AmirlyPhd/IeeeNfsuV7

README.md

@@ -4,7 +4,7 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: NousResearch/Llama-2-7b-hf
+base_model: meta-llama/Llama-2-7b-hf
 model-index:
 - name: trained_weigths
   results: []
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # trained_weigths
 
-This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0609
+- Loss: 1.5108
 
 ## Model description
 
@@ -37,22 +37,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 16
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- training_steps: 30
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.7687        | 0.03  | 30   | 1.0609          |
+| 1.5207        | 1.0   | 1377 | 1.5108          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj",
     "o_proj",
+    "gate_proj",
     "q_proj",
-    "gate_proj"
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f4bb35eaa42501a6e59b55e0a44d44722004922ef35e18ae879f8786229320
+oid sha256:bc4ff19d765a1f8708463447ab29e1e7f49ebba49cb8692145d83ebee8dddbad
 size 1688334680

runs/Apr13_01-53-08_61995e1f34b2/events.out.tfevents.1712973783.61995e1f34b2.78.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32604409229ca80321300f78678d4ae8cc37969d28c82689f8714cce9d7dccbe
+size 14024

special_tokens_map.json

@@ -21,7 +21,7 @@
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -14,7 +14,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -23,7 +23,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -32,7 +32,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {

tokenizer_config.json

@@ -5,7 +5,7 @@
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -13,7 +13,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -21,7 +21,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -54,6 +54,7 @@
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|im_end|>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc9d240b008498f5df064c69c1dc7f025073ab6e2dff33c62a2622c18d8e448
-size 4664
+oid sha256:19dd85d85061e913bde374860bf37f293854707bbe06f53abf3e68fdc405058f
+size 4728