End of training

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
 tags:
 - generated_from_trainer
-base_model: facebook/wav2vec2-large-xlsr-53
 metrics:
 - wer
 model-index:
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0971
-- Wer: 1.0
+- Loss: 0.9022
+- Wer: 0.7197
 
 ## Model description
 
@@ -49,16 +49,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer |
-|:-------------:|:-------:|:----:|:---------------:|:---:|
-| 10.1331       | 8.7719  | 500  | 3.1635          | 1.0 |
-| 3.0445        | 17.5439 | 1000 | 2.9632          | 1.0 |
-| 1.986         | 26.3158 | 1500 | 1.0971          | 1.0 |
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 9.9291        | 8.93  | 500  | 3.1984          | 1.0    |
+| 2.9471        | 17.86 | 1000 | 2.8526          | 1.0    |
+| 1.5367        | 26.79 | 1500 | 0.9022          | 0.7197 |
 
 
 ### Framework versions
 
-- Transformers 4.41.0
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.1
-- Tokenizers 0.19.1
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -86,7 +86,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 89,
+  "pad_token_id": 64,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -110,8 +110,8 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.41.0",
+  "transformers_version": "4.39.3",
   "use_weighted_layer_sum": false,
-  "vocab_size": 90,
+  "vocab_size": 65,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4abacde859d5c004cc9d47f2ef324f2c8b482839aa0ab309d28b0d630e1620e
-size 1262176480
+oid sha256:189b0cad850baa88393909a48e7174665a184ef754f72146c0a340715eabe05a
+size 1262073980

runs/May25_23-38-13_95fc9086696a/events.out.tfevents.1716680429.95fc9086696a.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a464a61b8fa2c19a40aeee6c5e4ade7ab575f7eb2df2e9a79938965081c91b
+size 13121

runs/May25_23-58-35_95fc9086696a/events.out.tfevents.1716681531.95fc9086696a.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc65c3e74b21857c0c00e4e7263ae05e553ff5df7d9b749c0fdcdc30b7a3fb8
+size 8271

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19d094c79176e116baf6cd8f23967359340bc8ca154fb328c82984cc7b100393
-size 5112
+oid sha256:070cd8a669f30108a2a693d99bbef862c1bd4f914569ba0172f4d0898b6fda25
+size 4920