Model save

README.md

@@ -1,8 +1,13 @@
 ---
 license: llama2
-base_model: meta-llama/Llama-2-7b-chat-hf
+library_name: peft
 tags:
+- trl
+- sft
 - generated_from_trainer
+datasets:
+- generator
+base_model: meta-llama/Llama-2-7b-chat-hf
 model-index:
 - name: llama2-7b-sft-lora
   results: []
@@ -13,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama2-7b-sft-lora
 
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
 
 ## Model description
 
@@ -37,17 +42,16 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 4
 - distributed_type: multi-GPU
-- num_devices: 4
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 64
-- total_eval_batch_size: 32
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 1
 
 ### Framework versions
 
-- Transformers 4.35.0
-- Pytorch 2.1.0+cu121
-- Datasets 2.14.6
-- Tokenizers 0.14.1
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49df4de880eb6fb53f2feb9bff517e17dcecd6384c75dfb00a947b40744189bf
+oid sha256:7d1d8ee5e122aa5ba15194f89a4f794f9c3fe72e5c3ede8c7f35cf55983cee6c
 size 258001832

runs/May16_15-03-43_d8bcbe5ca3fa/events.out.tfevents.1715871854.d8bcbe5ca3fa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8251750c14fb524f9911c2ab11b5ba52becf762e264be86b21068d2ec2cf9ec0
+size 3668

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]
 
@@ -198,17 +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
+- 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": [
-    "v_proj",
-    "down_proj",
     "k_proj",
     "q_proj",
     "up_proj",
-    "o_proj"
+    "o_proj",
+    "down_proj",
+    "v_proj"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
 }

step_0/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49df4de880eb6fb53f2feb9bff517e17dcecd6384c75dfb00a947b40744189bf
+oid sha256:7d1d8ee5e122aa5ba15194f89a4f794f9c3fe72e5c3ede8c7f35cf55983cee6c
 size 258001832

step_0/tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee563d624555c62fb5e5f06436c72f745ecd459b45f582abffe9ea1cc31e4de
-size 5560
+oid sha256:0972caf6dfbe417b15985b1fa88b70e41a7682ab205c10ce25d2feef0352bdc5
+size 5688

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee563d624555c62fb5e5f06436c72f745ecd459b45f582abffe9ea1cc31e4de
-size 5560
+oid sha256:0972caf6dfbe417b15985b1fa88b70e41a7682ab205c10ce25d2feef0352bdc5
+size 5688