Training in progress, epoch 0

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "c_proj",
-    "c_fc_1",
-    "out_proj",
     "q_proj",
+    "out_proj",
+    "c_proj",
+    "c_fc_0",
     "v_proj",
-    "c_fc_0"
+    "c_fc_1"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0f8d512345284187afceb62fcf150d5bfd5b9cbbfcfcb6349cef1171d08602
-size 4362172200
+oid sha256:08371e7b97fcbb2ad833b3f83b7827e7992c6ed2b1c7d386fdac2096edd4c926
+size 2684417600

runs/Feb14_04-08-14_cheetah-6b636a696e-v0ai2h-5c66894495-lb59j/events.out.tfevents.1739506105.cheetah-6b636a696e-v0ai2h-5c66894495-lb59j.149603.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a5de903b2a93951544fe31651829ca24d96750b4ded5481877f88027622f856
+size 24440

special_tokens_map.json

@@ -1,23 +1,25 @@
 {
-  "additional_special_tokens": [
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
-  "bos_token": "<|im_start|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|im_end|>",
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[|endofturn|]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,

tokenizer.json

@@ -3260,24 +3260,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 102400,
-      "content": "<|im_start|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 102401,
-      "content": "<|im_end|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -2896,22 +2896,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "102400": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102401": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_token": [
@@ -3226,16 +3210,12 @@
     "PI:IP_ADDRESS",
     "PI:USER"
   ],
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "bos_token": "<|im_start|>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "bos_token": "[BOS]",
+  "chat_template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '[|system|][|endofturn|]\n' }}{% endif %}{{ '[|' + message['role'] + '|]' + message['content'] }}{% if message['role'] == 'user' %}{{ '\n' }}{% else %}{{ '[|endofturn|]\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '[|assistant|]' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|im_end|>",
+  "eos_token": "[|endofturn|]",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|im_end|>",
+  "pad_token": "[PAD]",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0e09eeb28d7f89705c3678585d646de6abfe6e4e764fb810706077241d2a54
-size 5496
+oid sha256:7efa3a5097145ed7a92af4fbf428d9dae8e0da362a7f1c7a446c0b6a8f498f95
+size 5560