End of training

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+base_model: unsloth/meta-llama-3.1-8b-bnb-4bit
 library_name: peft
-license: apache-2.0
+license: llama3.1
 tags:
 - trl
 - sft
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3-bnb-4bit) on the None dataset.
+This model is a fine-tuned version of [unsloth/meta-llama-3.1-8b-bnb-4bit](https://huggingface.co/unsloth/meta-llama-3.1-8b-bnb-4bit) on the None dataset.
 
 ## Model description
 
@@ -54,8 +54,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.12.0
-- Transformers 4.44.0
-- Pytorch 2.3.1+cu121
-- Datasets 2.20.0
+- PEFT 0.13.3.dev0
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
 - Tokenizers 0.19.1

adapter_config.json

@@ -1,8 +1,9 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "base_model_name_or_path": "unsloth/meta-llama-3.1-8b-bnb-4bit",
   "bias": "none",
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -20,13 +21,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
     "k_proj",
+    "o_proj",
     "v_proj",
-    "down_proj",
     "gate_proj",
-    "o_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:d44550386a74be584d68fb7a912cb3a10ec39f6562f84aeb643f52f43815e8b5
+oid sha256:a99194740e22320bcc9dc66b656c6e73f06196d51802f5def4098520ca9809ac
 size 167832240

runs/Oct15_11-15-10_f6a5a5cff894/events.out.tfevents.1728990944.f6a5a5cff894.279.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05aba6f86c7550098306b91807015a00b9fb4670968b65b2ab00d433bec76e4c
+size 18635

special_tokens_map.json

@@ -1,27 +1,20 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<|begin_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|end_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "[control_768]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": "<|finetune_right_pad_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb8b1aa7694fe8996b9dc9fe84059913f11683a94e4fbba5aba2c7f9200071b
-size 5176
+oid sha256:ff5ca8de5d04ad67adeb9cab3f0fc38d6d92854b7c8d3951ca847d16714f5eaf
+size 5432