Training in progress, step 20000

config.json

@@ -5,7 +5,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 50281,
+  "bos_token_id": null,
   "classifier_activation": "silu",
   "classifier_bias": false,
   "classifier_dropout": 0.0,
@@ -15,7 +15,7 @@
   "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,
   "gradient_checkpointing": false,

eval/CrossEncoderClassificationEvaluator_test_cls_results.csv

@@ -0,0 +1,9 @@
+epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
+0,0,0.5604389685585404,1.0,0.6404980214265033,0.9980469,0.47140807251339023,0.9987358155494688,0.471402167346631
+0,0,0.5604389685585404,1.0,0.6404980214265033,0.9980469,0.47140807251339023,0.9987358155494688,0.471402167346631
+0,0,0.5604389685585404,1.0,0.6404980214265033,0.9980469,0.47140807251339023,0.9987358155494688,0.471402167346631
+0,0,0.5604389685585404,1.0,0.6404980214265033,0.9980469,0.47140807251339023,0.9987358155494688,0.471402167346631
+0.09596330363269086,20000,0.5963239749545546,0.16308594,0.6239773537176643,0.09814453,0.4681004879812037,0.9354964933931312,0.5552705588105546
+0.09596330363269086,20000,0.6022352386723221,0.16210938,0.6328914044315933,0.103515625,0.4799390395620801,0.9289347741022785,0.5643635475348859
+0.09596330363269086,20000,0.5982495118831213,0.16015625,0.6277295502814607,0.10498047,0.47738000031362215,0.9163230292267405,0.558510253292425
+0.09596330363269086,20000,0.6004712852622366,0.16210938,0.6300222402361205,0.106933594,0.48113462118446326,0.9123498780964994,0.5631214528032874

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5971ce7e3df4d6ffc5f6b887d7783aec6b77e444f8893e0e8e89d5cf8ad8fdc3
+oid sha256:e681126da5d5b971bb5ffcb6a4961563430a483a25eaaab848eb259fe4ca45e6
 size 299225554

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 8192,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 50283,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449c93d4ed449143fc8e439083e1a2750b4990c94c9a03d9e3aa81a528410713
+size 6353