Hugging Face's logo

foxxy-hm
/
wav2vec2-base-finetune-vi

Automatic Speech Recognition
Transformers
PyTorch
Vietnamese
wav2vec2
audio
Inference Endpoints
Model card Files Community
1
foxxy-hm commited on
Commit
6c08f73
·
1 Parent(s): 277ae2b

Upload 18 files

Browse files
Files changed (18) hide show
  1. checkpoint-5000/config.json +108 -0
  2. checkpoint-5000/optimizer.pt +3 -0
  3. checkpoint-5000/preprocessor_config.json +9 -0
  4. checkpoint-5000/pytorch_model.bin +3 -0
  5. checkpoint-5000/rng_state.pth +3 -0
  6. checkpoint-5000/scaler.pt +3 -0
  7. checkpoint-5000/scheduler.pt +3 -0
  8. checkpoint-5000/trainer_state.json +166 -0
  9. checkpoint-5000/training_args.bin +3 -0
  10. checkpoint-5500/config.json +108 -0
  11. checkpoint-5500/optimizer.pt +3 -0
  12. checkpoint-5500/preprocessor_config.json +9 -0
  13. checkpoint-5500/pytorch_model.bin +3 -0
  14. checkpoint-5500/rng_state.pth +3 -0
  15. checkpoint-5500/scaler.pt +3 -0
  16. checkpoint-5500/scheduler.pt +3 -0
  17. checkpoint-5500/trainer_state.json +181 -0
  18. checkpoint-5500/training_args.bin +3 -0
checkpoint-5000/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h",
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": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
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": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_dropout_prob": 0.1,
58
+ "hidden_size": 768,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 3072,
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": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 12,
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": 12,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 768,
80
+ "pad_token_id": 109,
81
+ "proj_codevector_dim": 256,
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": "4.20.0",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 110,
107
+ "xvector_output_dim": 512
108
+ }
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab61a3ea59b0477d6157c5e36bd4b35b009623ffc8a6e3970cf68ac71835ba8
3
+ size 722166405
checkpoint-5000/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": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-5000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6416c9220620122566fbcaa34f9297a3c0e0893728cbe8aff75ecc725cba0962
3
+ size 377898657
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9289719fe6aa89c43eed5a0c5e1788f88e24188a9e80ecc8f2549914393286db
3
+ size 14639
checkpoint-5000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c0dce48d9ccf7788e0ef646b9c8cf20b95ce1eca7ffe98d50c1b7c3f95d77f
3
+ size 557
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5db4db3085ce59d670b78bcb8124e1a0fa73c1d33e29a3507004c094fd177e7f
3
+ size 627
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.3377837116154874,
5
+ "global_step": 5000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.33,
12
+ "learning_rate": 4.9800000000000004e-05,
13
+ "loss": 1.0211,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.33,
18
+ "eval_loss": 0.5140587091445923,
19
+ "eval_runtime": 112.0215,
20
+ "eval_samples_per_second": 13.372,
21
+ "eval_steps_per_second": 1.678,
22
+ "eval_wer": 0.32459210916641945,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 0.67,
27
+ "learning_rate": 9.98e-05,
28
+ "loss": 0.7098,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 0.67,
33
+ "eval_loss": 0.41307497024536133,
34
+ "eval_runtime": 114.0249,
35
+ "eval_samples_per_second": 13.137,
36
+ "eval_steps_per_second": 1.649,
37
+ "eval_wer": 0.2981311183625037,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "learning_rate": 9.002403846153846e-05,
43
+ "loss": 0.6115,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_loss": 0.37654194235801697,
49
+ "eval_runtime": 115.4275,
50
+ "eval_samples_per_second": 12.978,
51
+ "eval_steps_per_second": 1.629,
52
+ "eval_wer": 0.2660338178582023,
53
+ "step": 1500
54
+ },
55
+ {
56
+ "epoch": 1.34,
57
+ "learning_rate": 8.000801282051282e-05,
58
+ "loss": 0.5112,
59
+ "step": 2000
60
+ },
61
+ {
62
+ "epoch": 1.34,
63
+ "eval_loss": 0.3202863931655884,
64
+ "eval_runtime": 113.0512,
65
+ "eval_samples_per_second": 13.251,
66
+ "eval_steps_per_second": 1.663,
67
+ "eval_wer": 0.24526846633046573,
68
+ "step": 2000
69
+ },
70
+ {
71
+ "epoch": 1.67,
