End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheBloke/vigogne-2-70B-chat-GPTQ](https://huggingface.co/TheBloke/vigogne-2-70B-chat-GPTQ) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7698
+- Loss: 0.8007
 
 ## Model description
 
@@ -34,40 +34,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0004
+- learning_rate: 0.0005
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- training_steps: 1000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.01  | 50   | 1.0362          |
-| No log        | 0.02  | 100  | 0.9411          |
-| No log        | 0.03  | 150  | 0.9255          |
-| No log        | 0.04  | 200  | 0.8966          |
-| No log        | 0.05  | 250  | 0.8685          |
-| No log        | 0.06  | 300  | 0.8707          |
-| No log        | 0.08  | 350  | 0.8515          |
-| No log        | 0.09  | 400  | 0.8420          |
-| No log        | 0.1   | 450  | 0.8399          |
-| 0.9406        | 0.11  | 500  | 0.8246          |
-| 0.9406        | 0.12  | 550  | 0.8070          |
-| 0.9406        | 0.13  | 600  | 0.8089          |
-| 0.9406        | 0.14  | 650  | 0.8018          |
-| 0.9406        | 0.15  | 700  | 0.7947          |
-| 0.9406        | 0.16  | 750  | 0.7910          |
-| 0.9406        | 0.17  | 800  | 0.7828          |
-| 0.9406        | 0.18  | 850  | 0.7774          |
-| 0.9406        | 0.19  | 900  | 0.7747          |
-| 0.9406        | 0.21  | 950  | 0.7712          |
-| 0.7812        | 0.22  | 1000 | 0.7698          |
+| No log        | 0.04  | 200  | 0.9786          |
+| No log        | 0.09  | 400  | 0.9424          |
+| 0.9766        | 0.13  | 600  | 0.9057          |
+| 0.9766        | 0.18  | 800  | 0.8812          |
+| 0.8539        | 0.22  | 1000 | 0.8675          |
+| 0.8539        | 0.27  | 1200 | 0.8434          |
+| 0.8539        | 0.31  | 1400 | 0.8311          |
+| 0.8396        | 0.36  | 1600 | 0.8195          |
+| 0.8396        | 0.4   | 1800 | 0.8073          |
+| 0.7841        | 0.44  | 2000 | 0.8007          |
 
 
 ### Framework versions