Model save

README.md

@@ -1,11 +1,10 @@
 ---
 license: other
-library_name: peft
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
 datasets:
 - generator
 model-index:
@@ -30,8 +29,7 @@ More information needed
 
 ## Training and evaluation data
 
-Trained on the Spider dataset for text-to-sql, specific dataset version used can be found here: [dataset](https://huggingface.co/datasets/VictorDCh/spider-clean-text-to-sql).
-This dataset also contains the evaluation data ("dev" part) and the testing data ("test" part).
+More information needed
 
 ## Training procedure
 
@@ -39,24 +37,23 @@ This dataset also contains the evaluation data ("dev" part) and the testing data
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 5
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 10
+- total_train_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 1
 
 ### Training results
 
-66.4% execution accuracy on the Spider test dataset.
+
 
 ### Framework versions
 
-- PEFT 0.7.2.dev0
 - Transformers 4.36.2
 - Pytorch 2.1.2+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2

generation_config.json

@@ -1,11 +1,9 @@
 {
-  "bos_token_id": 128000,
+  "bos_token_id": 128257,
   "do_sample": true,
-  "eos_token_id": [
-    128001,
-    128009
-  ],
+  "eos_token_id": 128256,
   "max_length": 4096,
+  "pad_token_id": 128256,
   "temperature": 0.6,
   "top_p": 0.9,
   "transformers_version": "4.36.2"

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75194b68138ccf37163e4ff612c97999368b49d5264a5d54506cec22b6958a73
-size 4976714976
+oid sha256:53a989a55fd02cb7119232b24aaced01e4ec0df2528ed6410fb1a33b32d7f326
+size 4976715056

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27481275558447069ba9dc67a43324411da2291c33459ca4ee71058f7d18a7c0
-size 4999802616
+oid sha256:d14ccf1a38a3dbee6e56b1901065f587171efde9ce58633fbb2b8366570adf12
+size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d72b7a0322e04c140ac50244a8d77619ea6620a1a637a682e8194b52b1d1a1
-size 4915916080
+oid sha256:01fc65dfc0472490cfdc5b1522c9933c43f3b4fb2cf88ac50d1dd527f9aff24c
+size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5721e2b184cbd61e38dbeb8d90f9752689af126fd4f22c748b99394b642d46a
+oid sha256:ee1687938bc153181b4355541c5fc8d294e9224533afc18136061680619a93ea
 size 1168155192