72
+ "learning_rate": 7.001201923076923e-05,
73
+ "loss": 0.4763,
74
+ "step": 2500
75
+ },
76
+ {
77
+ "epoch": 1.67,
78
+ "eval_loss": 0.29251885414123535,
79
+ "eval_runtime": 113.4478,
80
+ "eval_samples_per_second": 13.204,
81
+ "eval_steps_per_second": 1.657,
82
+ "eval_wer": 0.23500444971818452,
83
+ "step": 2500
84
+ },
85
+ {
86
+ "epoch": 2.0,
87
+ "learning_rate": 5.999599358974359e-05,
88
+ "loss": 0.4386,
89
+ "step": 3000
90
+ },
91
+ {
92
+ "epoch": 2.0,
93
+ "eval_loss": 0.2935383915901184,
94
+ "eval_runtime": 112.4069,
95
+ "eval_samples_per_second": 13.327,
96
+ "eval_steps_per_second": 1.672,
97
+ "eval_wer": 0.22284188668051022,
98
+ "step": 3000
99
+ },
100
+ {
101
+ "epoch": 2.34,
102
+ "learning_rate": 4.997996794871795e-05,
103
+ "loss": 0.3802,
104
+ "step": 3500
105
+ },
106
+ {
107
+ "epoch": 2.34,
108
+ "eval_loss": 0.2789919078350067,
109
+ "eval_runtime": 111.4408,
110
+ "eval_samples_per_second": 13.442,
111
+ "eval_steps_per_second": 1.687,
112
+ "eval_wer": 0.21388312073568674,
113
+ "step": 3500
114
+ },
115
+ {
116
+ "epoch": 2.67,
117
+ "learning_rate": 3.998397435897436e-05,
118
+ "loss": 0.3727,
119
+ "step": 4000
120
+ },
121
+ {
122
+ "epoch": 2.67,
123
+ "eval_loss": 0.26136162877082825,
124
+ "eval_runtime": 111.228,
125
+ "eval_samples_per_second": 13.468,
126
+ "eval_steps_per_second": 1.69,
127
+ "eval_wer": 0.21050133491545536,
128
+ "step": 4000
129
+ },
130
+ {
131
+ "epoch": 3.0,
132
+ "learning_rate": 2.9967948717948717e-05,
133
+ "loss": 0.3747,
134
+ "step": 4500
135
+ },
136
+ {
137
+ "epoch": 3.0,
138
+ "eval_loss": 0.24868248403072357,
139
+ "eval_runtime": 112.653,
140
+ "eval_samples_per_second": 13.297,
141
+ "eval_steps_per_second": 1.669,
142
+ "eval_wer": 0.20539899139721152,
143
+ "step": 4500
144
+ },
145
+ {
146
+ "epoch": 3.34,
147
+ "learning_rate": 1.9951923076923078e-05,
148
+ "loss": 0.3192,
149
+ "step": 5000
150
+ },
151
+ {
152
+ "epoch": 3.34,
153
+ "eval_loss": 0.2479962557554245,
154
+ "eval_runtime": 117.7279,
155
+ "eval_samples_per_second": 12.724,
156
+ "eval_steps_per_second": 1.597,
157
+ "eval_wer": 0.20166122812221893,
158
+ "step": 5000
159
+ }
160
+ ],
161
+ "max_steps": 5992,
162
+ "num_train_epochs": 4,
163
+ "total_flos": 1.2902768061426483e+18,
164
+ "trial_name": null,
165
+ "trial_params": null
166
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc6476f18e70f806c108d7c1e7515c1712aeba84566834c0c576bb35f1bd321
3
+ size 3323
checkpoint-5500/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h",
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": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
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": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_dropout_prob": 0.1,
58
+ "hidden_size": 768,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 3072,
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": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 12,
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": 12,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 768,
80
+ "pad_token_id": 109,
81
+ "proj_codevector_dim": 256,
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": "4.20.0",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 110,
107
+ "xvector_output_dim": 512
108
+ }
checkpoint-5500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7b1649037408d7555e48dd7a38b066ca7a7d0e18cf0fe1122f552518d36080
3
+ size 722166405
checkpoint-5500/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": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-5500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03398881073b70b1f797a6ced8f2fd6befa31a9c40027031d8ae9e93f8a856fa
3
+ size 377898657
checkpoint-5500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0768686ec19ae0847e16bf663f06a4e063a9f43cb22ae48878bf1765cf467121
3
+ size 14639
checkpoint-5500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64317940bdef3bf2f71d94b0d5bcbf9f5d73db0bee2e5813533e8952d8f9bda
3
+ size 557
checkpoint-5500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7a4123b7778069a040345365fa3eb30cd916ad62b115635d7e49f6d53ae9ac
3
+ size 627
checkpoint-5500/trainer_state.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.671562082777036,
5
