Model save

README.md

@@ -14,8 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
 # idefics-9b-instruct-ft-instruct-compact
 
 This model is a fine-tuned version of [HuggingFaceM4/idefics-9b-instruct](https://huggingface.co/HuggingFaceM4/idefics-9b-instruct) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: nan
 
 ## Model description
 
@@ -34,7 +32,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 2e-05
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
@@ -46,28 +44,6 @@ The following hyperparameters were used during training:
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 3.7449        | 0.18  | 25   | 3.3985          |
-| 2.0448        | 0.36  | 50   | 1.6004          |
-| 0.7728        | 0.54  | 75   | 0.5974          |
-| 0.5519        | 0.73  | 100  | 0.5353          |
-| 0.5128        | 0.91  | 125  | nan             |
-| 6.5038        | 1.09  | 150  | nan             |
-| 8.2169        | 1.27  | 175  | nan             |
-| 3.1474        | 1.45  | 200  | nan             |
-| 3.2837        | 1.63  | 225  | nan             |
-| 2.7581        | 1.81  | 250  | nan             |
-| 6.01          | 2.0   | 275  | nan             |
-| 5.9971        | 2.18  | 300  | nan             |
-| 6.5173        | 2.36  | 325  | nan             |
-| 10.7043       | 2.54  | 350  | nan             |
-| 2.5312        | 2.72  | 375  | nan             |
-| 3.013         | 2.9   | 400  | nan             |
-
-
 ### Framework versions
 
 - Transformers 4.35.2