End of training

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: google/mt5-small
 tags:
 - generated_from_trainer
 metrics:
@@ -8,7 +9,6 @@ metrics:
 - recall
 - f1
 - wer
-base_model: google/mt5-small
 model-index:
 - name: nep-spell-mt5-small-0
   results: []
@@ -21,20 +21,20 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6065
-- Accuracy: 0.0
-- Precision: 0.0
-- Recall: 0.0
-- F1: 0.0
-- Wer: 7.0137
-- Cer: 13.4164
-- Chrf: 1.5380
-- Exact Match: 0.0
-- Bertscore:precision: 0.4936
-- Bertscore:recall: 0.5422
-- Bertscore:f1: 0.5139
-- Ter: 701.3722
-- Blerurt: -0.5287
+- Loss: 0.0009
+- Accuracy: 0.8446
+- Precision: 0.889
+- Recall: 0.8446
+- F1: 0.8603
+- Wer: 0.0105
+- Cer: 0.0024
+- Chrf: 99.2925
+- Exact Match: 0.8446
+- Bertscore:precision: 0.9972
+- Bertscore:recall: 0.9975
+- Bertscore:f1: 0.9973
+- Ter: 1.0546
+- Blerurt: 0.8889
 
 ## Model description
 
@@ -54,8 +54,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 3
+- eval_batch_size: 3
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -64,10 +64,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1  | Wer     | Cer     | Chrf   | Exact Match | Bertscore:precision | Bertscore:recall | Bertscore:f1 | Ter       | Blerurt |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:---:|:-------:|:-------:|:------:|:-----------:|:-------------------:|:----------------:|:------------:|:---------:|:-------:|
-| 39.0737       | 0.39  | 500  | 14.0796         | 0.0      | 0.0       | 0.0    | 0.0 | 28.9335 | 58.5317 | 0.3292 | 0.0         | 0.3772              | 0.5413           | 0.4436       | 2893.3486 | -0.9012 |
-| 4.5775        | 0.79  | 1000 | 1.6065          | 0.0      | 0.0       | 0.0    | 0.0 | 7.0137  | 13.4164 | 1.5380 | 0.0         | 0.4936              | 0.5422           | 0.5139       | 701.3722  | -0.5287 |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1     | Wer    | Cer    | Chrf    | Exact Match | Bertscore:precision | Bertscore:recall | Bertscore:f1 | Ter    | Blerurt |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|:------:|:-------:|:-----------:|:-------------------:|:----------------:|:------------:|:------:|:-------:|
+| 0.006         | 0.75  | 10000 | 0.0009          | 0.8446   | 0.889     | 0.8446 | 0.8603 | 0.0105 | 0.0024 | 99.2925 | 0.8446      | 0.9972              | 0.9975           | 0.9973       | 1.0546 | 0.8889  |
 
 
 ### Framework versions

logs/events.out.tfevents.1708223192.419c861fdb15.2395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5cfc87553ca5ba22b36545fd06a6a7bda0db4f3bd1c9df415e9fd0d7065196
+size 4625

logs/events.out.tfevents.1708223722.419c861fdb15.6079.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406d5ee8bc0a11e02a4e09e6971f40c1182fec98cf7ef97dcd03c4c87f2baae4
+size 4625

logs/events.out.tfevents.1708224025.419c861fdb15.6079.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a251ef01a7d83ec611ccd46598f547696fda07fe2626025f420e51a173bc68
+size 7966

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:096aa1a889cb9e1cdfc067629f46f51925b7e99412442c613d43ae8260f17c63
+oid sha256:33053c787f37e522c04ba0b2cd9fbbf1b6fee3d5216414adf93f458bdbfef190
 size 1200729512

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2617a98a4d96484e9ea190cd4e7d3af48b5a5c13a6b641fef48e3de09d788d8
+oid sha256:c3e66c550aa0115657a0eeb8f5ebb68f5e78abd8d238e42899fb9e4dc7ce276c
 size 4856