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
+0,0,0.5526425637918265,0.9589844,0.6182535546787762,0.6035156,0.4474616451825811,0.9999097011106763,0.4262552623354809
+0,0,0.5526425637918265,0.9589844,0.6182535546787762,0.6035156,0.4474616451825811,0.9999097011106763,0.4262552623354809
+0,0,0.5526425637918265,0.9589844,0.6182535546787762,0.6035156,0.4474616451825811,0.9999097011106763,0.4262552623354809
+0,0,0.5526425637918265,0.9589844,0.6182535546787762,0.6035156,0.4474616451825811,0.9999097011106763,0.4262552623354809
+0.09596330363269086,20000,0.6076078906618192,0.1875,0.6569540025519276,0.07910156,0.5033899120065394,0.9453390723294104,0.5956208960759726
+0.09596330363269086,20000,0.6040126573756144,0.20800781,0.6606378016199482,0.083984375,0.5099261877874339,0.9378141648857719,0.590106659536392
+0.09596330363269086,20000,0.6046724567427456,0.18457031,0.6571979174430118,0.07714844,0.5084514003294893,0.928964873732053,0.5918929196664637
+0.09596330363269086,20000,0.6017100922372585,0.19921875,0.6539650060550382,0.07470703,0.5006153600255734,0.9427505041687987,0.5839840201608288

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57f77ebd6a51dda0900d118d06b23e5a84f8ccadceab69fc303efa78783a0617
+oid sha256:160aa613bec4156768917281d3dad813fafd9298631e755cf64516c28d208134
 size 299228626

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 299,
+    "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 sha256:75f4396753950ebe568629d637dab7058b2af2533948250b5f7114489c99dca7
+size 6353