End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: asapp/sew-d-tiny-100k
+base_model: asapp/sew-d-tiny-100k-ft-ls100h
 tags:
 - generated_from_trainer
 metrics:
@@ -18,14 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sewd_classifier
 
-This model is a fine-tuned version of [asapp/sew-d-tiny-100k](https://huggingface.co/asapp/sew-d-tiny-100k) on an unknown dataset.
+This model is a fine-tuned version of [asapp/sew-d-tiny-100k-ft-ls100h](https://huggingface.co/asapp/sew-d-tiny-100k-ft-ls100h) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
+- Loss: 4.4387
 - Accuracy: 0.0128
 - Precision: 0.0002
 - Recall: 0.0128
 - F1: 0.0003
-- Binary: 0.1299
+- Binary: 0.1156
 
 ## Model description
 
@@ -59,9 +59,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Binary |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
-| 0.0           | 1.0   | 876  | nan             | 0.0128   | 0.0002    | 0.0128 | 0.0003 | 0.1299 |
-| 0.0           | 2.0   | 1752 | nan             | 0.0128   | 0.0002    | 0.0128 | 0.0003 | 0.1299 |
-| 0.0           | 3.0   | 2628 | nan             | 0.0128   | 0.0002    | 0.0128 | 0.0003 | 0.1299 |
+| 4.4296        | 1.0   | 876  | 4.4357          | 0.0128   | 0.0002    | 0.0128 | 0.0003 | 0.1156 |
+| 4.427         | 2.0   | 1752 | 4.4385          | 0.0128   | 0.0002    | 0.0128 | 0.0003 | 0.1156 |
+| 4.4257        | 3.0   | 2628 | 4.4387          | 0.0128   | 0.0002    | 0.0128 | 0.0003 | 0.1156 |
 
 
 ### Framework versions

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "asapp/sew-d-tiny-100k",
-  "activation_dropout": 0.0,
+  "_name_or_path": "asapp/sew-d-tiny-100k-ft-ls100h",
+  "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [
     "SEWDForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "conv_bias": false,
@@ -54,17 +54,17 @@
     2,
     1
   ],
-  "ctc_loss_reduction": "sum",
+  "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
+  "feat_proj_dropout": 0.0,
   "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_layer_norm_eps": 1e-05,
   "final_dropout": 0.0,
   "hidden_act": "gelu_python",
-  "hidden_dropout": 0.1,
+  "hidden_dropout": 0.0,
   "hidden_size": 384,
   "id2label": {
     "0": "LABEL_0",
@@ -241,10 +241,10 @@
     "LABEL_9": 9
   },
   "layer_norm_eps": 1e-07,
-  "layerdrop": 0.05,
-  "mask_feature_length": 10,
+  "layerdrop": 0.1,
+  "mask_feature_length": 64,
   "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.0,
+  "mask_feature_prob": 0.5,
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.65,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da4c2bf9ca39f30f76fa4b9c6d4a54426e86af2027bfe5cd89c8e330a172f7d7
+oid sha256:79ff77b47cc02c6ad91798d5a75fa4087ad43a70d3b11f9716973cb542460603
 size 96968812

runs/Jun11_00-02-10_LAPTOP-1GID9RGH/events.out.tfevents.1718038931.LAPTOP-1GID9RGH.22860.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5618b5507afa08b1dd7b55a4d102ab7c5884a06e22e23cf3bc4b2ad20c763dad
+size 11928

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3456573c5ce2735370189efdd7541878e1323dd0a901ea6226795161eec7881d
+oid sha256:9b67d26a553a2ef4eb806550922b7f0cc62cb2dd5edce049e08c38aa48b7179d
 size 4984