Training in progress, epoch 0
Browse files- README.md +72 -0
- config.json +118 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- runs/May26_07-48-33_e7e43b6fa54b/events.out.tfevents.1716709714.e7e43b6fa54b.174.6 +3 -0
- runs/May26_07-48-51_e7e43b6fa54b/events.out.tfevents.1716709732.e7e43b6fa54b.174.7 +3 -0
- runs/May27_07-58-57_0ce2d95275b8/events.out.tfevents.1716796738.0ce2d95275b8.274.0 +3 -0
- runs/May27_21-41-07_f4e57fe9fcf0/events.out.tfevents.1716846068.f4e57fe9fcf0.437.0 +3 -0
- runs/May28_02-29-22_d2055eeddde7/events.out.tfevents.1716863363.d2055eeddde7.795.0 +3 -0
- runs/May28_03-41-53_41aa79c24ea4/events.out.tfevents.1716867715.41aa79c24ea4.940.0 +3 -0
- runs/May29_00-27-09_b4e3ac6e9b08/events.out.tfevents.1716942430.b4e3ac6e9b08.519.0 +3 -0
- runs/May29_00-40-30_b4e3ac6e9b08/events.out.tfevents.1716943230.b4e3ac6e9b08.519.1 +3 -0
- runs/May30_02-28-44_6970b3dafd8e/events.out.tfevents.1717036128.6970b3dafd8e.297.0 +3 -0
- runs/May30_02-35-21_f726364025c0/events.out.tfevents.1717036522.f726364025c0.476.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: humor_model_v2
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# humor_model_v2
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2683
|
21 |
+
- Accuracy: 0.9639
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 3e-05
|
41 |
+
- train_batch_size: 32
|
42 |
+
- eval_batch_size: 32
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 128
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 10
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
55 |
+
| No log | 0.9524 | 5 | 0.6652 | 0.9157 |
|
56 |
+
| 0.6722 | 1.9048 | 10 | 0.5931 | 0.9217 |
|
57 |
+
| 0.6722 | 2.8571 | 15 | 0.5272 | 0.9337 |
|
58 |
+
| 0.5461 | 4.0 | 21 | 0.4712 | 0.8554 |
|
59 |
+
| 0.5461 | 4.9524 | 26 | 0.3943 | 0.8916 |
|
60 |
+
| 0.3891 | 5.9048 | 31 | 0.3369 | 0.9337 |
|
61 |
+
| 0.3891 | 6.8571 | 36 | 0.3099 | 0.9398 |
|
62 |
+
| 0.2976 | 8.0 | 42 | 0.2811 | 0.9578 |
|
63 |
+
| 0.2976 | 8.9524 | 47 | 0.2713 | 0.9578 |
|
64 |
+
| 0.2393 | 9.5238 | 50 | 0.2683 | 0.9639 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.41.1
|
70 |
+
- Pytorch 2.3.0+cu121
|
71 |
+
- Datasets 2.19.1
|
72 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_attn_dim": null,
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": false,
|
8 |
+
"apply_spec_augment": true,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2ForSequenceClassification"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.1,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 256,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": false,
|
18 |
+
"conv_dim": [
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512,
|
25 |
+
512
|
26 |
+
],
|
27 |
+
"conv_kernel": [
|
28 |
+
10,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
3,
|
33 |
+
2,
|
34 |
+
2
|
35 |
+
],
|
36 |
+
"conv_stride": [
|
37 |
+
5,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2,
|
43 |
+
2
|
44 |
+
],
|
45 |
+
"ctc_loss_reduction": "sum",
|
46 |
+
"ctc_zero_infinity": false,
|
47 |
+
"diversity_loss_weight": 0.1,
|
48 |
+
"do_stable_layer_norm": false,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"freeze_feat_extract_train": true,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_size": 768,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 3072,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
63 |
+
"mask_channel_length": 10,
|
64 |
+
"mask_channel_min_space": 1,
|
65 |
+
"mask_channel_other": 0.0,
|
66 |
+
"mask_channel_prob": 0.0,
|
67 |
+
"mask_channel_selection": "static",
|
68 |
+
"mask_feature_length": 10,
|
69 |
+
"mask_feature_min_masks": 0,
|
70 |
+
"mask_feature_prob": 0.0,
|
71 |
+
"mask_time_length": 10,
|
72 |
+
