End of training

README.md

@@ -2,10 +2,11 @@
 license: apache-2.0
 library_name: peft
 tags:
+- axolotl
 - generated_from_trainer
 base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
 model-index:
-- name: outputs/lora-out
+- name: test-model-ft-tinylama
   results: []
 ---
 
@@ -28,7 +29,7 @@ strict: false
 datasets:
   - path: RemVdH/databricks-dolly-3k
     type: alpaca
-dataset_prepared_path:
+dataset_prepared_path: last_run_prepared
 val_set_size: 0.05
 output_dir: ./outputs/lora-out
 
@@ -45,6 +46,8 @@ lora_dropout: 0.05
 lora_target_linear: true
 lora_fan_in_fan_out:
 
+hub_model_id: RemVdH/test-model-ft-tinylama
+
 wandb_project:
 wandb_entity:
 wandb_watch:
@@ -86,11 +89,11 @@ special_tokens:
 
 </details><br>
 
-# outputs/lora-out
+# test-model-ft-tinylama
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7524
+- Loss: 1.7487
 
 ## Model description
 
@@ -125,20 +128,20 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.9375        | 0.0465 | 1    | 2.1187          |
-| 1.9298        | 0.2791 | 6    | 2.0222          |
-| 1.8244        | 0.5581 | 12   | 1.8084          |
-| 1.7278        | 0.8372 | 18   | 1.7874          |
-| 1.7525        | 1.1047 | 24   | 1.7821          |
-| 1.8701        | 1.3837 | 30   | 1.7774          |
-| 1.6449        | 1.6628 | 36   | 1.7599          |
-| 1.7854        | 1.9419 | 42   | 1.7577          |
-| 1.6611        | 2.1977 | 48   | 1.7541          |
-| 1.6157        | 2.4767 | 54   | 1.7543          |
-| 1.7079        | 2.7558 | 60   | 1.7552          |
-| 1.7268        | 3.0116 | 66   | 1.7492          |
-| 1.8108        | 3.2907 | 72   | 1.7522          |
-| 1.6888        | 3.5698 | 78   | 1.7493          |
-| 1.7847        | 3.8488 | 84   | 1.7524          |
+| 1.9299        | 0.2791 | 6    | 2.0168          |
+| 1.825         | 0.5581 | 12   | 1.8114          |
+| 1.7291        | 0.8372 | 18   | 1.7892          |
+| 1.7519        | 1.1047 | 24   | 1.7811          |
+| 1.8679        | 1.3837 | 30   | 1.7753          |
+| 1.6452        | 1.6628 | 36   | 1.7567          |
+| 1.7842        | 1.9419 | 42   | 1.7574          |
+| 1.6599        | 2.1977 | 48   | 1.7538          |
+| 1.6158        | 2.4767 | 54   | 1.7543          |
+| 1.7082        | 2.7558 | 60   | 1.7560          |
+| 1.7263        | 3.0116 | 66   | 1.7518          |
+| 1.8113        | 3.2907 | 72   | 1.7511          |
+| 1.6883        | 3.5698 | 78   | 1.7497          |
+| 1.7864        | 3.8488 | 84   | 1.7487          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69db749b108e8961ff48c48274c973f35d04cd7d9ab69ce66c9ff0b941c006d
+oid sha256:243c991e5798d9cbb6504705fa0d5f46258ebfc1d4780dc4fff8d407258591bf
 size 101036698