End of training

README.md

@@ -1,6 +1,5 @@
 ---
-license: other
-base_model: 01-ai/Yi-6B
+base_model: NousResearch/Llama-2-7b-chat-hf
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # finetuned_llama
 
-This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on an unknown dataset.
+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.
 
 ## Model description
 
@@ -36,8 +35,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "01-ai/Yi-6B",
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a611c6c2b931b0e6f37d27f030bd8a07ffb6b3ccb8271d0d9cfcc7b29cde76
-size 2179352
+oid sha256:3b79962ac1dbad719913bd2a973b2e8d53ccffabdb52b6dbd0f0c821fe7ba626
+size 1155352

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

runs/Nov21_09-00-53_Ubuntu-2204-jammy-amd64-base/events.out.tfevents.1700553653.Ubuntu-2204-jammy-amd64-base.23201.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b5c8263b9862224a58fd17d003acc1b7d83877845ce54b817e821c40927bbd2
+size 5004

special_tokens_map.json

@@ -1,19 +1,19 @@
 {
   "bos_token": {
-    "content": "<|startoftext|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
-size 1033105
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": false,
-  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -11,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<|startoftext|>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -19,26 +17,30 @@
       "special": true
     },
     "2": {
-      "content": "<|endoftext|>",
+      "content": "</s>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
-  "auto_map": {
-    "AutoTokenizer": [
-      "01-ai/Yi-6B--tokenization_yi.YiTokenizer",
-      null
-    ]
-  },
-  "bos_token": "<|startoftext|>",
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 4096,
-  "pad_token": "<|endoftext|>",
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
-  "tokenizer_class": "YiTokenizer",
-  "unk_token": "<unk>"
+  "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:cf4a82d1da640ff5f3422b043d28006958b3d21b2d3180fdaa0ae7caadfdbe51
+oid sha256:a932de1505296599656b46e27ac2c5c5ebc8f4ede3236a905b8dc9768ea8212c
 size 4600