End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/mms-1b-l1107](https://huggingface.co/facebook/mms-1b-l1107) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 13.9971
-- Wer: 1.0
-- Cer: 0.9156
+- Loss: 2.4432
+- Wer: 0.4844
+- Cer: 0.1329
 
 ## Model description
 
@@ -50,15 +50,22 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer | Cer    |
-|:-------------:|:-----:|:----:|:---------------:|:---:|:------:|
-| No log        | 1.0   | 27   | 16.2785         | 1.0 | 0.8311 |
-| No log        | 2.0   | 54   | 13.9971         | 1.0 | 0.9156 |
+| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
+| No log        | 4.0   | 108  | 3.4128          | 1.0    | 1.0    |
+| No log        | 5.0   | 135  | 3.2507          | 1.0    | 1.0    |
+| No log        | 6.0   | 162  | 2.9310          | 1.0    | 0.3287 |
+| No log        | 7.0   | 189  | 2.3864          | 0.875  | 0.1958 |
+| 5.6606        | 8.0   | 216  | 2.5689          | 0.7188 | 0.1772 |
+| 5.6606        | 9.0   | 243  | 2.2867          | 0.625  | 0.1655 |
+| 5.6606        | 10.0  | 270  | 2.3748          | 0.5    | 0.1352 |
+| 5.6606        | 11.0  | 297  | 2.4432          | 0.4844 | 0.1329 |
+| 5.6606        | 12.0  | 324  | 2.5012          | 0.5156 | 0.1352 |
 
 
 ### Framework versions
 
-- Transformers 4.40.2
-- Pytorch 1.10.1
+- Transformers 4.41.0
+- Pytorch 1.10.1+cu111
 - Datasets 2.19.1
 - Tokenizers 0.19.1

adapter.mus.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f073d91ec38130a3b1f74b5ca435c978d04b58366f39f4a34cc646e2bbe717e2
-size 8834400
+oid sha256:cd5629b6684d98cef5e49ecece087f2eed541861225564229630969b8cf14cab
+size 8803656

config.json

@@ -77,7 +77,7 @@
   "num_hidden_layers": 48,
   "num_negatives": 100,
   "output_hidden_size": 1280,
-  "pad_token_id": 35,
+  "pad_token_id": 29,
   "proj_codevector_dim": 1024,
   "tdnn_dilation": [
     1,
@@ -101,8 +101,8 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.41.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 38,
+  "vocab_size": 32,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:096e9b601b6342329643c7a4d4f86bb3a0f5cf6b26079142227e557f34c9067d
-size 3858926736
+oid sha256:96d10415a2abd7a8692fea4d1982954b49bf92dd3f09c4f51f6226440a0d9d11
+size 3858895992

runs/May22_01-36-05_patas-gn2/events.out.tfevents.1716367000.patas-gn2.1497720.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a98991bc76971c1f8a7330a43be88d9d8b4825614c75ef415133e95c627f51
+size 10189

runs/May22_01-36-05_patas-gn2/events.out.tfevents.1716370951.patas-gn2.1497720.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ded4baaed37f08f10cc39404e780878b54f0ce6ef8591519aa0e1f304d0927
+size 453

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102156d5107f100eab3785f23ae0dee7dfde1f5004fe4c0c7182594347440a74
-size 4591
+oid sha256:10e32f75ea3330262c53b49c2096950d1cd0cd84f88a180e98aaccf37d5a6652
+size 4719