Training in progress, step 250

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "o_proj",
-    "up_proj",
-    "gate_proj",
     "k_proj",
     "down_proj",
+    "v_proj",
+    "o_proj",
     "q_proj",
-    "v_proj"
+    "up_proj",
+    "gate_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:dfbd3c99f49a7c52d55c522c4109896168f530c7441d80012ac9117dadbd2fcb
+oid sha256:216026260bf077995ed784ec1121177b7a98a7212d360dc724e3ee94983030de
 size 167832240

runs/May16_15-13-39_iai/events.out.tfevents.1715847230.iai.45113.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e475b450ed379bab40d3dcdc49e8d9d95588ba62fe27f9623d5501c662739321
+size 5638

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|end_of_text|>",
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -2052,7 +2052,7 @@
   "bos_token": "<|begin_of_text|>",
   "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
+  "eos_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31897ef7a626d5658d20065e8cea910eea492e87ea224f25048c8e138c76f24
+oid sha256:ac08b5af2b463eb560602c6f6562a1e9af9c77d3ee2aac3a17090ac8ff8613e2
 size 4984