mattchurgin
commited on
Commit
•
7d63985
1
Parent(s):
711df8a
Training in progress, step 5
Browse files- all_results.json +8 -0
- config.json +15 -20
- pytorch_model.bin +2 -2
- run.sh +1 -1
- special_tokens_map.json +1 -1
- train_results.json +8 -0
- trainer_state.json +25 -0
- training_args.bin +1 -1
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.03,
|
3 |
+
"train_loss": 94.465576171875,
|
4 |
+
"train_runtime": 12.1749,
|
5 |
+
"train_samples": 704,
|
6 |
+
"train_samples_per_second": 1.643,
|
7 |
+
"train_steps_per_second": 0.821
|
8 |
+
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
@@ -15,19 +15,16 @@
|
|
15 |
"contrastive_logits_temperature": 0.1,
|
16 |
"conv_bias": false,
|
17 |
"conv_dim": [
|
18 |
-
|
19 |
-
|
20 |
-
32
|
21 |
],
|
22 |
"conv_kernel": [
|
23 |
-
|
24 |
-
|
25 |
-
8
|
26 |
],
|
27 |
"conv_stride": [
|
28 |
-
|
29 |
-
|
30 |
-
4
|
31 |
],
|
32 |
"ctc_loss_reduction": "mean",
|
33 |
"ctc_zero_infinity": false,
|
@@ -35,17 +32,15 @@
|
|
35 |
"do_stable_layer_norm": true,
|
36 |
"eos_token_id": 2,
|
37 |
"feat_extract_activation": "gelu",
|
38 |
-
"feat_extract_dropout": 0.0,
|
39 |
"feat_extract_norm": "layer",
|
40 |
"feat_proj_dropout": 0.0,
|
41 |
"feat_quantizer_dropout": 0.0,
|
42 |
"final_dropout": 0.0,
|
43 |
"hidden_act": "gelu",
|
44 |
"hidden_dropout": 0.0,
|
45 |
-
"
|
46 |
-
"hidden_size": 16,
|
47 |
"initializer_range": 0.02,
|
48 |
-
"intermediate_size":
|
49 |
"layer_norm_eps": 1e-05,
|
50 |
"layerdrop": 0.0,
|
51 |
"mask_feature_length": 10,
|
@@ -59,12 +54,12 @@
|
|
59 |
"num_attention_heads": 2,
|
60 |
"num_codevector_groups": 2,
|
61 |
"num_codevectors_per_group": 320,
|
62 |
-
"num_conv_pos_embedding_groups":
|
63 |
-
"num_conv_pos_embeddings":
|
64 |
-
"num_feat_extract_layers":
|
65 |
-
"num_hidden_layers":
|
66 |
-
"num_negatives":
|
67 |
-
"output_hidden_size":
|
68 |
"pad_token_id": 50,
|
69 |
"proj_codevector_dim": 256,
|
70 |
"tdnn_dilation": [
|
1 |
{
|
2 |
+
"_name_or_path": "patrickvonplaten/wav2vec2_tiny_random_robust",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
15 |
"contrastive_logits_temperature": 0.1,
|
16 |
"conv_bias": false,
|
17 |
"conv_dim": [
|
18 |
+
64,
|
19 |
+
64
|
|
|
20 |
],
|
21 |
"conv_kernel": [
|
22 |
+
40,
|
23 |
+
40
|
|
|
24 |
],
|
25 |
"conv_stride": [
|
26 |
+
30,
|
27 |
+
30
|
|
|
28 |
],
|
29 |
"ctc_loss_reduction": "mean",
|
30 |
"ctc_zero_infinity": false,
|
32 |
"do_stable_layer_norm": true,
|
33 |
"eos_token_id": 2,
|
34 |
"feat_extract_activation": "gelu",
|
|
|
35 |
"feat_extract_norm": "layer",
|
36 |
"feat_proj_dropout": 0.0,
|
37 |
"feat_quantizer_dropout": 0.0,
|
38 |
"final_dropout": 0.0,
|
39 |
"hidden_act": "gelu",
|
40 |
"hidden_dropout": 0.0,
|
41 |
+
"hidden_size": 64,
|
|
|
42 |
"initializer_range": 0.02,
|
43 |
+
"intermediate_size": 128,
|
44 |
"layer_norm_eps": 1e-05,
|
45 |
"layerdrop": 0.0,
|
46 |
"mask_feature_length": 10,
|
54 |
"num_attention_heads": 2,
|
55 |
"num_codevector_groups": 2,
|
56 |
"num_codevectors_per_group": 320,
|
57 |
+
"num_conv_pos_embedding_groups": 4,
|
58 |
+
"num_conv_pos_embeddings": 64,
|
59 |
+
"num_feat_extract_layers": 2,
|
60 |
+
"num_hidden_layers": 2,
|
61 |
+
"num_negatives": 100,
|
62 |
+
"output_hidden_size": 64,
|
63 |
"pad_token_id": 50,
|
64 |
"proj_codevector_dim": 256,
|
65 |
"tdnn_dilation": [
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7a2903d916d51d415eeac7b97c1af82cb6941d2ec5390d1f34259b064120421
|
3 |
+
size 1247823
|
run.sh
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
python run_speech_recognition_ctc.py \
|
2 |
--dataset_name="mozilla-foundation/common_voice_7_0" \
|
3 |
-
--model_name_or_path="
|
4 |
--dataset_config_name="ab" \
|
5 |
--output_dir="./" \
|
6 |
--overwrite_output_dir \
|
1 |
python run_speech_recognition_ctc.py \
|
2 |
--dataset_name="mozilla-foundation/common_voice_7_0" \
|
3 |
+
--model_name_or_path="patrickvonplaten/wav2vec2_tiny_random_robust" \
|
4 |
--dataset_config_name="ab" \
|
5 |
--output_dir="./" \
|
6 |
--overwrite_output_dir \
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.03,
|
3 |
+
"train_loss": 94.465576171875,
|
4 |
+
"train_runtime": 12.1749,
|
5 |
+
"train_samples": 704,
|
6 |
+
"train_samples_per_second": 1.643,
|
7 |
+
"train_steps_per_second": 0.821
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.028409090909090908,
|
5 |
+
"global_step": 10,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"step": 10,
|
13 |
+
"total_flos": 508182128640.0,
|
14 |
+
"train_loss": 94.465576171875,
|
15 |
+
"train_runtime": 12.1749,
|
16 |
+
"train_samples_per_second": 1.643,
|
17 |
+
"train_steps_per_second": 0.821
|
18 |
+
}
|
19 |
+
],
|
20 |
+
"max_steps": 10,
|
21 |
+
"num_train_epochs": 1,
|
22 |
+
"total_flos": 508182128640.0,
|
23 |
+
"trial_name": null,
|
24 |
+
"trial_params": null
|
25 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2991
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98c0ec628eb5b67c35784454f7e2b25d6572700b45737cf330ddf9ce21d18f23
|
3 |
size 2991
|