Training in progress, step 100

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Weni/WeniGPT-Agents-Llama3-5.0.79-SFT-merged",
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "up_proj",
     "q_proj",
-    "v_proj",
-    "down_proj",
     "o_proj",
-    "gate_proj"
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a03202b6acd1f25cb95cdf2872f0e6fb3aa4a30c3dfdc23f041d843930e86b8
+oid sha256:98d137e511bca5d19d21b42be8bd24141e4edab751e2ce840b62bbdef5026ad3
 size 6627156248

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 8192,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": false,
+  "add_eos_token": true,
   "added_tokens_decoder": {
     "128000": {
       "content": "<|begin_of_text|>",
@@ -2060,8 +2062,5 @@
   ],
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|end_of_text|>",
-  "stride": 0,
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6efbfacb1bd4246105fb968c73512f01080c6c548d71fc0d30e01db2580eaef9
-size 6968
+oid sha256:8eace8fb9295b5f6073e5c82ca95806d4f3e1270ef54f30633e10491766d5b97
+size 6648