End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: unsloth/mistral-7b-v0.3
+base_model: TitanML/tiny-mixtral
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_bb4495a3-40e6-47d5-8acb-8dbb8fc1970b
+- Aivesa/dataset_e20de044-9cbc-4c4d-be18-2311862fc892
 model-index:
-- name: f16a710f-b5df-407b-8bd3-f553e1ab5dd8
+- name: 123065a1-9b3c-4f1d-9da6-851c05141cb8
   results: []
 ---
 
@@ -21,18 +20,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: unsloth/mistral-7b-v0.3
+base_model: TitanML/tiny-mixtral
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_bb4495a3-40e6-47d5-8acb-8dbb8fc1970b
+  path: Aivesa/dataset_e20de044-9cbc-4c4d-be18-2311862fc892
   type:
-    field_input: choices
-    field_instruction: subject
-    field_output: question
+    field_instruction: instruction
+    field_output: output
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -48,7 +46,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/f16a710f-b5df-407b-8bd3-f553e1ab5dd8
+hub_model_id: Aivesa/123065a1-9b3c-4f1d-9da6-851c05141cb8
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -79,6 +77,8 @@ 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
@@ -88,10 +88,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: bb4495a3-40e6-47d5-8acb-8dbb8fc1970b
+wandb_name: e20de044-9cbc-4c4d-be18-2311862fc892
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: bb4495a3-40e6-47d5-8acb-8dbb8fc1970b
+wandb_runid: e20de044-9cbc-4c4d-be18-2311862fc892
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# f16a710f-b5df-407b-8bd3-f553e1ab5dd8
+# 123065a1-9b3c-4f1d-9da6-851c05141cb8
 
-This model is a fine-tuned version of [unsloth/mistral-7b-v0.3](https://huggingface.co/unsloth/mistral-7b-v0.3) on the Aivesa/dataset_bb4495a3-40e6-47d5-8acb-8dbb8fc1970b dataset.
+This model is a fine-tuned version of [TitanML/tiny-mixtral](https://huggingface.co/TitanML/tiny-mixtral) on the Aivesa/dataset_e20de044-9cbc-4c4d-be18-2311862fc892 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6346
+- Loss: 10.1504
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 7.3363        | 0.0086 | 3    | 2.0843          |
-| 6.8908        | 0.0171 | 6    | 1.7118          |
-| 5.9452        | 0.0257 | 9    | 1.6346          |
+| 10.5889       | 0.0012 | 3    | 10.5570         |
+| 10.5141       | 0.0024 | 6    | 10.4529         |
+| 10.2928       | 0.0036 | 9    | 10.1504         |
 
 
 ### Framework versions