Training in progress, step 20000

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 50281,
+  "bos_token_id": null,
   "classifier_activation": "gelu",
   "classifier_bias": false,
   "classifier_dropout": 0.0,
@@ -14,7 +14,7 @@
   "deterministic_flash_attn": false,
   "dtype": "bfloat16",
   "embedding_dropout": 0.0,
-  "eos_token_id": 50282,
+  "eos_token_id": null,
   "global_attn_every_n_layers": 3,
   "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
@@ -40,7 +40,7 @@
   "norm_eps": 1e-05,
   "num_attention_heads": 12,
   "num_hidden_layers": 22,
-  "pad_token_id": 50283,
+  "pad_token_id": 50284,
   "position_embedding_type": "absolute",
   "repad_logits_with_grad": false,
   "sentence_transformers": {

eval/CrossEncoderClassificationEvaluator_test_cls_results.csv

@@ -0,0 +1,9 @@
+epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
+0,0,0.5526425637918265,0.95703125,0.6183066872638612,0.23583984,0.44751128174041893,0.9999398007404509,0.4459251044873924
+0,0,0.5526425637918265,0.95703125,0.6183066872638612,0.23583984,0.44751128174041893,0.9999398007404509,0.4459251044873924
+0,0,0.5526425637918265,0.95703125,0.6183066872638612,0.23583984,0.44751128174041893,0.9999398007404509,0.4459251044873924
+0,0,0.5526425637918265,0.95703125,0.6183066872638612,0.23583984,0.44751128174041893,0.9999398007404509,0.4459251044873924
+0.09596330363269086,20000,0.6022352386723221,0.14941406,0.664680569347898,0.07373047,0.5150592440590455,0.9368208771032116,0.5896801747708452
+0.09596330363269086,20000,0.600444354675823,0.20605469,0.6587224520813983,0.08496094,0.507225175143447,0.9392589471149505,0.5827764263943414
+0.09596330363269086,20000,0.6078233353531273,0.14550781,0.6616197444069161,0.068359375,0.5103227492486606,0.9404328326761581,0.5922194743786546
+0.09596330363269086,20000,0.6059381943041809,0.18457031,0.6609096749054836,0.068359375,0.5082936469368581,0.9444962826957228,0.5908186531444527

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d1761887e4e8b88cca77bf1744f71a06745e806939f3773fd65f0afdde8ab6
+oid sha256:4e94b0f0cf9fa63de06ec649fad971797ad0a7ec734ae3e0bd5be9e147f6cf13
 size 299228626

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 127,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 50284,
+    "pad_type_id": 0,
+    "pad_token": "[MASK]"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597684b0e2198e1a1819b5450436582c2910d42eb83b51c139a395ed979973f0
+size 6353