Training in progress, step 11000

adapter_config.json

@@ -22,13 +22,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "v_proj",
+    "gate_proj",
+    "o_proj",
     "k_proj",
-    "q_proj",
     "up_proj",
-    "down_proj",
-    "o_proj",
-    "gate_proj"
+    "q_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:f1ee36dd5776d0a2883c681ae105372007f66e9e58a67edfc54f1365b8c61dce
+oid sha256:61857f48358c48a0688b720e9bcd64f65836c3dcb9b217d6c63af4d6b6b26734
 size 2460946960

runs/May11_15-47-34_77e0eb8f5427/events.out.tfevents.1715442494.77e0eb8f5427.155.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4a5e9e1bde6b85ed8812ad2ad1bfabf6719b367bfa99762672c8d5501b41f5
+size 5885

tokenizer_config.json

@@ -400,8 +400,12 @@
   "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 1024,
   "model_max_length": 4096,
   "pad_token": "<|endoftext|>",
+  "stride": 0,
   "tokenizer_class": "GPTNeoXTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db781c44455fe7bb96fd2029b04467c270de7d9e62308b5ab26aef36cf86797
+oid sha256:35777b5b187d85c4243dbcf8ef3df79d663d5c1592b328fa4de32e9b88fa0c50
 size 5048