End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: peft
 license: apache-2.0
-base_model: Qwen/Qwen2-0.5B
+base_model: Maykeye/TinyLLama-v0
 tags:
 - axolotl
 - generated_from_trainer
@@ -19,18 +19,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.4.1`
 ```yaml
 adapter: lora
-base_model: Qwen/Qwen2-0.5B
+base_model: Maykeye/TinyLLama-v0
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: null
 datasets:
 - format: custom
-  path: mhenrichsen/alpaca_2k_test
+  path: samoline/api-generator
   type:
-    field_input: input
-    field_instruction: instruction
-    field_output: output
-    format: '{instruction} {input}'
+    field_instruction: query
+    field_output: functions
+    format: '{instruction}'
     no_input_format: '{instruction}'
     system_format: '{system}'
     system_prompt: ''
@@ -65,7 +64,7 @@ lora_target_linear: true
 lr_scheduler: cosine
 max_steps: 10
 micro_batch_size: 2
-mlflow_experiment_name: mhenrichsen/alpaca_2k_test
+mlflow_experiment_name: samoline/api-generator
 model_type: AutoModelForCausalLM
 num_epochs: 1
 optimizer: adamw_bnb_8bit
@@ -76,6 +75,8 @@ s2_attention: null
 sample_packing: false
 saves_per_epoch: 4
 sequence_len: 512
+special_tokens:
+  pad_token: </s>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -98,9 +99,9 @@ xformers_attention: null
 
 # e3947cb3-7c20-41c7-b215-9a5e96c2917b
 
-This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the None dataset.
+This model is a fine-tuned version of [Maykeye/TinyLLama-v0](https://huggingface.co/Maykeye/TinyLLama-v0) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5238
+- Loss: 10.0749
 
 ## Model description
 
@@ -134,10 +135,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.5558        | 0.0042 | 1    | 1.5606          |
-| 1.402         | 0.0126 | 3    | 1.5598          |
-| 1.3486        | 0.0253 | 6    | 1.5497          |
-| 1.4565        | 0.0379 | 9    | 1.5238          |
+| 10.0927       | 0.0010 | 1    | 10.5287         |
+| 10.8992       | 0.0031 | 3    | 10.5203         |
+| 10.3469       | 0.0062 | 6    | 10.3812         |
+| 10.3735       | 0.0092 | 9    | 10.0749         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc077b1f1dc59430ba408afb480d511f372e3c86cc07bdd7903fa45a4ebb65af
-size 17717130
+oid sha256:9712679a4c96a8630eb2bc4dc4c977031474c204fbe23d309a99cda0da01caf1
+size 416906