Training in progress, step 388

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Viet-Mistral/Vistral-7B-Chat",
+  "base_model_name_or_path": "viet-mistral/vistral-7b-chat",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "down_proj",
-    "k_proj",
     "gate_proj",
     "o_proj",
+    "k_proj",
     "v_proj",
-    "up_proj",
-    "q_proj"
+    "down_proj",
+    "q_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7df26615ae394fbc3ed96f806fbc3ed2507f91b47f0b507f0a4b4ffc581c7a
+oid sha256:c9bd25e01b57bd09ca47387e1c5c2380c226d3febc763a8999e7c0e4bbbbe287
 size 1342238560

runs/Jun13_03-43-43_645eb69199b5/events.out.tfevents.1718250281.645eb69199b5.697.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d1630b572457ec7ef607e738e36e171d38334645b2a173456ebfdea83962747
+size 5415

tokenizer.json

@@ -67,23 +67,13 @@
       "special": false
     }
   ],
-  "normalizer": {
-    "type": "Sequence",
-    "normalizers": [
-      {
-        "type": "Prepend",
-        "prepend": "▁"
-      },
-      {
-        "type": "Replace",
-        "pattern": {
-          "String": " "
-        },
-        "content": "▁"
-      }
-    ]
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "prepend_scheme": "first",
+    "split": false
   },
-  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -68,7 +69,7 @@
   "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 = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
+  "legacy": false,
   "model_max_length": 32768,
   "pad_token": "<unk>",
   "padding_side": "right",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c2996b09fae0a79594c41493e134575ed8d80461fb584b20e2205f3dcde275
+oid sha256:9911005fc1fd1241e83522e3fb6ab028dff3db94a10d1cbec012cdf1cc04d6c8
 size 5112