Model save

README.md

@@ -48,6 +48,6 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - Transformers 4.35.0
-- Pytorch 2.2.0+cu121
-- Datasets 2.14.7
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
 - Tokenizers 0.14.1

adapter_config.json

@@ -8,24 +8,20 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "loftq_config": {},
   "lora_alpha": 16,
   "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
+    "q_proj",
     "o_proj",
     "up_proj",
-    "q_proj",
-    "v_proj"
+    "down_proj",
+    "v_proj",
+    "k_proj"
   ],
-  "task_type": "CAUSAL_LM",
-  "use_rslora": false
+  "task_type": "CAUSAL_LM"
 }

runs/May16_17-06-17_cdc34a7ce3be/events.out.tfevents.1715879257.cdc34a7ce3be.62268.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e5b6791427747363f2bd22c96b74db429e177534dadbee660f96713c5a4c62
+size 4308

step_0/README.md

@@ -18,7 +18,6 @@ base_model: meta-llama/Llama-2-7b-chat-hf
 
 
 - **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
@@ -77,7 +76,7 @@ Use the code below to get started with the model.
 
 ### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
 [More Information Needed]
 
@@ -108,7 +107,7 @@ Use the code below to get started with the model.
 
 #### Testing Data
 
-<!-- This should link to a Dataset Card if possible. -->
+<!-- This should link to a Data Card if possible. -->
 
 [More Information Needed]
 
@@ -199,6 +198,10 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 
 
+## Training procedure
+
+
 ### Framework versions
 
-- PEFT 0.8.2
+
+- PEFT 0.6.1

step_0/adapter_config.json

@@ -8,24 +8,20 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "loftq_config": {},
   "lora_alpha": 16,
   "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
+    "q_proj",
     "o_proj",
     "up_proj",
-    "q_proj",
-    "v_proj"
+    "down_proj",
+    "v_proj",
+    "k_proj"
   ],
-  "task_type": "CAUSAL_LM",
-  "use_rslora": false
+  "task_type": "CAUSAL_LM"
 }

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f31f86312a87c59ce516aaa40473d613fb013c8021c43eed2f88a3e4e0ffda1
+oid sha256:66247858b5728ead4dbdf5ac24a724ae24015e0ac1489f89e2b67562e415e726
 size 5560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f31f86312a87c59ce516aaa40473d613fb013c8021c43eed2f88a3e4e0ffda1
+oid sha256:66247858b5728ead4dbdf5ac24a724ae24015e0ac1489f89e2b67562e415e726
 size 5560