your-username/llama2_finetuned

README.md

@@ -4,7 +4,7 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: ybelkada/falcon-7b-sharded-bf16
+base_model: TinyPixel/Llama-2-7B-bf16-sharded
 model-index:
 - name: results
   results: []
@@ -13,10 +13,12 @@ model-index:
 <!-- 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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/team2001/falcon/runs/g89n84q2)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/team2001/llama/runs/2it381ub)
 # results
 
-This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on an unknown dataset.
+This model is a fine-tuned version of [TinyPixel/Llama-2-7B-bf16-sharded](https://huggingface.co/TinyPixel/Llama-2-7B-bf16-sharded) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5778
 
 ## Model description
 
@@ -35,20 +37,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.0004
 - train_batch_size: 4
-- eval_batch_size: 8
+- eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
-- lr_scheduler_warmup_ratio: 0.03
+- lr_scheduler_warmup_steps: 100
 - num_epochs: 1
-- mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3877        | 1.0   | 4174 | 0.5778          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
+  "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,10 +20,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "dense_4h_to_h",
-    "dense_h_to_4h",
-    "query_key_value"
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "lm_head"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c199d8563d2475ada86114386192ba9d6addf3af7a9bd49d15215bac0cf7452
-size 130583912
+oid sha256:298801c2a7f16cd43893e849890d15da9c3236f7553ed86b58d1775024830910
+size 686566992

special_tokens_map.json

@@ -1,23 +1,24 @@
 {
-  "additional_special_tokens": [
-    ">>TITLE<<",
-    ">>ABSTRACT<<",
-    ">>INTRODUCTION<<",
-    ">>SUMMARY<<",
-    ">>COMMENT<<",
-    ">>ANSWER<<",
-    ">>QUESTION<<",
-    ">>DOMAIN<<",
-    ">>PREFIX<<",
-    ">>SUFFIX<<",
-    ">>MIDDLE<<"
-  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>"
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,119 +1,39 @@
 {
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
-      "content": ">>TITLE<<",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": ">>ABSTRACT<<",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": ">>INTRODUCTION<<",
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": ">>SUMMARY<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": ">>COMMENT<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": ">>ANSWER<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": ">>QUESTION<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": ">>DOMAIN<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": ">>PREFIX<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "9": {
-      "content": ">>SUFFIX<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "10": {
-      "content": ">>MIDDLE<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "11": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [
-    ">>TITLE<<",
-    ">>ABSTRACT<<",
-    ">>INTRODUCTION<<",
-    ">>SUMMARY<<",
-    ">>COMMENT<<",
-    ">>ANSWER<<",
-    ">>QUESTION<<",
-    ">>DOMAIN<<",
-    ">>PREFIX<<",
-    ">>SUFFIX<<",
-    ">>MIDDLE<<"
-  ],
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 2048,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1311408a6959dd88543c60097d041cb07fac4a54a00bc9e684287e00039940d3
-size 5112
+oid sha256:081d01a8b69f8dfc82774bb9978d2baff39d267842d3d394cf2223e9e630d3ab
+size 5048