Model save

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-large-lv60
+tags:
+- generated_from_trainer
+datasets:
+- ami
+metrics:
+- wer
+model-index:
+- name: facebook/wav2vec2-large-lv60
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: ami
+      type: ami
+      config: ihm
+      split: None
+      args: ihm
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.8378987185753448
+---
+
+<!-- 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. -->
+
+# facebook/wav2vec2-large-lv60
+
+This model is a fine-tuned version of [facebook/wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60) on the ami dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9465
+- Wer: 0.8379
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 2.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Wer    |
+|:-------------:|:------:|:-----:|:---------------:|:------:|
+| 1.0919        | 0.1565 | 1000  | 1.0169          | 0.7064 |
+| 1.4768        | 0.3131 | 2000  | 0.7156          | 0.4356 |
+| 0.9728        | 0.4696 | 3000  | 0.6462          | 0.4030 |
+| 0.5418        | 0.6262 | 4000  | 0.6171          | 0.3707 |
+| 0.8492        | 0.7827 | 5000  | 0.5758          | 0.3695 |
+| 1.4826        | 0.9393 | 6000  | 0.5801          | 0.3545 |
+| 0.3274        | 1.0958 | 7000  | 0.5244          | 0.3375 |
+| 0.2089        | 1.2523 | 8000  | 0.5047          | 0.3239 |
+| 0.2916        | 1.4089 | 9000  | 0.4901          | 0.3171 |
+| 0.1617        | 1.5654 | 10000 | 0.5070          | 0.3151 |
+| 0.3815        | 1.7220 | 11000 | 0.4948          | 0.3180 |
+| 1.0171        | 1.8785 | 12000 | 0.9465          | 0.8379 |
+
+
+### Framework versions
+
+- Transformers 4.42.0.dev0
+- Pytorch 2.3.0a0+gitcd033a1
+- Datasets 2.19.1
+- Tokenizers 0.19.1

run.ami.log

@@ -23036,3 +23036,17 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 {'loss': 1.2623, 'grad_norm': 4.058191299438477, 'learning_rate': 4.3988269794721406e-07, 'epoch': 2.0}
 
 Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+Saving model checkpoint to ./
+Configuration saved in ./config.json
+Model weights saved in ./model.safetensors
+Feature extractor saved in ./preprocessor_config.json
+tokenizer config file saved in ./tokenizer_config.json
+Special tokens file saved in ./special_tokens_map.json
+added tokens file saved in ./added_tokens.json
+Saving model checkpoint to ./
+Configuration saved in ./config.json
+Model weights saved in ./model.safetensors
+Feature extractor saved in ./preprocessor_config.json
+tokenizer config file saved in ./tokenizer_config.json
+Special tokens file saved in ./special_tokens_map.json
+added tokens file saved in ./added_tokens.json