End of training

README.md

@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [napatswift/mt5-budget-seq-1](https://huggingface.co/napatswift/mt5-budget-seq-1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Cer: 0.5769
-- Loss: 0.0073
+- Loss: 0.0056
+- Cer: 0.7435
 
 ## Model description
 
@@ -50,6 +50,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Cer    | Validation Loss |
 |:-------------:|:-----:|:----:|:------:|:---------------:|
 | 0.0215        | 0.34  | 400  | 0.5769 | 0.0073          |
+| 0.0142        | 2.12  | 800  | 0.0072 | 0.7436          |
+| 0.0091        | 3.18  | 1200 | 0.0070 | 0.7436          |
+| 0.006         | 4.24  | 1600 | 0.0056 | 0.7435          |
 
 
 ### Framework versions

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eff4626d9a292183ce191b27e843cb66fce7aeb8046ec4310c14554d30621ed
+oid sha256:fdf63b34ff06a395fa868313a8b6654e8571815be06b4bb07a8d6c9b243662a2
 size 988946613