Hugging Face's logo

oluwagbotty
/
mms_eng_yor

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Community
oluwagbotty commited on
Commit
7dbd02a
·
verified ·
1 Parent(s): 5d32dbd

Training in progress, step 1000, checkpoint

Browse files
Files changed (9) hide show
  1. checkpoint-1000/config.json +107 -0
  2. checkpoint-1000/model.safetensors +3 -0
  3. checkpoint-1000/optimizer.pt +3 -0
  4. checkpoint-1000/preprocessor_config.json +9 -0
  5. checkpoint-1000/rng_state.pth +3 -0
  6. checkpoint-1000/scaler.pt +3 -0
  7. checkpoint-1000/scheduler.pt +3 -0
  8. checkpoint-1000/trainer_state.json +194 -0
  9. checkpoint-1000/training_args.bin +3 -0
checkpoint-1000/config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.05,
3
+ "adapter_attn_dim": 16,
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": 1024,
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": 0.05,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 1280,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 5120,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_feature_length": 10,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.05,
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": 48,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1280,
79
+ "pad_token_id": 65,
80
+ "proj_codevector_dim": 1024,
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": "4.52.0.dev0",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 68,
106
+ "xvector_output_dim": 512
107
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8947115775ecf90d0580d30845d828d7fe7317ca947b3f08a57c6bb62895906d
3
+ size 3859080512
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea301ddf8fcedd1e14f23b4000614e0c197ea8e9607d45aff905af977ce90e47
3
+ size 18147578
checkpoint-1000/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-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc861da1066f5826d2d98a3ff53b361c9edd19d2591deae68f75cccb3b137d4f
3
+ size 14308
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478dbce8758822ae027961670976703b5d60e02bff909fcc8ed53152165c6e30
3
+ size 988
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dee13a83e27cd752b00e7ed425ef420e15855ff105857b1181299eeddae9290
3
+ size 1064
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.433617539585871,
6
+ "eval_steps": 100,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.243605359317905,
14
+ "grad_norm": 33.11063766479492,
15
+ "learning_rate": 4.8844282238442824e-05,
16
+ "loss": 10.7343,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.243605359317905,
21
+ "eval_loss": 4.385446548461914,
22
+ "eval_runtime": 206.0799,
23
+ "eval_samples_per_second": 7.992,
24
+ "eval_steps_per_second": 1.0,
25
+ "eval_wer": 1.0,
26
+ "step": 100
27
+ },
28
+ {
29
+ "epoch": 0.48721071863581,
30
+ "grad_norm": 2.508547067642212,
31
+ "learning_rate": 4.762773722627738e-05,
32
+ "loss": 3.1325,
33
+ "step": 200
34
+ },
35
+ {
36
+ "epoch": 0.48721071863581,
37
+ "eval_loss": 2.1581695079803467,
38
+ "eval_runtime": 206.4525,
39
+ "eval_samples_per_second": 7.978,
40
+ "eval_steps_per_second": 0.998,
41
+ "eval_wer": 0.9690996270644646,
42
+ "step": 200
43
+ },
44
+ {
45
+ "epoch": 0.730816077953715,
46
+ "grad_norm": 1.2504737377166748,
47
+ "learning_rate": 4.641119221411192e-05,
48
+ "loss": 1.6166,
49
+ "step": 300
50
+ },
51
+ {
52
+ "epoch": 0.730816077953715,
53
+ "eval_loss": 1.1347323656082153,
54
+ "eval_runtime": 206.3117,
55
+ "eval_samples_per_second": 7.983,
56
+ "eval_steps_per_second": 0.998,
57
+ "eval_wer": 0.7188184455099745,
58
+ "step": 300
59
+ },
60
+ {
61
+ "epoch": 0.97442143727162,
62
