Hugging Face's logo

Amiran13
/
wav2vec2-large-xlsr-georgian_v1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Amiran13 commited on
Commit
75ca3f3
·
1 Parent(s): ed3f466

Training in progress, step 200, checkpoint

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. checkpoint-200/config.json +117 -0
  3. checkpoint-200/model.safetensors +3 -0
  4. checkpoint-200/optimizer.pt +3 -0
  5. checkpoint-200/preprocessor_config.json +9 -0
  6. checkpoint-200/rng_state.pth +0 -0
  7. checkpoint-200/scheduler.pt +0 -0
  8. checkpoint-200/trainer_state.json +157 -0
  9. checkpoint-200/training_args.bin +0 -0
.gitattributes CHANGED
@@ -1 +1,2 @@
1
  model.safetensors filter=lfs diff=lfs merge=lfs -text
 
 
1
  model.safetensors filter=lfs diff=lfs merge=lfs -text
2
+ checkpoint-200/optimizer.pt filter=lfs diff=lfs merge=lfs -text
checkpoint-200/config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
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
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
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": "mean",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.1,
64
+ "mask_channel_length": 10,
65
+ "mask_channel_min_space": 1,
66
+ "mask_channel_other": 0.0,
67
+ "mask_channel_prob": 0.0,
68
+ "mask_channel_selection": "static",
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.05,
77
+ "mask_time_selection": "static",
78
+ "model_type": "wav2vec2",
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 16,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 24,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 1024,
89
+ "pad_token_id": 38,
90
+ "proj_codevector_dim": 768,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.35.2",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 41,
116
+ "xvector_output_dim": 512
117
+ }
checkpoint-200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7862609cd101ef38fb0fab144c32cd9ff84b530eedf61513e0fec3ca427054b1
3
+ size 1261975580
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a60b8d80cb2c4c1d3dd3cc278a5afde567a750f0ffef46daab3978560fdb21a
3
+ size 2490495926
checkpoint-200/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": true,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-200/rng_state.pth ADDED
Binary file (14.3 kB). View file
 
checkpoint-200/scheduler.pt ADDED
Binary file (1.06 kB). View file
 
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.32546786004882017,
5
+ "eval_steps": 100,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 1.4999999999999999e-05,
14
+ "loss": 11.8163,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 2.8499999999999998e-05,
20
+ "loss": 11.8929,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.05,
25
+ "learning_rate": 4.3499999999999993e-05,
26
+ "loss": 12.0064,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.07,
31
+ "learning_rate": 5.6999999999999996e-05,
32
+ "loss": 10.5132,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.08,
37
+ "learning_rate": 7.199999999999999e-05,
38
+ "loss": 7.9699,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.1,
43
+ "learning_rate": 8.699999999999999e-05,
44
+ "loss": 4.7703,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.11,
49
+ "learning_rate": 0.000102,
50
+ "loss": 3.7982,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.13,
55
+ "learning_rate": 0.000117,
56
+ "loss": 3.436,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.15,
61
+ "learning_rate": 0.00013199999999999998,
62
+ "loss": 3.2573,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.16,
67
+ "learning_rate": 0.000147,
68
+ "loss": 3.1412,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.16,
73
+ "eval_loss": 3.0855324268341064,
74
+ "eval_runtime": 1038.5545,
75
+ "eval_samples_per_second": 11.178,
76
+ "eval_steps_per_second": 0.699,
77
+ "eval_wer": 1.0,
78
+ "step": 100
79
+ },
80
+ {
81
+ "epoch": 0.18,
82
+ "learning_rate": 0.000162,
83
+ "loss": 3.0577,
84
+ "step": 110
85
+ },
86
+ {
87
+ "epoch": 0.2,
88
+ "learning_rate": 0.00017699999999999997,
89
+ "loss": 3.0443,
90
+ "step": 120
91
+ },
92
+ {
93
+ "epoch": 0.21,
94
+ "learning_rate": 0.00019199999999999998,
95
+ "loss": 3.0597,
96
+ "step": 130
97
+ },
98
+ {
99
+ "epoch": 0.23,
100
+ "learning_rate": 0.00020699999999999996,
101
+ "loss": 3.061,
102
+ "step": 140
103
+ },
104
+ {
105
+ "epoch": 0.24,
106
+ "learning_rate": 0.00022199999999999998,
107
+ "loss": 3.0717,
108
+ "step": 150
109
+ },
110
+ {
111
+ "epoch": 0.26,
112
+ "learning_rate": 0.000237,
113
+ "loss": 3.0299,
114
+ "step": 160
115
+ },
116
+ {
117
+ "epoch": 0.28,
118
+ "learning_rate": 0.00025199999999999995,
119
+ "loss": 3.0295,
120
+ "step": 170
121
+ },
122
+ {
123
+ "epoch": 0.29,
124
+ "learning_rate": 0.000267,
125
+ "loss": 3.0423,
126
+ "step": 180
127
+ },
128
+ {
129
+ "epoch": 0.31,
130
+ "learning_rate": 0.00028199999999999997,
131
+ "loss": 3.0437,
132
+ "step": 190
133
+ },
134
+ {
135
+ "epoch": 0.33,
136
+ "learning_rate": 0.00029699999999999996,
137
+ "loss": 3.0569,
138
+ "step": 200
139
+ },
140
+ {
141
+ "epoch": 0.33,
142
+ "eval_loss": 3.036912679672241,
143
+ "eval_runtime": 1030.0275,
144
+ "eval_samples_per_second": 11.271,
145
+ "eval_steps_per_second": 0.705,
146
+ "eval_wer": 1.0,
147
+ "step": 200
148
+ }
149
+ ],
150
+ "logging_steps": 10,
151
+ "max_steps": 9210,
152
+ "num_train_epochs": 15,
153
+ "save_steps": 200,
154
+ "total_flos": 2.0964781566643507e+18,
155
+ "trial_name": null,
156
+ "trial_params": null
157
+ }
checkpoint-200/training_args.bin ADDED
Binary file (4.6 kB). View file