your-username/falcon_finetuned

README.md

@@ -1,11 +1,10 @@
 ---
-license: apache-2.0
 library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: mistralai/Mistral-7B-v0.1
+base_model: ybelkada/falcon-7b-sharded-bf16
 model-index:
 - name: results
   results: []
@@ -14,11 +13,15 @@ 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/awqj4mrk)
+[<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/awqj4mrk)
+[<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/lq1v9kx5)
+[<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/lq1v9kx5)
+[<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/lq1v9kx5)
+[<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/lq1v9kx5)
 # results
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3806
+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.
 
 ## Model description
 
@@ -39,24 +42,24 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
 - train_batch_size: 4
-- eval_batch_size: 4
+- eval_batch_size: 8
 - 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_steps: 100
-- num_epochs: 1
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 2
+- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.3872        | 1.0   | 4174 | 0.3806          |
 
 
 ### Framework versions
 
-- PEFT 0.11.1.dev0
-- Transformers 4.40.2
+- PEFT 0.11.2.dev0
+- Transformers 4.41.0
 - Pytorch 2.2.1+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,14 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "v_proj",
-    "q_proj",
-    "lm_head",
-    "gate_proj",
-    "down_proj",
-    "o_proj",
-    "k_proj"
+    "query_key_value",
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3191c437b593a85b2422e00b5cd458c8a06e0ba0ca9d7b0c56fed5935956783
-size 694431312
+oid sha256:ea4724b2e8238c5839864e6fd5c887d6b01d57a2b987dc96ba109afc00986f2e
+size 130583912

runs/May18_13-41-21_babd416a164d/events.out.tfevents.1716039780.babd416a164d.1437.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e33d7a4ac7f0a1355efb607f4861d16d9a94218e286c3e8a36b3b6fb6fbfa7a
+size 5515

runs/May18_13-43-34_babd416a164d/events.out.tfevents.1716039828.babd416a164d.1437.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6b614a281e46c63df507e35337ddeed3bd10c65df1d6e0020e784f150d4b0e
+size 5514

runs/May18_13-45-46_babd416a164d/events.out.tfevents.1716040174.babd416a164d.1437.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4a33eee20246382198a5c538cd504e35ff759f8e52092883df896951619001
+size 5516

runs/May18_13-51-03_babd416a164d/events.out.tfevents.1716040273.babd416a164d.1437.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac55fac9d13f289e80e4a4c138b7809bc2dbabc2acbb971aa53d7288fb8700c
+size 5721

runs/May18_13-53-00_babd416a164d/events.out.tfevents.1716040397.babd416a164d.1437.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c627d54cf4343bce656d6360f94a92cfd53f3ce884cbcf35f392d05877023f01
+size 5514

runs/May18_13-53-39_babd416a164d/events.out.tfevents.1716040433.babd416a164d.1437.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a156aae08598e1a69ca446a8e281474844a5f6ebe3a4ea8c3f02a5d2d1cbe9f7
+size 27788

special_tokens_map.json

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

tokenizer_config.json

@@ -1,9 +1,8 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": ">>TITLE<<",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -11,7 +10,7 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": ">>ABSTRACT<<",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -19,7 +18,79 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": ">>INTRODUCTION<<",
+      "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,
       "rstrip": false,
@@ -27,16 +98,22 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<unk>",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "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"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213abb780a160958fe966296f84c0c08b32c4a88dbbd320063c02f2f9d92106f
-size 4984
+oid sha256:3e6dc1265cda0347e7adeec07916f41c4bcb1cb01405dae1d6aa6a77dfc24569
+size 5112