Model save

README.md

@@ -0,0 +1,56 @@
+---
+license: llama3
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+model-index:
+- name: llama-3-8B-Intruct-ft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llama-3-8B-Intruct-ft
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.05
+- training_steps: 128
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.1.0.post2+cxx11.abi
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "models/meta-llama/Meta-Llama-3-8B-Instruct",
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "output_proj",
+    "q_proj",
     "v_proj",
-    "q_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9274405661a1cec0fad0d96216a3db862de27b6e8e139c7a727254db8cd98b
+oid sha256:4ba84d1020b9bff353d5efc7b3de9981a4c5df4a28aed4733f4409061ba22468
 size 75523312

special_tokens_map.json

@@ -13,5 +13,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "[PAD]"
+  "pad_token": "<|eot_id|>"
 }

tokenizer.json

@@ -2306,15 +2306,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 128256,
-      "content": "[PAD]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -2047,14 +2047,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "128256": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<|begin_of_text|>",
@@ -2066,6 +2058,6 @@
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "pad_token": "<|eot_id|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319581e6a7a0126d61777c8fefa32c370beb70dac16eda9e4491d24e3514a6ee
+oid sha256:b9902c84d8e80052d0d2b771e55d671022953c9e4139f13cabb8e0f8119e81fa
 size 5368