Model save

README.md

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

adapter_config.json

@@ -8,20 +8,24 @@
   "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": [
-    "o_proj",
-    "k_proj",
     "v_proj",
-    "up_proj",
     "q_proj",
-    "down_proj"
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
 }

runs/May17_08-54-31_c842148f8542/events.out.tfevents.1715936167.c842148f8542.173323.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf6fc5d31fe36b0b3dc9fac3e26278d26bf02eb9889cf80c27f76d7b51899a46
+size 4308

step_0/README.md

@@ -18,6 +18,7 @@ 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]
@@ -76,7 +77,7 @@ Use the code below to get started with the model.
 
 ### Training Data
 
-<!-- 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. -->
+<!-- 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. -->
 
 [More Information Needed]
 
@@ -107,7 +108,7 @@ Use the code below to get started with the model.
 
 #### Testing Data
 
-<!-- This should link to a Data Card if possible. -->
+<!-- This should link to a Dataset Card if possible. -->
 
 [More Information Needed]
 
@@ -198,66 +199,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 
 
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
 ### Framework versions
 
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
+- PEFT 0.8.2

step_0/adapter_config.json

@@ -8,20 +8,24 @@
   "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": [
-    "o_proj",
-    "k_proj",
     "v_proj",
-    "up_proj",
     "q_proj",
-    "down_proj"
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
 }

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fc9636bd68b1bfb0f3387ff1cc2c04a3bdd76543b748ab2b1b0380fbfd624e
+oid sha256:b4f6a2d68f11d33fcf2104f78f607f78b0659939807a12b62e4a97cedb2025de
 size 5560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fc9636bd68b1bfb0f3387ff1cc2c04a3bdd76543b748ab2b1b0380fbfd624e
+oid sha256:b4f6a2d68f11d33fcf2104f78f607f78b0659939807a12b62e4a97cedb2025de
 size 5560