End of training

README.md

@@ -1,13 +1,13 @@
 ---
 library_name: peft
-base_model: Korabbit/llama-2-ko-7b
+base_model: katuni4ka/tiny-random-olmo-hf
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_ea212b2c-7a64-40e6-b0ba-090dcd4d4cf9
+- Aivesa/dataset_6968a579-81bd-4958-a406-832f6d9ed6e2
 model-index:
-- name: 7f64d457-d879-428f-895a-d47c066eebc8
+- name: e59954e8-965b-441b-a19c-8b176615c1a4
   results: []
 ---
 
@@ -20,14 +20,14 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: Korabbit/llama-2-ko-7b
+base_model: katuni4ka/tiny-random-olmo-hf
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_ea212b2c-7a64-40e6-b0ba-090dcd4d4cf9
+  path: Aivesa/dataset_6968a579-81bd-4958-a406-832f6d9ed6e2
   type:
     field_input: input
     field_instruction: instruction
@@ -47,7 +47,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/7f64d457-d879-428f-895a-d47c066eebc8
+hub_model_id: Aivesa/e59954e8-965b-441b-a19c-8b176615c1a4
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -78,8 +78,6 @@ sample_packing: false
 save_safetensors: true
 saves_per_epoch: 4
 sequence_len: 512
-special_tokens:
-  pad_token: </s>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -89,10 +87,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: ea212b2c-7a64-40e6-b0ba-090dcd4d4cf9
+wandb_name: 6968a579-81bd-4958-a406-832f6d9ed6e2
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: ea212b2c-7a64-40e6-b0ba-090dcd4d4cf9
+wandb_runid: 6968a579-81bd-4958-a406-832f6d9ed6e2
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -101,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 7f64d457-d879-428f-895a-d47c066eebc8
+# e59954e8-965b-441b-a19c-8b176615c1a4
 
-This model is a fine-tuned version of [Korabbit/llama-2-ko-7b](https://huggingface.co/Korabbit/llama-2-ko-7b) on the Aivesa/dataset_ea212b2c-7a64-40e6-b0ba-090dcd4d4cf9 dataset.
+This model is a fine-tuned version of [katuni4ka/tiny-random-olmo-hf](https://huggingface.co/katuni4ka/tiny-random-olmo-hf) on the Aivesa/dataset_6968a579-81bd-4958-a406-832f6d9ed6e2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1518
+- Loss: 10.8346
 
 ## Model description
 
@@ -139,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 3.2394        | 0.0108 | 3    | 3.6426          |
-| 2.9842        | 0.0215 | 6    | 2.8471          |
-| 1.676         | 0.0323 | 9    | 1.1518          |
+| 10.8479       | 0.0040 | 3    | 10.8399         |
+| 10.8439       | 0.0080 | 6    | 10.8379         |
+| 10.8219       | 0.0120 | 9    | 10.8346         |
 
 
 ### Framework versions