Training in progress, step 500

README.md

@@ -1,20 +1,41 @@
 ---
 library_name: transformers
+license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
 tags:
 - generated_from_trainer
 datasets:
 - common_voice_17_0
+metrics:
+- wer
 model-index:
-- name: best_model_copy
-  results: []
+- name: result_data-1
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_17_0
+      type: common_voice_17_0
+      config: uk
+      split: test
+      args: uk
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.36512878573450325
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# best_model_copy
+# result_data-1
 
-This model was trained from scratch on the common_voice_17_0 dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_17_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2220
+- Wer: 0.3651
+- Cer: 0.1691
 
 ## Model description
 
@@ -33,7 +54,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 6.532628754904162e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -43,11 +64,21 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 32
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- training_steps: 20
+- lr_scheduler_warmup_steps: 206
+- num_epochs: 7.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss | Wer    | Cer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------:|
+| 0.6324        | 0.9099 | 1000 | 0.5004          | 0.6083 | 0.2381 |
+| 0.3497        | 1.8198 | 2000 | 0.3087          | 0.4650 | 0.1965 |
+| 0.2642        | 2.7298 | 3000 | 0.2636          | 0.4249 | 0.1841 |
+| 0.2328        | 3.6397 | 4000 | 0.2431          | 0.3960 | 0.1789 |
+| 0.1933        | 4.5496 | 5000 | 0.2289          | 0.3773 | 0.1732 |
+| 0.1783        | 5.4595 | 6000 | 0.2300          | 0.3728 | 0.1711 |
+| 0.1617        | 6.3694 | 7000 | 0.2233          | 0.3637 | 0.1700 |
 
 
 ### Framework versions

all_results.json

@@ -8,9 +8,9 @@
     "eval_steps_per_second": 0.973,
     "eval_wer": 0.36512878573450325,
     "total_flos": 5.670215301911177e+19,
-    "train_loss": 0.0,
-    "train_runtime": 0.0021,
+    "train_loss": 0.6279906528631082,
+    "train_runtime": 12613.1325,
     "train_samples": 35144,
-    "train_samples_per_second": 303179.869,
-    "train_steps_per_second": 9474.371
+    "train_samples_per_second": 19.504,
+    "train_steps_per_second": 0.61
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e38c1ef5f98213097dc909a322bd8b032c79a0f6b4090e080891ef1c9450a3
+oid sha256:65fd38bdd9eb5d3221f74bcb2b95aae5c0ba46c886054aad54fe7a1f3afacd54
 size 1261971480

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 7.0,
     "total_flos": 5.670215301911177e+19,
-    "train_loss": 0.0,
-    "train_runtime": 0.0021,
+    "train_loss": 0.6279906528631082,
+    "train_runtime": 12613.1325,
     "train_samples": 35144,
-    "train_samples_per_second": 303179.869,
-    "train_steps_per_second": 9474.371
+    "train_samples_per_second": 19.504,
+    "train_steps_per_second": 0.61
 }

trainer_state.json

@@ -614,16 +614,16 @@
       "epoch": 7.0,
       "step": 7693,
       "total_flos": 5.670215301911177e+19,
-      "train_loss": 0.0,
-      "train_runtime": 0.0021,
-      "train_samples_per_second": 303179.869,
-      "train_steps_per_second": 9474.371
+      "train_loss": 0.6279906528631082,
+      "train_runtime": 12613.1325,
+      "train_samples_per_second": 19.504,
+      "train_steps_per_second": 0.61
     }
   ],
   "logging_steps": 100,
-  "max_steps": 20,
+  "max_steps": 7693,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 7,
   "save_steps": 1000,
   "stateful_callbacks": {
     "TrainerControl": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dd9a3371207756c14b28a56bce31f16533d1bb9f10f83944d5afdbbdde100f9
+oid sha256:e9c3b967339fedd24be512b8d851eeee9701f6ecbd2b3a0a29e3af25125287ba
 size 5368