End of training

README.md

@@ -1,12 +1,12 @@
 ---
 library_name: peft
 license: other
-base_model: SeaLLMs/SeaLLM3-7B-Chat
+base_model: SeaLLMs/SeaLLMs-v3-7B-Chat
 tags:
 - axolotl
 - generated_from_trainer
 model-index:
-- name: proof-reading-SeaLLM3-7B-Chat-3090-v11
+- name: proof-reading-hl-v1
   results: []
 ---
 
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 axolotl version: `0.5.0`
 ```yaml
-base_model: SeaLLMs/SeaLLM3-7B-Chat
+base_model: SeaLLMs/SeaLLMs-v3-7B-Chat
 trust_remote_code: true
 
 load_in_8bit: false
@@ -26,7 +26,7 @@ load_in_4bit: true
 strict: false
 
 datasets:
-  - path: Tippawan/p11-seallm
+  - path: Tippawan/hl-2
     type: chat_template
     conversation: chatml
     field_messages: messages
@@ -41,7 +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-v11  # Replace with your Hugging Face repo ID
+hub_model_id: Tippawan/proof-reading-hl-v1 # 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
@@ -49,14 +49,14 @@ save_total_limit: 3
 load_best_model_at_end: true
 
 adapter: lora
-lora_model_dir: Tippawan/proof-reading-SeaLLM3-7B-Chat-3090-v9
+lora_model_dir: 
 lora_r: 16
 lora_alpha: 32
 lora_dropout: 0.05
 lora_target_linear: true
 lora_fan_in_fan_out:
 
-wandb_project: proof-reading-SeaLLM3-7B-Chat-3090-v11
+wandb_project: proof-reading-hl-v1
 wandb_entity: 
 wandb_watch:
 wandb_name:
@@ -64,7 +64,7 @@ wandb_log_model:
 
 gradient_accumulation_steps: 4
 micro_batch_size: 2
-num_epochs: 1 #editted 3
+num_epochs: 10 #editted 3
 optimizer: adamw_torch
 lr_scheduler: cosine
 learning_rate: 0.0002
@@ -92,13 +92,14 @@ weight_decay: 0.0
 fsdp:
 fsdp_config:
 special_tokens:
+
 ```
 
 </details><br>
 
-# proof-reading-SeaLLM3-7B-Chat-3090-v11
+# proof-reading-hl-v1
 
-This model is a fine-tuned version of [SeaLLMs/SeaLLM3-7B-Chat](https://huggingface.co/SeaLLMs/SeaLLM3-7B-Chat) on the None dataset.
+This model is a fine-tuned version of [SeaLLMs/SeaLLMs-v3-7B-Chat](https://huggingface.co/SeaLLMs/SeaLLMs-v3-7B-Chat) on the None dataset.
 
 ## Model description
 
@@ -126,7 +127,7 @@ The following hyperparameters were used during training:
 - 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
+- num_epochs: 10
 
 ### Training results
 

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be0710fe18dc5c0bce44d297de83dbbff8402c49f8a3cf6c7284c445680f90f
+oid sha256:005442da11bab27e4487afab889afb5a1983f44da1667266a9bd4c6f9cb933d1
 size 161621802