Commit
β’
36a9cd0
1
Parent(s):
c7f63cd
Training in progress, step 50
Browse files- .ipynb_checkpoints/run-checkpoint.sh +5 -5
- checkpoint-50/config.json +107 -0
- checkpoint-50/optimizer.pt +3 -0
- checkpoint-50/preprocessor_config.json +9 -0
- checkpoint-50/pytorch_model.bin +3 -0
- checkpoint-50/rng_state.pth +3 -0
- checkpoint-50/scaler.pt +3 -0
- checkpoint-50/scheduler.pt +3 -0
- checkpoint-50/trainer_state.json +55 -0
- checkpoint-50/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- run.sh +5 -5
- special_tokens_map.json +1 -1
- training_args.bin +1 -1
.ipynb_checkpoints/run-checkpoint.sh
CHANGED
@@ -4,19 +4,19 @@ python run_speech_recognition_ctc.py \
|
|
4 |
--dataset_config_name="sv-SE" \
|
5 |
--output_dir="./" \
|
6 |
--overwrite_output_dir \
|
7 |
-
--num_train_epochs="
|
8 |
--per_device_train_batch_size="8" \
|
9 |
--per_device_eval_batch_size="8" \
|
10 |
--gradient_accumulation_steps="4" \
|
11 |
--learning_rate="7.5e-5" \
|
12 |
-
--warmup_steps="
|
13 |
--length_column_name="input_length" \
|
14 |
--evaluation_strategy="steps" \
|
15 |
--text_column_name="sentence" \
|
16 |
--chars_to_ignore , ? . ! \- \; \: \" β % β β οΏ½ β β β¦ β \
|
17 |
-
--save_steps="
|
18 |
-
--eval_steps="
|
19 |
-
--logging_steps="
|
20 |
--layerdrop="0.0" \
|
21 |
--activation_dropout="0.1" \
|
22 |
--save_total_limit="3" \
|
|
|
4 |
--dataset_config_name="sv-SE" \
|
5 |
--output_dir="./" \
|
6 |
--overwrite_output_dir \
|
7 |
+
--num_train_epochs="2" \
|
8 |
--per_device_train_batch_size="8" \
|
9 |
--per_device_eval_batch_size="8" \
|
10 |
--gradient_accumulation_steps="4" \
|
11 |
--learning_rate="7.5e-5" \
|
12 |
+
--warmup_steps="20" \
|
13 |
--length_column_name="input_length" \
|
14 |
--evaluation_strategy="steps" \
|
15 |
--text_column_name="sentence" \
|
16 |
--chars_to_ignore , ? . ! \- \; \: \" β % β β οΏ½ β β β¦ β \
|
17 |
+
--save_steps="50" \
|
18 |
+
--eval_steps="50" \
|
19 |
+
--logging_steps="10" \
|
20 |
--layerdrop="0.0" \
|
21 |
--activation_dropout="0.1" \
|
22 |
--save_total_limit="3" \
|
checkpoint-50/config.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForCTC"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 768,
|
15 |
+
"contrastive_logits_temperature": 0.1,
|
16 |
+
"conv_bias": true,
|
17 |
+
"conv_dim": [
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512
|
25 |
+
],
|
26 |
+
"conv_kernel": [
|
27 |
+
10,
|
28 |
+
3,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
2,
|
33 |
+
2
|
34 |
+
],
|
35 |
+
"conv_stride": [
|
36 |
+
5,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2
|
43 |
+
],
|
44 |
+
"ctc_loss_reduction": "mean",
|
45 |
+
"ctc_zero_infinity": false,
|
46 |
+
"diversity_loss_weight": 0.1,
|
47 |
+
"do_stable_layer_norm": true,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "layer",
|
52 |
+
"feat_proj_dropout": 0.0,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"hidden_act": "gelu",
|
56 |
+
"hidden_dropout": 0.0,
|
57 |
+
"hidden_size": 1024,
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 4096,
|
60 |
+
"layer_norm_eps": 1e-05,
|
61 |
+
"layerdrop": 0.0,
|
62 |
+
"mask_feature_length": 64,
|
63 |
+
"mask_feature_min_masks": 0,
|
64 |
+
"mask_feature_prob": 0.25,
|
65 |
+
"mask_time_length": 10,
|
66 |
+
"mask_time_min_masks": 2,
|
67 |
+
"mask_time_prob": 0.75,
|
68 |
+
"model_type": "wav2vec2",
|
69 |
+
"num_adapter_layers": 3,
|
70 |
+
"num_attention_heads": 16,
|
71 |
+
"num_codevector_groups": 2,
|
72 |
+
"num_codevectors_per_group": 320,
|
73 |
+
"num_conv_pos_embedding_groups": 16,
|
74 |
+
"num_conv_pos_embeddings": 128,
|
75 |
+
"num_feat_extract_layers": 7,
|
76 |
+
"num_hidden_layers": 24,
|
77 |
+
"num_negatives": 100,
|
78 |
+
"output_hidden_size": 1024,
|
79 |
+
"pad_token_id": 34,
|
80 |
+
"proj_codevector_dim": 768,
|
81 |
+
"tdnn_dilation": [
|
82 |
+
1,
|
83 |
+
2,
|
84 |
+
3,
|
85 |
+
1,
|
86 |
+
1
|
87 |
+
],
|
88 |
+
"tdnn_dim": [
|
89 |
+
512,
|
90 |
+
512,
|
91 |
+
512,
|
92 |
+
512,
|
93 |
+
1500
|
94 |
+
],
|
95 |
+
"tdnn_kernel": [
|
96 |
+
5,
|
97 |
+
3,
|
98 |
+
3,
|
99 |
+
1,
|
100 |
+
1
|
101 |
+
],
|
102 |
+
"torch_dtype": "float32",
|
103 |
+
"transformers_version": "4.16.0.dev0",
|
104 |
+
"use_weighted_layer_sum": false,
|
105 |
+
"vocab_size": 37,
|
106 |
+
"xvector_output_dim": 512
