aiface commited on
Commit
d4b1e63
1 Parent(s): 0eabe24

Training in progress, epoch 1, checkpoint

Browse files
checkpoint-729/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mms-1b-all",
3
+ "activation_dropout": 0.05,
4
+ "adapter_attn_dim": 16,
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": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 1024,
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": 0.05,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.0,
58
+ "hidden_size": 1280,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 5120,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
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": 0.05,
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": 48,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1280,
80
+ "pad_token_id": 92,
81
+ "proj_codevector_dim": 1024,
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": "4.34.1",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 95,
107
+ "xvector_output_dim": 512
108
+ }
checkpoint-729/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af4fea956d9183b74cb64b0ba97b974a27b3bc2b4ea28c9465dd7755535510f
3
+ size 18424186
checkpoint-729/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-729/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11ddb2b193ad3d656c349024c4911d8fc719a3953ee8a980083631a800dae06
3
+ size 3859463050
checkpoint-729/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34df90dfc3f2029a76b587ce9924df48dd9eb2f6f72cdeeea8f63aefe9f535ae
3
+ size 14308
checkpoint-729/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31e50c5c870205c924d849149568b3ca13ecb1cb74a85667d361757e0ea99bc
3
+ size 1064
checkpoint-729/trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 729,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14,
13
+ "learning_rate": 0.00048,
14
+ "loss": 7.0366,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.27,
19
+ "learning_rate": 0.0004933240611961058,
20
+ "loss": 0.4467,
21
+ "step": 200
22
+ },
23
+ {
24
+ "epoch": 0.41,
25
+ "learning_rate": 0.00048643949930458967,
26
+ "loss": 0.3946,
27
+ "step": 300
28
+ },
29
+ {
30
+ "epoch": 0.55,
31
+ "learning_rate": 0.0004794853963838665,
32
+ "loss": 0.399,
33
+ "step": 400
34
+ },
35
+ {
36
+ "epoch": 0.69,
37
+ "learning_rate": 0.0004726008344923505,
38
+ "loss": 0.3696,
39
+ "step": 500
40
+ },
41
+ {
42
+ "epoch": 0.69,
43
+ "eval_loss": 0.3043254017829895,
44
+ "eval_runtime": 65.1553,
45
+ "eval_samples_per_second": 11.664,
46
+ "eval_steps_per_second": 1.458,
47
+ "eval_wer": 0.265993265993266,
48
+ "step": 500
49
+ },
50
+ {
51
+ "epoch": 0.82,
52
+ "learning_rate": 0.0004656467315716273,
53
+ "loss": 0.3677,
54
+ "step": 600
55
+ },
56
+ {
57
+ "epoch": 0.96,
58
+ "learning_rate": 0.00045869262865090403,
59
+ "loss": 0.3534,
60
+ "step": 700
61
+ }
62
+ ],
63
+ "logging_steps": 100,
64
+ "max_steps": 7290,
65
+ "num_train_epochs": 10,
66
+ "save_steps": 500,
67
+ "total_flos": 5.050015040194851e+18,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
checkpoint-729/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d3aa848da266dd9fcefac1319c4009241b1015d8306bc1c8253b19be17b56d9
3
+ size 4536