End of training

README.md

@@ -3,8 +3,6 @@ license: apache-2.0
 base_model: Samuael/asr-alffamharic-phoneme-based
 tags:
 - generated_from_trainer
-metrics:
-- wer
 model-index:
 - name: asr-alffamharic-phoneme-based
   results: []
@@ -17,8 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Samuael/asr-alffamharic-phoneme-based](https://huggingface.co/Samuael/asr-alffamharic-phoneme-based) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4179
-- Wer: 0.4986
+- eval_loss: 0.3353
+- eval_wer: 0.4832
+- eval_runtime: 21.1513
+- eval_samples_per_second: 16.973
+- eval_steps_per_second: 2.128
+- epoch: 10.46
+- step: 1600
 
 ## Model description
 
@@ -44,29 +47,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 20
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.3208        | 1.23  | 200  | 0.4162          | 0.5180 |
-| 0.3139        | 2.45  | 400  | 0.4169          | 0.5141 |
-| 0.2832        | 3.68  | 600  | 0.4136          | 0.5167 |
-| 0.2904        | 4.91  | 800  | 0.4137          | 0.5144 |
-| 0.255         | 6.13  | 1000 | 0.4149          | 0.5113 |
-| 0.2536        | 7.36  | 1200 | 0.4132          | 0.5108 |
-| 0.2222        | 8.59  | 1400 | 0.4186          | 0.5086 |
-| 0.2247        | 9.82  | 1600 | 0.4134          | 0.5076 |
-| 0.2106        | 11.04 | 1800 | 0.4145          | 0.5093 |
-| 0.2101        | 12.27 | 2000 | 0.4191          | 0.5026 |
-| 0.2383        | 13.5  | 2200 | 0.4183          | 0.5    |
-| 0.2882        | 14.72 | 2400 | 0.4160          | 0.4988 |
-| 0.2337        | 15.95 | 2600 | 0.4166          | 0.4998 |
-| 0.2424        | 17.18 | 2800 | 0.4172          | 0.4985 |
-| 0.2301        | 18.4  | 3000 | 0.4175          | 0.4993 |
-| 0.2257        | 19.63 | 3200 | 0.4179          | 0.4986 |
-
+- num_epochs: 30
 
 ### Framework versions
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06583092da54a35f8e79893fa0407b729eff47674389074ffef921951417308
+oid sha256:e208e3f1d213634955ea90565604041a812128f4c4e27b47df6c85acb4acbec6
 size 377686878

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:297df8c644b7d59e8d0aec7e5bacc36ebd293bd56cc9b9f673c9f52538fd0c0e
+oid sha256:0f2defc07db446a1eaffcb98cbbe090025c2fc6fc646e3e9a81c78ab37321d5b
 size 4600