+ "grad_norm": 1.3984403610229492,
63
+ "learning_rate": 4.520681265206813e-05,
64
+ "loss": 1.1808,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.97442143727162,
69
+ "eval_loss": 0.9792075157165527,
70
+ "eval_runtime": 206.2345,
71
+ "eval_samples_per_second": 7.986,
72
+ "eval_steps_per_second": 0.999,
73
+ "eval_wer": 0.6746581424258569,
74
+ "step": 400
75
+ },
76
+ {
77
+ "epoch": 1.2168087697929355,
78
+ "grad_norm": 10.769020080566406,
79
+ "learning_rate": 4.3990267639902676e-05,
80
+ "loss": 1.0459,
81
+ "step": 500
82
+ },
83
+ {
84
+ "epoch": 1.2168087697929355,
85
+ "eval_loss": 0.9049620032310486,
86
+ "eval_runtime": 208.2322,
87
+ "eval_samples_per_second": 7.909,
88
+ "eval_steps_per_second": 0.989,
89
+ "eval_wer": 0.6494405966968567,
90
+ "step": 500
91
+ },
92
+ {
93
+ "epoch": 1.4604141291108403,
94
+ "grad_norm": 0.8941505551338196,
95
+ "learning_rate": 4.277372262773723e-05,
96
+ "loss": 1.0317,
97
+ "step": 600
98
+ },
99
+ {
100
+ "epoch": 1.4604141291108403,
101
+ "eval_loss": 0.8543379306793213,
102
+ "eval_runtime": 205.6459,
103
+ "eval_samples_per_second": 8.009,
104
+ "eval_steps_per_second": 1.002,
105
+ "eval_wer": 0.6338128218788848,
106
+ "step": 600
107
+ },
108
+ {
109
+ "epoch": 1.7040194884287454,
110
+ "grad_norm": 0.9768113493919373,
111
+ "learning_rate": 4.1569343065693435e-05,
112
+ "loss": 0.9836,
113
+ "step": 700
114
+ },
115
+ {
116
+ "epoch": 1.7040194884287454,
117
+ "eval_loss": 0.8191400766372681,
118
+ "eval_runtime": 207.1525,
119
+ "eval_samples_per_second": 7.951,
120
+ "eval_steps_per_second": 0.994,
121
+ "eval_wer": 0.6251701888356124,
122
+ "step": 700
123
+ },
124
+ {
125
+ "epoch": 1.9476248477466505,
126
+ "grad_norm": 0.9090480208396912,
127
+ "learning_rate": 4.035279805352798e-05,
128
+ "loss": 0.9567,
129
+ "step": 800
130
+ },
131
+ {
132
+ "epoch": 1.9476248477466505,
133
+ "eval_loss": 0.7955169081687927,
134
+ "eval_runtime": 206.8205,
135
+ "eval_samples_per_second": 7.963,
136
+ "eval_steps_per_second": 0.996,
137
+ "eval_wer": 0.6124430237376428,
138
+ "step": 800
139
+ },
140
+ {
141
+ "epoch": 2.1900121802679657,
142
+ "grad_norm": 0.6563196778297424,
143
+ "learning_rate": 3.913625304136253e-05,
144
+ "loss": 0.9354,
145
+ "step": 900
146
+ },
147
+ {
148
+ "epoch": 2.1900121802679657,
149
+ "eval_loss": 0.7705180644989014,
150
+ "eval_runtime": 206.4429,
151
+ "eval_samples_per_second": 7.978,
152
+ "eval_steps_per_second": 0.998,
153
+ "eval_wer": 0.6046291363286569,
154
+ "step": 900
155
+ },
156
+ {
157
+ "epoch": 2.433617539585871,
158
+ "grad_norm": 0.8123560547828674,
159
+ "learning_rate": 3.791970802919708e-05,
160
+ "loss": 0.9037,
161
+ "step": 1000
162
+ },
163
+ {
164
+ "epoch": 2.433617539585871,
165
+ "eval_loss": 0.75263512134552,
166
+ "eval_runtime": 206.6571,
167
+ "eval_samples_per_second": 7.97,
168
+ "eval_steps_per_second": 0.997,
169
+ "eval_wer": 0.5982359557213047,
170
+ "step": 1000
171
+ }
172
+ ],
173
+ "logging_steps": 100,
174
+ "max_steps": 4110,
175
+ "num_input_tokens_seen": 0,
176
+ "num_train_epochs": 10,
177
+ "save_steps": 100,
178
+ "stateful_callbacks": {
179
+ "TrainerControl": {
180
+ "args": {
181
+ "should_epoch_stop": false,
182
+ "should_evaluate": false,
183
+ "should_log": false,
184
+ "should_save": true,
185
+ "should_training_stop": false
186
+ },
187
+ "attributes": {}
188
+ }
189
+ },
190
+ "total_flos": 1.4109000983694397e+19,
191
+ "train_batch_size": 16,
192
+ "trial_name": null,
193
+ "trial_params": null
194
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41bd293a9b52d9fe0c62e74d444b5c5eb9f144a78a0b1288422dc9f7980a2243
3
+ size 5240