Training in progress, epoch 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "roberta-base",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -9,13 +9,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.1,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146ef30cb58c4e6dd8f30608b36c88e416d4f1a788bb08489e6716a20a9c9a2c
-size 7147668
+oid sha256:5f3294587efc7bc8aedb172ede03de536d211c7552effebe5358f9a8766dc0fa
+size 4787492

runs/Mar01_18-17-45_1371a69697f7/events.out.tfevents.1709317066.1371a69697f7.20759.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b2b280700f9b694221a91016eec444978cd7ec22e2a0373e24339cd407c85c0
+size 5948

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b880a875f3108382e6c6a8bcb81d1f7266b03b8f4fce587fa7fab728f346f983
+oid sha256:063bb9c33b051a63f576958b478348440fe93bdba8f6e3b4976d151ece57f49f
 size 4984