End of training

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: NousResearch/Llama-2-7b-chat-hf
+license: openrail
+base_model: LinkSoul/Chinese-Llama-2-7b
 tags:
 - trl
 - sft
@@ -14,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) on an unknown dataset.
+This model is a fine-tuned version of [LinkSoul/Chinese-Llama-2-7b](https://huggingface.co/LinkSoul/Chinese-Llama-2-7b) on an unknown dataset.
 
 ## Model description
 
@@ -34,7 +35,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -50,5 +51,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.1
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "base_model_name_or_path": "LinkSoul/Chinese-Llama-2-7b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,8 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919313a9324465d46985f5ef0c8df1f72cd1e9698b4bbb0db0bc352008aad203
+oid sha256:5511dbcd638e6ce8afc3a7929bb7ec2124e8addb957f8c199583f322cee3ba19
 size 134235048

runs/Feb16_15-23-20_8d934c220c4e/events.out.tfevents.1708097011.8d934c220c4e.3396.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f8959fedd4d8bcf9cd80d72716f6e479449bfb335567b398f29d5b333fda3b
+size 5275

runs/Feb16_15-24-31_8d934c220c4e/events.out.tfevents.1708097078.8d934c220c4e.3396.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:265a4a412ff7bf83e77f8d3ec4d9b28de1a5f3ed3eb2e73ed723b51effb0c818
+size 5583

tokenizer.json

@@ -34,15 +34,6 @@
       "rstrip": false,
       "normalized": true,
       "special": true
-    },
-    {
-      "id": 32000,
-      "content": "<pad>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
     }
   ],
   "normalizer": {

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -23,23 +25,17 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32000": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
+  "legacy": true,
+  "model_max_length": 4096,
   "pad_token": "</s>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "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:e06744f8b5dc550acdefdb3937fd93d46bd3628a7e8e2c1b50f94b95297e8d7f
+oid sha256:93775b138c851ea56aaf11434d2f43b05dd0c1b3961a877baa1430980145c808
 size 4536