Training in progress, step 389

.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_results.csv

@@ -0,0 +1,7 @@
+epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
+0.15051020408163265,59,0.7265625,0.6843721270561218,0.6956521739130435,0.7142857142857143,0.6779661016949152,0.6574362516403198,0.7343480130942729,0.44823424273450235
+0.3010204081632653,118,0.7421875,0.6371709108352661,0.7226890756302521,0.7166666666666667,0.7288135593220338,0.6371709108352661,0.7364484045530271,0.4819043546124848
+0.45153061224489793,177,0.7265625,0.6064693927764893,0.7154471544715446,0.6875,0.7457627118644068,0.6064693927764893,0.7384081520364875,0.45451419021127865
+0.6020408163265306,236,0.7265625,0.6457405090332031,0.6956521739130435,0.6075949367088608,0.8135593220338984,0.5757047533988953,0.7331921735040308,0.37357604001642775
+0.7525510204081632,295,0.71875,0.7058789730072021,0.6887417218543046,0.5652173913043478,0.8813559322033898,0.5248329639434814,0.7280268374444242,0.3344280153577804
+0.9030612244897959,354,0.7109375,0.7116010189056396,0.7092198581560283,0.6097560975609756,0.847457627118644,0.5781652927398682,0.7346738886839252,0.3986067385792586

eval/binary_classification_evaluation_allNLI-dev_results.csv

@@ -0,0 +1,7 @@
+epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
+0.15051020408163265,59,0.765625,0.7472490072250366,0.7058823529411764,0.6101694915254238,0.8372093023255814,0.6876716017723083,0.6640883745760782,0.5368906701581015
+0.3010204081632653,118,0.7578125,0.6858762502670288,0.7037037037037038,0.5846153846153846,0.8837209302325582,0.6323522329330444,0.6650692878242668,0.5347980893043971
+0.45153061224489793,177,0.765625,0.677872896194458,0.6972477064220183,0.5757575757575758,0.8837209302325582,0.6217950582504272,0.6675617855438021,0.5238753184730511
+0.6020408163265306,236,0.78125,0.7120361328125,0.6990291262135923,0.6,0.8372093023255814,0.660472571849823,0.676708312028844,0.5251630700083426
+0.7525510204081632,295,0.7734375,0.7263156175613403,0.7155963302752293,0.5909090909090909,0.9069767441860465,0.6493248343467712,0.6781090048839976,0.5569730681100454
+0.9030612244897959,354,0.7734375,0.716580331325531,0.6964285714285715,0.5652173913043478,0.9069767441860465,0.6203938126564026,0.669835314309871,0.5249655273153817

eval/similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,7 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.15051020408163265,59,0.9002300823689351,0.9128881860762427
+0.3010204081632653,118,0.9044351509469432,0.9150873525635388
+0.45153061224489793,177,0.9053834511159466,0.9166033910456952
+0.6020408163265306,236,0.9087666657124194,0.9172235092747959
+0.7525510204081632,295,0.9044911125085072,0.9157384386655222
+0.9030612244897959,354,0.9033761016886019,0.9159521259386664

pytorch_model.bin

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

runs/Apr16_11-11-34_e9df31cefdc1/events.out.tfevents.1744801907.e9df31cefdc1.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd703916ea06b4967321e4e195da02993d98a31044932eb4673d74c67e7100b
+size 104882

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 sha256:70d04c00bd21048a7c5303767dc7409f064f1eab4fd560a78ce3c24dced9eb56
+size 5880