Training in progress, epoch 0

adapter_config.json

@@ -15,7 +15,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9379336b5abb58eff6866204e853fcf72225f34d799c1f973df4262c8d31a45
-size 4517152
+oid sha256:c17883c47e01ccfbfbf6d385e7a381032d74ecf6eaf83f9f1e6303e2df326759
+size 36056608

runs/Jan27_23-18-38_c42946757f0b/events.out.tfevents.1706397546.c42946757f0b.6367.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307d690500cbe70395841d33fbf6a8d9dd843428ac1b4780af8200f013b9e30e
+size 20708

special_tokens_map.json

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -55,7 +55,7 @@
   "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "pad_token": "</s>",
   "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84366e715c2ea3a0608089fe0e7bd1b47c30fdd32bffc30a12558f4be847b17e
+oid sha256:0249c0bd2c6f0ce34d4f4103cec3ccc87e696fbd06afa82844437b4e4cbcdb91
 size 4664