|
107 |
+
}
|
checkpoint-50/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e59c74b41c4b1b3768c9b03acbfe97aeac7e3a7fee68c17a27fc0f6fc4005304
|
3 |
+
size 2490361937
|
checkpoint-50/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,
|
7 |
+
"return_attention_mask": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
checkpoint-50/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dcafa9a58adee9c2dd0c4c04b15f3b1affea9b4fad06e5c8af956a938054769
|
3 |
+
size 1262075377
|
checkpoint-50/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14dd13f385e830f5e013aa12c8f455e60dbd26d2b24429728757725e99609101
|
3 |
+
size 14567
|
checkpoint-50/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58db19cd158cab87b95a3329bd53321ccb26cb15fcfe671116e04cc3c9745427
|
3 |
+
size 559
|
checkpoint-50/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb707a581933f4f3461df9727f0a85dd78930b27f2451939d060d737f2c9f1d2
|
3 |
+
size 623
|
checkpoint-50/trainer_state.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.145032632342277,
|
5 |
+
"global_step": 50,
|
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 |
+
"learning_rate": 3.75e-05,
|
13 |
+
"loss": 12.1562,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.06,
|
18 |
+
"learning_rate": 7.125e-05,
|
19 |
+
"loss": 8.7679,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.09,
|
24 |
+
"learning_rate": 7.398952095808383e-05,
|
25 |
+
"loss": 5.3683,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.12,
|
30 |
+
"learning_rate": 7.286676646706586e-05,
|
31 |
+
"loss": 4.3219,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.15,
|
36 |
+
"learning_rate": 7.17440119760479e-05,
|
37 |
+
"loss": 3.7182,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.15,
|
42 |
+
"eval_loss": 3.836604595184326,
|
43 |
+
"eval_runtime": 133.4846,
|
44 |
+
"eval_samples_per_second": 34.611,
|
45 |
+
"eval_steps_per_second": 4.33,
|
46 |
+
"eval_wer": 1.0,
|
47 |
+
"step": 50
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"max_steps": 688,
|
51 |
+
"num_train_epochs": 2,
|
52 |
+
"total_flos": 1.4741265581374464e+17,
|
53 |
+
"trial_name": null,
|
54 |
+
"trial_params": null
|
55 |
+
}
|
checkpoint-50/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77806a16ec6ef209c8a5c1c085159a0bc8e45c23f2d143f2c13e01527f13b5b2
|
3 |
+
size 2991
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262075377
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dcafa9a58adee9c2dd0c4c04b15f3b1affea9b4fad06e5c8af956a938054769
|
3 |
size 1262075377
|
run.sh
CHANGED
@@ -4,19 +4,19 @@ python run_speech_recognition_ctc.py \
|
|
4 |
--dataset_config_name="sv-SE" \
|
5 |
--output_dir="./" \
|
6 |
--overwrite_output_dir \
|
7 |
-
--num_train_epochs="
|
8 |
--per_device_train_batch_size="8" \
|
9 |
--per_device_eval_batch_size="8" \
|
10 |
--gradient_accumulation_steps="4" \
|
11 |
--learning_rate="7.5e-5" \
|
12 |
-
--warmup_steps="
|
13 |
--length_column_name="input_length" \
|
14 |
--evaluation_strategy="steps" \
|
15 |
--text_column_name="sentence" \
|
16 |
--chars_to_ignore , ? . ! \- \; \: \" β % β β οΏ½ β β β¦ β \
|
17 |
-
--save_steps="
|
18 |
-
--eval_steps="
|
19 |
-
--logging_steps="
|
20 |
--layerdrop="0.0" \
|
21 |
--activation_dropout="0.1" \
|
22 |
--save_total_limit="3" \
|
|
|
4 |
--dataset_config_name="sv-SE" \
|
5 |
--output_dir="./" \
|
6 |
--overwrite_output_dir \
|
7 |
+
--num_train_epochs="2" \
|
8 |
--per_device_train_batch_size="8" \
|
9 |
--per_device_eval_batch_size="8" \
|
10 |
--gradient_accumulation_steps="4" \
|
11 |
--learning_rate="7.5e-5" \
|
12 |
+
--warmup_steps="20" \
|
13 |
--length_column_name="input_length" \
|
14 |
--evaluation_strategy="steps" \
|
15 |
--text_column_name="sentence" \
|
16 |
--chars_to_ignore , ? . ! \- \; \: \" β % β β οΏ½ β β β¦ β \
|
17 |
+
--save_steps="50" \
|
18 |
+
--eval_steps="50" \
|
19 |
+
--logging_steps="10" \
|
20 |
--layerdrop="0.0" \
|
21 |
--activation_dropout="0.1" \
|
22 |
--save_total_limit="3" \
|
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}, {"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}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
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 sha256:77806a16ec6ef209c8a5c1c085159a0bc8e45c23f2d143f2c13e01527f13b5b2
|
3 |
size 2991
|