"mask_time_min_masks": 2,
|
73 |
+
"mask_time_min_space": 1,
|
74 |
+
"mask_time_other": 0.0,
|
75 |
+
"mask_time_prob": 0.05,
|
76 |
+
"mask_time_selection": "static",
|
77 |
+
"model_type": "wav2vec2",
|
78 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_codevector_groups": 2,
|
83 |
+
"num_codevectors_per_group": 320,
|
84 |
+
"num_conv_pos_embedding_groups": 16,
|
85 |
+
"num_conv_pos_embeddings": 128,
|
86 |
+
"num_feat_extract_layers": 7,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"num_negatives": 100,
|
89 |
+
"output_hidden_size": 768,
|
90 |
+
"pad_token_id": 0,
|
91 |
+
"proj_codevector_dim": 256,
|
92 |
+
"tdnn_dilation": [
|
93 |
+
1,
|
94 |
+
2,
|
95 |
+
3,
|
96 |
+
1,
|
97 |
+
1
|
98 |
+
],
|
99 |
+
"tdnn_dim": [
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
1500
|
105 |
+
],
|
106 |
+
"tdnn_kernel": [
|
107 |
+
5,
|
108 |
+
3,
|
109 |
+
3,
|
110 |
+
1,
|
111 |
+
1
|
112 |
+
],
|
113 |
+
"torch_dtype": "float32",
|
114 |
+
"transformers_version": "4.41.1",
|
115 |
+
"use_weighted_layer_sum": false,
|
116 |
+
"vocab_size": 32,
|
117 |
+
"xvector_output_dim": 512
|
118 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6529fa7d787bb22fd11b4e639764ca9143538d27dc2c714dc359ffcb66906f1
|
3 |
+
size 378302360
|
preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"return_attention_mask": false,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
runs/May26_07-48-33_e7e43b6fa54b/events.out.tfevents.1716709714.e7e43b6fa54b.174.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef16bf392f8a973520a2a73b36b217293bb0c9c1f602a2e16b379a7e15624640
|
3 |
+
size 6545
|
runs/May26_07-48-51_e7e43b6fa54b/events.out.tfevents.1716709732.e7e43b6fa54b.174.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a4838b9804ae38cc15811edeae42c3ff5055c59eb8e71b0f98dacd6c5dc0462
|
3 |
+
size 11098
|
runs/May27_07-58-57_0ce2d95275b8/events.out.tfevents.1716796738.0ce2d95275b8.274.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e0d1bb9991e8c2b293312cef9c44d7ccbb681ab5ce69f2d4ece11309d2cc3ef
|
3 |
+
size 8505
|
runs/May27_21-41-07_f4e57fe9fcf0/events.out.tfevents.1716846068.f4e57fe9fcf0.437.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84872cf3e0f3efc462984964b4928c1c322dab65a2bcf00c0b8aa1e5802c2e3e
|
3 |
+
size 11059
|
runs/May28_02-29-22_d2055eeddde7/events.out.tfevents.1716863363.d2055eeddde7.795.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4c94b8414a3830aa391ccb10f9bc87c90a4e5c04b8be7b28d1d35e89df4201d
|
3 |
+
size 11059
|
runs/May28_03-41-53_41aa79c24ea4/events.out.tfevents.1716867715.41aa79c24ea4.940.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b58712cba28280dec6a53c3d4f56e83ead0e5a7718ba31717bb0878a12cd7ca
|
3 |
+
size 11059
|
runs/May29_00-27-09_b4e3ac6e9b08/events.out.tfevents.1716942430.b4e3ac6e9b08.519.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ced349a6f1605bf1f332098c1d22d2664f164b7e8441cd10b1231cf10b315bb3
|
3 |
+
size 10187
|
runs/May29_00-40-30_b4e3ac6e9b08/events.out.tfevents.1716943230.b4e3ac6e9b08.519.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90b5a95730e3cbe6745352f2a027db59c0ed1bb60e49d17aea6b5810ab45a61e
|
3 |
+
size 7386
|
runs/May30_02-28-44_6970b3dafd8e/events.out.tfevents.1717036128.6970b3dafd8e.297.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:140840b47298e0fdbdda3ae51106d0eef539f0a67e0fdda87dc6bf96b5abcc20
|
3 |
+
size 88
|
runs/May30_02-35-21_f726364025c0/events.out.tfevents.1717036522.f726364025c0.476.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:166ad5aa7a3c30934ff3603df0345908531b92ba973db656a3dc253d6dd2182d
|
3 |
+
size 6823
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b11758508c49a83b7b317c66fcb711e5c8d1b5307c9d119a680318e8993bd5ae
|
3 |
+
size 5112
|