End of training

README.md

@@ -1,12 +1,12 @@
 ---
-base_model: SeaLLMs/SeaLLM3-7B-Chat
 library_name: peft
 license: other
+base_model: SeaLLMs/SeaLLM3-7B-Chat
 tags:
 - axolotl
 - generated_from_trainer
 model-index:
-- name: proof-reading-SeaLLM3-7B-Chat-3090-v10
+- name: proof-reading-SeaLLM3-7B-Chat-3090-v11
   results: []
 ---
 
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
 <details><summary>See axolotl config</summary>
 
-axolotl version: `0.4.1`
+axolotl version: `0.5.0`
 ```yaml
 base_model: SeaLLMs/SeaLLM3-7B-Chat
 trust_remote_code: true
@@ -26,9 +26,8 @@ load_in_4bit: true
 strict: false
 
 datasets:
-  - path: Tippawan/pr-10-wiki-seallm
-    type: sharegpt
-    split: 'train[:100000]'
+  - path: Tippawan/p11-seallm
+    type: chat_template
     conversation: chatml
     field_messages: messages
 chat_template: chatml
@@ -42,7 +41,7 @@ eval_sample_packing: false
 pad_to_sequence_len: false
 
 push_to_hub: true
-hub_model_id: Tippawan/proof-reading-SeaLLM3-7B-Chat-3090-v10  # Replace with your Hugging Face repo ID
+hub_model_id: Tippawan/proof-reading-SeaLLM3-7B-Chat-3090-v11  # Replace with your Hugging Face repo ID
 use_auth_token: true  # Ensure you have set your Hugging Face API token in the environment
 hub_private_repo: true  # Set to true if you want the repository to be private
 hub_strategy: all_checkpoints
@@ -57,7 +56,7 @@ lora_dropout: 0.05
 lora_target_linear: true
 lora_fan_in_fan_out:
 
-wandb_project: proof-reading-SeaLLM3-7B-Chat-3090-v10
+wandb_project: proof-reading-SeaLLM3-7B-Chat-3090-v11
 wandb_entity: 
 wandb_watch:
 wandb_name:
@@ -97,7 +96,7 @@ special_tokens:
 
 </details><br>
 
-# proof-reading-SeaLLM3-7B-Chat-3090-v10
+# proof-reading-SeaLLM3-7B-Chat-3090-v11
 
 This model is a fine-tuned version of [SeaLLMs/SeaLLM3-7B-Chat](https://huggingface.co/SeaLLMs/SeaLLM3-7B-Chat) on the None dataset.
 
@@ -124,7 +123,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 8
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 10
 - num_epochs: 1
@@ -135,8 +134,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.12.0
-- Transformers 4.45.0.dev0
+- PEFT 0.13.2
+- Transformers 4.46.1
 - Pytorch 2.3.1+cu121
-- Datasets 2.21.0
-- Tokenizers 0.19.1
+- Datasets 3.0.1
+- Tokenizers 0.20.3

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:510bb9fcb5e688917e13ab4eb4ad4b47014c4f16f157be766a5439ece5fe30b1
+oid sha256:5be0710fe18dc5c0bce44d297de83dbbff8402c49f8a3cf6c7284c445680f90f
 size 161621802