Model save

README.md

@@ -1,13 +1,13 @@
 ---
-license: llama3
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+datasets:
+- generator
 library_name: peft
+license: llama3
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
-datasets:
-- generator
 model-index:
 - name: Llama-3-8B-Instruct-2-spider-3
   results: []
@@ -54,8 +54,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.7.2.dev0
-- Transformers 4.36.2
-- Pytorch 2.1.2+cu121
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.3.1+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -6,6 +6,7 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
@@ -19,14 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "up_proj",
     "v_proj",
+    "gate_proj",
     "down_proj",
+    "q_proj",
     "o_proj",
-    "k_proj",
-    "gate_proj",
-    "up_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35651fd2d4d77fc8198174c3b77ad985612f98af5d45b637679968949dcd2ebf
+oid sha256:0cb34adda599bf72c99dcc3823230581a6839a00de4af4b6b07791e8f6306638
 size 3443619040

runs/Jul03_11-53-33_664dd173faa0/events.out.tfevents.1720000432.664dd173faa0.97513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a58b156ed881594e1471b93ab1a38f70e29901778070d6e5b85b976023d870c1
+size 27297

special_tokens_map.json

@@ -1,14 +1,14 @@
 {
   "additional_special_tokens": [
     {
-      "content": "<|im_end|>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<|im_start|>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,

tokenizer.json

@@ -2309,7 +2309,7 @@
     },
     {
       "id": 128256,
-      "content": "<|im_end|>",
+      "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -2318,7 +2318,7 @@
     },
     {
       "id": 128257,
-      "content": "<|im_start|>",
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -2425,6 +2425,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": true,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -2049,7 +2049,7 @@
       "special": true
     },
     "128256": {
-      "content": "<|im_end|>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2057,7 +2057,7 @@
       "special": true
     },
     "128257": {
-      "content": "<|im_start|>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2066,8 +2066,8 @@
     }
   },
   "additional_special_tokens": [
-    "<|im_end|>",
-    "<|im_start|>"
+    "<|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 %}",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8698391b9185037ebe8916b12c3ed7bc163284870b4501d4ac452f73b61559
-size 4728
+oid sha256:eaeedb4d19a2abdc486408f425e44a2526e6f8e13403bc4201ea5faef8c6804f
+size 5048