+ "global_step": 5500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.33,
12
+ "learning_rate": 4.9800000000000004e-05,
13
+ "loss": 1.0211,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.33,
18
+ "eval_loss": 0.5140587091445923,
19
+ "eval_runtime": 112.0215,
20
+ "eval_samples_per_second": 13.372,
21
+ "eval_steps_per_second": 1.678,
22
+ "eval_wer": 0.32459210916641945,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 0.67,
27
+ "learning_rate": 9.98e-05,
28
+ "loss": 0.7098,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 0.67,
33
+ "eval_loss": 0.41307497024536133,
34
+ "eval_runtime": 114.0249,
35
+ "eval_samples_per_second": 13.137,
36
+ "eval_steps_per_second": 1.649,
37
+ "eval_wer": 0.2981311183625037,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "learning_rate": 9.002403846153846e-05,
43
+ "loss": 0.6115,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_loss": 0.37654194235801697,
49
+ "eval_runtime": 115.4275,
50
+ "eval_samples_per_second": 12.978,
51
+ "eval_steps_per_second": 1.629,
52
+ "eval_wer": 0.2660338178582023,
53
+ "step": 1500
54
+ },
55
+ {
56
+ "epoch": 1.34,
57
+ "learning_rate": 8.000801282051282e-05,
58
+ "loss": 0.5112,
59
+ "step": 2000
60
+ },
61
+ {
62
+ "epoch": 1.34,
63
+ "eval_loss": 0.3202863931655884,
64
+ "eval_runtime": 113.0512,
65
+ "eval_samples_per_second": 13.251,
66
+ "eval_steps_per_second": 1.663,
67
+ "eval_wer": 0.24526846633046573,
68
+ "step": 2000
69
+ },
70
+ {
71
+ "epoch": 1.67,
72
+ "learning_rate": 7.001201923076923e-05,
73
+ "loss": 0.4763,
74
+ "step": 2500
75
+ },
76
+ {
77
+ "epoch": 1.67,
78
+ "eval_loss": 0.29251885414123535,
79
+ "eval_runtime": 113.4478,
80
+ "eval_samples_per_second": 13.204,
81
+ "eval_steps_per_second": 1.657,
82
+ "eval_wer": 0.23500444971818452,
83
+ "step": 2500
84
+ },
85
+ {
86
+ "epoch": 2.0,
87
+ "learning_rate": 5.999599358974359e-05,
88
+ "loss": 0.4386,
89
+ "step": 3000
90
+ },
91
+ {
92
+ "epoch": 2.0,
93
+ "eval_loss": 0.2935383915901184,
94
+ "eval_runtime": 112.4069,
95
+ "eval_samples_per_second": 13.327,
96
+ "eval_steps_per_second": 1.672,
97
+ "eval_wer": 0.22284188668051022,
98
+ "step": 3000
99
+ },
100
+ {
101
+ "epoch": 2.34,
102
+ "learning_rate": 4.997996794871795e-05,
103
+ "loss": 0.3802,
104
+ "step": 3500
105
+ },
106
+ {
107
+ "epoch": 2.34,
108
+ "eval_loss": 0.2789919078350067,
109
+ "eval_runtime": 111.4408,
110
+ "eval_samples_per_second": 13.442,
111
+ "eval_steps_per_second": 1.687,
112
+ "eval_wer": 0.21388312073568674,
113
+ "step": 3500
114
+ },
115
+ {
116
+ "epoch": 2.67,
117
+ "learning_rate": 3.998397435897436e-05,
118
+ "loss": 0.3727,
119
+ "step": 4000
120
+ },
121
+ {
122
+ "epoch": 2.67,
123
+ "eval_loss": 0.26136162877082825,
124
+ "eval_runtime": 111.228,
125
+ "eval_samples_per_second": 13.468,
126
+ "eval_steps_per_second": 1.69,
127
+ "eval_wer": 0.21050133491545536,
128
+ "step": 4000
129
+ },
130
+ {
131
+ "epoch": 3.0,
132
+ "learning_rate": 2.9967948717948717e-05,
133
+ "loss": 0.3747,
134
+ "step": 4500
135
+ },
136
+ {
137
+ "epoch": 3.0,
138
+ "eval_loss": 0.24868248403072357,
139
+ "eval_runtime": 112.653,
140
+ "eval_samples_per_second": 13.297,
141
+ "eval_steps_per_second": 1.669,
142
+ "eval_wer": 0.20539899139721152,
143
+ "step": 4500
144
+ },
145
+ {
146
+ "epoch": 3.34,
147
+ "learning_rate": 1.9951923076923078e-05,
148
+ "loss": 0.3192,
149
+ "step": 5000
150
+ },
151
+ {
152
+ "epoch": 3.34,
153
+ "eval_loss": 0.2479962557554245,
154
+ "eval_runtime": 117.7279,
155
+ "eval_samples_per_second": 12.724,
156
+ "eval_steps_per_second": 1.597,
157
+ "eval_wer": 0.20166122812221893,
158
+ "step": 5000
159
+ },
160
+ {
161
+ "epoch": 3.67,
162
+ "learning_rate": 9.935897435897435e-06,
163
+ "loss": 0.2852,
164
+ "step": 5500
165
+ },
166
+ {
167
+ "epoch": 3.67,
168
+ "eval_loss": 0.24946188926696777,
169
+ "eval_runtime": 116.0708,
170
+ "eval_samples_per_second": 12.906,
171
+ "eval_steps_per_second": 1.62,
172
+ "eval_wer": 0.20005932957579353,
173
+ "step": 5500
174
+ }
175
+ ],
176
+ "max_steps": 5992,
177
+ "num_train_epochs": 4,
178
+ "total_flos": 1.4196823993181012e+18,
179
+ "trial_name": null,
180
+ "trial_params": null
181
+ }
checkpoint-5500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc6476f18e70f806c108d7c1e7515c1712aeba84566834c0c576bb35f1bd321
3
+ size 3323