Training in progress, epoch 1

adapter_config.json

@@ -9,18 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 256,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
     "q_proj",
-    "v_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecd2fa499762d881bd41e8061dd5a00e3ee8ef70624ae80674edd82e71dea7ee
-size 27280152
+oid sha256:d23220a3633769306c36d9e8c9a51c6a76d45b2e271645d2d3c9bd89eaf7920f
+size 1342238560

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Left",
-    "max_length": 512,
+    "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -31,7 +31,6 @@
     "</s>"
   ],
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a07124bf85181ce854162e5345ac40e75f0bb37e67cf27da686b078ef9d0e4
+oid sha256:7d727d1de19e7c9284ad0f10cdf35d6def71e5d4d362cccd05045ebc46049d28
 size 4664