End of training

README.md

@@ -7,7 +7,12 @@ tags:
 datasets:
 - lemon-mint/Korean-FineTome-100k
 - lemon-mint/smol-koreantalk
+- heegyu/open-korean-instructions-v20231020
+- FreedomIntelligence/evol-instruct-korean
 - FreedomIntelligence/alpaca-gpt4-korean
+- FreedomIntelligence/sharegpt-korean
+- coastral/korean-writing-style-instruct
+- devngho/korean-instruction-mix
 model-index:
 - name: ko-tiny-exp
   results: []
@@ -41,6 +46,27 @@ datasets:
       role: role
       content: content
 
+  - path: heegyu/open-korean-instructions-v20231020
+    type: chat_template
+    split: train[:20%]
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+    roles:
+      user: ["human", "user"]
+      assistant: ["gpt", "assistant", "bot"]
+      system: ["system", "input"]
+
+  # NOTE: https://github.com/FreedomIntelligence/MultilingualSIFT
+  - path: FreedomIntelligence/evol-instruct-korean
+    type: chat_template
+    split: train[:20%]
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+
   - path: FreedomIntelligence/alpaca-gpt4-korean
     type: chat_template
     split: train[:20%]
@@ -49,6 +75,30 @@ datasets:
       role: from
       content: value
 
+  - path: FreedomIntelligence/sharegpt-korean
+    type: chat_template
+    split: train[:20%]
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+
+  - path: coastral/korean-writing-style-instruct
+    type: chat_template
+    split: train[:20%]
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+
+  - path: devngho/korean-instruction-mix
+    type: chat_template
+    split: train[:20%]
+    field_messages: messages
+    message_property_mappings:
+      role: from
+      content: value
+
 dataset_prepared_path: last_run_prepared
 val_set_size: 0.05
 
@@ -80,7 +130,7 @@ added_tokens_overrides:
   128002: "<|im_start|>"
 
 special_tokens:
-  bos_token: <|im_start|>
+  bos_token: <|begin_of_text|>
   eos_token: <|im_end|>
   pad_token: <|im_end|>
 
@@ -91,7 +141,7 @@ resume_from_checkpoint:
 logging_steps: 1
 flash_attention: true
 
-num_epochs: 4
+num_epochs: 3
 weight_decay: 0.0
 
 ```
@@ -100,9 +150,9 @@ weight_decay: 0.0
 
 # ko-tiny-exp
 
-This model is a fine-tuned version of [minpeter/pretrained-tiny-ko](https://huggingface.co/minpeter/pretrained-tiny-ko) on the lemon-mint/Korean-FineTome-100k, the lemon-mint/smol-koreantalk and the FreedomIntelligence/alpaca-gpt4-korean datasets.
+This model is a fine-tuned version of [minpeter/pretrained-tiny-ko](https://huggingface.co/minpeter/pretrained-tiny-ko) on the lemon-mint/Korean-FineTome-100k, the lemon-mint/smol-koreantalk, the heegyu/open-korean-instructions-v20231020, the FreedomIntelligence/evol-instruct-korean, the FreedomIntelligence/alpaca-gpt4-korean, the FreedomIntelligence/sharegpt-korean, the coastral/korean-writing-style-instruct and the devngho/korean-instruction-mix datasets.
 It achieves the following results on the evaluation set:
-- Loss: 3.5174
+- Loss: 2.0944
 
 ## Model description
 
@@ -133,13 +183,14 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 100
-- training_steps: 112
+- training_steps: 264
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 3.5354        | 0.0351 | 1    | 3.5174          |
+| 3.362         | 0.0114 | 1    | 3.3719          |
+| 2.1121        | 2.2727 | 200  | 2.0944          |
 
 
 ### Framework versions