End of training

README.md

@@ -1,10 +1,10 @@
 ---
-base_model: mattbonnell/wav2vec2-base-wonders-phonemes
-datasets:
-- transcribed_calls
 license: apache-2.0
+base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
+datasets:
+- transcribed_calls
 model-index:
 - name: wav2vec2-base-wonders-phonemes
   results: []
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-base-wonders-phonemes
 
-This model is a fine-tuned version of [mattbonnell/wav2vec2-base-wonders-phonemes](https://huggingface.co/mattbonnell/wav2vec2-base-wonders-phonemes) on the transcribed_calls dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the transcribed_calls dataset.
 
 ## Model description
 
@@ -35,18 +35,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 32
+- train_batch_size: 48
 - eval_batch_size: 2
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 6
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 384
-- total_eval_batch_size: 12
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.01
-- num_epochs: 2
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results

global_step2/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a32ac063ba87f793cced3a83c6613576d463297604f7e5695a467ccd247d2e
+size 8516692

global_step2/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112c9a0e68408c2325e2fffc17a35a81afa2c3ae585253b2cf9df5e1ecab5cb7
+size 360823287

latest

@@ -1 +1 @@
-global_step26
+global_step2