End of training
Browse files- last-checkpoint/config.json +0 -108
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/preprocessor_config.json +0 -10
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scaler.pt +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/trainer_state.json +0 -31
- last-checkpoint/training_args.bin +0 -3
- pytorch_model.bin +1 -1
- runs/Oct22_12-20-14_035cd7a4c2da/events.out.tfevents.1666441655.035cd7a4c2da.486.0 +2 -2
last-checkpoint/config.json
DELETED
@@ -1,108 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
3 |
-
"activation_dropout": 0.0,
|
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": 0.1,
|
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 |
-
"gradient_checkpointing": false,
|
56 |
-
"hidden_act": "gelu",
|
57 |
-
"hidden_dropout": 0.1,
|
58 |
-
"hidden_size": 1024,
|
59 |
-
"initializer_range": 0.02,
|
60 |
-
"intermediate_size": 4096,
|
61 |
-
"layer_norm_eps": 1e-05,
|
62 |
-
"layerdrop": 0.1,
|
63 |
-
"mask_feature_length": 10,
|
64 |
-
"mask_feature_min_masks": 0,
|
65 |
-
"mask_feature_prob": 0.0,
|
66 |
-
"mask_time_length": 10,
|
67 |
-
"mask_time_min_masks": 2,
|
68 |
-
"mask_time_prob": 0.075,
|
69 |
-
"model_type": "wav2vec2",
|
70 |
-
"num_adapter_layers": 3,
|
71 |
-
"num_attention_heads": 16,
|
72 |
-
"num_codevector_groups": 2,
|
73 |
-
"num_codevectors_per_group": 320,
|
74 |
-
"num_conv_pos_embedding_groups": 16,
|
75 |
-
"num_conv_pos_embeddings": 128,
|
76 |
-
"num_feat_extract_layers": 7,
|
77 |
-
"num_hidden_layers": 24,
|
78 |
-
"num_negatives": 100,
|
79 |
-
"output_hidden_size": 1024,
|
80 |
-
"pad_token_id": 0,
|
81 |
-
"proj_codevector_dim": 768,
|
82 |
-
"tdnn_dilation": [
|
83 |
-
1,
|
84 |
-
2,
|
85 |
-
3,
|
86 |
-
1,
|
87 |
-
1
|
88 |
-
],
|
89 |
-
"tdnn_dim": [
|
90 |
-
512,
|
91 |
-
512,
|
92 |
-
512,
|
93 |
-
512,
|
94 |
-
1500
|
95 |
-
],
|
96 |
-
"tdnn_kernel": [
|
97 |
-
5,
|
98 |
-
3,
|
99 |
-
3,
|
100 |
-
1,
|
101 |
-
1
|
102 |
-
],
|
103 |
-
"torch_dtype": "float32",
|
104 |
-
"transformers_version": "4.23.1",
|
105 |
-
"use_weighted_layer_sum": false,
|
106 |
-
"vocab_size": 81,
|
107 |
-
"xvector_output_dim": 512
|
108 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7b0522b0db4fcdbe547845a39567fb1eb91bd812e22c311fa2309662c26f06d4
|
3 |
-
size 2490723217
|
|
|
|
|
|
|
|
last-checkpoint/preprocessor_config.json
DELETED
@@ -1,10 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"do_normalize": true,
|
3 |
-
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
-
"feature_size": 1,
|
5 |
-
"padding_side": "right",
|
6 |
-
"padding_value": 0.0,
|
7 |
-
"processor_class": "Wav2Vec2Processor",
|
8 |
-
"return_attention_mask": true,
|
9 |
-
"sampling_rate": 16000
|
10 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:fc289ff52aec542e06466fad3d90b829626572193d568b236ee7c72d2f2b396d
|
3 |
-
size 1262230833
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:97f10cef73b77ccf50acfc9fdfcce4d825ac4879ba8ea90837642cbc5bdaf4f7
|
3 |
-
size 14567
|
|
|
|
|
|
|
|
last-checkpoint/scaler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:9369836f62ac3d234b0a55fd53d2bec38ea9d1165256455adc8f64c291c08280
|
3 |
-
size 559
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:f81e2caa92e2eca52c3d6b2adc455e637e8ec990dad88a3c7972b41ec2c96422
|
3 |
-
size 623
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
@@ -1,31 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.20917767028369721,
|
5 |
-
"global_step": 800,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.21,
|
12 |
-
"learning_rate": 0.0002976391096979332,
|
13 |
-
"loss": 6.4525,
|
14 |
-
"step": 800
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.21,
|
18 |
-
"eval_loss": 1.4264159202575684,
|
19 |
-
"eval_runtime": 579.6055,
|
20 |
-
"eval_samples_per_second": 37.262,
|
21 |
-
"eval_steps_per_second": 4.658,
|
22 |
-
"eval_wer": 0.9522086267891338,
|
23 |
-
"step": 800
|
24 |
-
}
|
25 |
-
],
|
26 |
-
"max_steps": 38240,
|
27 |
-
"num_train_epochs": 10,
|
28 |
-
"total_flos": 2.536758481694976e+18,
|
29 |
-
"trial_name": null,
|
30 |
-
"trial_params": null
|
31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:4033fcd8e67dce330e711cf22738b88ae3860329ea7760913077a6254b5968c9
|
3 |
-
size 3439
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262230833
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a271053de3a37133ae2bddd8c864ad394c671314aa068e85534203254810174
|
3 |
size 1262230833
|
runs/Oct22_12-20-14_035cd7a4c2da/events.out.tfevents.1666441655.035cd7a4c2da.486.0
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 sha256:388ad5fb67bcba7556b4ee122536f9d74ceac74b9f3158b22ca61457d97f7394
|
3 |
+
size 7599
|