End of training

README.md

@@ -29,16 +29,16 @@ strict: false
 datasets:
   - path: ./data/openhermes2_5_10k.jsonl
     type: sharegpt
-    conversation: llama3
+    conversation: chatml
 dataset_prepared_path: 
 val_set_size: 0.15
-output_dir: ./outputs_lora-out
+output_dir: ./lora-output-dir
 hub_model_id: venetis/llama3-8b-hermes-sandals-sample-10k
 
 data_seed: 117
 seed: 117
 
-chat_template: llama3
+chat_template: chatml
 adapter: lora
 lora_model_dir:
 lora_r: 32
@@ -107,7 +107,7 @@ lora_modules_to_save:
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8933
+- Loss: 0.8913
 
 ## Model description
 
@@ -141,22 +141,22 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.9791        | 0.0102 | 1    | 1.0349          |
-| 0.7725        | 0.2538 | 25   | 0.8235          |
-| 0.8046        | 0.5076 | 50   | 0.8169          |
-| 0.7678        | 0.7614 | 75   | 0.8099          |
-| 0.7324        | 1.0152 | 100  | 0.7924          |
-| 0.4486        | 1.2487 | 125  | 0.8461          |
-| 0.4419        | 1.5025 | 150  | 0.8462          |
-| 0.4992        | 1.7563 | 175  | 0.8350          |
-| 0.4671        | 2.0102 | 200  | 0.8272          |
-| 0.2618        | 2.2411 | 225  | 0.8615          |
-| 0.275         | 2.4949 | 250  | 0.8697          |
-| 0.2583        | 2.7487 | 275  | 0.8672          |
-| 0.3158        | 3.0025 | 300  | 0.8639          |
-| 0.2073        | 3.2335 | 325  | 0.8940          |
-| 0.1602        | 3.4873 | 350  | 0.8931          |
-| 0.1904        | 3.7411 | 375  | 0.8933          |
+| 0.9567        | 0.0102 | 1    | 1.0036          |
+| 0.7583        | 0.2545 | 25   | 0.8184          |
+| 0.8226        | 0.5089 | 50   | 0.8238          |
+| 0.7471        | 0.7634 | 75   | 0.8094          |
+| 0.7339        | 1.0178 | 100  | 0.7954          |
+| 0.4737        | 1.2494 | 125  | 0.8393          |
+| 0.4723        | 1.5038 | 150  | 0.8395          |
+| 0.5529        | 1.7583 | 175  | 0.8327          |
+| 0.4288        | 2.0127 | 200  | 0.8277          |
+| 0.2476        | 2.2468 | 225  | 0.8617          |
+| 0.2566        | 2.5013 | 250  | 0.8676          |
+| 0.2787        | 2.7557 | 275  | 0.8654          |
+| 0.3477        | 3.0102 | 300  | 0.8648          |
+| 0.1912        | 3.2392 | 325  | 0.8909          |
+| 0.1868        | 3.4936 | 350  | 0.8912          |
+| 0.1864        | 3.7481 | 375  | 0.8913          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11818ca0411c345a582973e166a7ea0a185370f4a65a9a42478da155eee042dd
+oid sha256:0ad75736c96439fef7ac6573457990b3614d98c25164d676e2e68bac32c7806a
 size 4370694462