2de3456501b.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fa5f8f566412d225b2a7e33874b4f84adaf02292bd3d5ed53e4fe575e38424
+size 126230

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:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

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:ed3b4b7ba2632853cc2592ceca005969ed0e21d4a8f049a5d7e595c810fe44fe
+size 5880