Training in progress, step 100

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,19 +1,24 @@
 ---
-license: mit
-base_model: TheBloke/zephyr-7B-alpha-GPTQ
+base_model: beomi/gemma-ko-2b
+datasets:
+- arrow
+library_name: peft
+license: other
 tags:
+- trl
+- sft
 - generated_from_trainer
 model-index:
-- name: zephyr-support-chatbot
+- name: outputs
   results: []
 ---
 
 <!-- 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. -->
 
-# zephyr-support-chatbot
+# outputs
 
-This model is a fine-tuned version of [TheBloke/zephyr-7B-alpha-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-alpha-GPTQ) on the None dataset.
+This model is a fine-tuned version of [beomi/gemma-ko-2b](https://huggingface.co/beomi/gemma-ko-2b) on the arrow dataset.
 
 ## Model description
 
@@ -33,12 +38,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 8
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- training_steps: 250
+- lr_scheduler_type: linear
+- training_steps: 3000
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -47,7 +54,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu118
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+- PEFT 0.11.1
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -1,26 +1,34 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TheBloke/zephyr-7B-alpha-GPTQ",
+  "base_model_name_or_path": "beomi/gemma-ko-2b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 8,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 6,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "q_proj",
-    "v_proj"
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29db1885dd9cbd333cd3f7940e7f4c23993fdb601eef65a7961b959716c9f350
-size 27280152
+oid sha256:5bf35ef97e3c228e8a66d6eea3bf577449dd431a2bf055ea38b64d1757f27d3e
+size 29450584

special_tokens_map.json

@@ -1,24 +1,25 @@
 {
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
   "bos_token": {
-    "content": "<s>",
+    "content": "<bos>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -1,7 +1,9 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +11,7 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "<eos>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +19,15 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,21 +35,15 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
-  "bos_token": "<s>",
+  "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
+  "eos_token": "<eos>",
+  "legacy": null,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "left",
+  "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f110571761d23259f481f6d42ee4f28fcaf68085a30f72a8f9ee9cffdbab5d
-size 4600
+oid sha256:8b8a95389c016d6b8fe64d6e37c9c8b0792f81c1bbb63271aa8ee8ef10979ec5
+size 5368