Hugging Face's logo

hiba2
/
wav2vec2-large-mms-1b-arabic-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Model card Files Metrics Community
hiba2 commited on
Commit
ce20d4f
·
1 Parent(s): 448bcc9

Training in progress, step 200

Browse files
Files changed (12) hide show
  1. model.safetensors +1 -1
  2. runs/Jan05_16-44-24_ee9bb81f5493/events.out.tfevents.1704473295.ee9bb81f5493.329.0 +2 -2
  3. runs/Jan05_17-30-35_ee9bb81f5493/events.out.tfevents.1704475998.ee9bb81f5493.329.1 +3 -0
  4. tmp-checkpoint-1600/config.json +108 -0
  5. tmp-checkpoint-1600/model.safetensors +3 -0
  6. tmp-checkpoint-1600/optimizer.pt +3 -0
  7. tmp-checkpoint-1600/preprocessor_config.json +9 -0
  8. tmp-checkpoint-1600/rng_state.pth +3 -0
  9. tmp-checkpoint-1600/scheduler.pt +3 -0
  10. tmp-checkpoint-1600/trainer_state.json +261 -0
  11. tmp-checkpoint-1600/training_args.bin +3 -0
  12. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2477df08042ad435314391e2757d24ae8f17962d431aca89d9a9036bc76e910
3
  size 3859270100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aebd4663bf1ed82f7f983f30bc9200b4cc5fa334aaad0b6813e6d83e98fb2e32
3
  size 3859270100
runs/Jan05_16-44-24_ee9bb81f5493/events.out.tfevents.1704473295.ee9bb81f5493.329.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acc5c19f2285ca4b891e9040964443cac996f42288f48f1711b20c507c00f78c
3
- size 12451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a928cf01131b453a6999938e72dc950c80f803ef5a765dd82bd554116fc1f2e2
3
+ size 13401
runs/Jan05_17-30-35_ee9bb81f5493/events.out.tfevents.1704475998.ee9bb81f5493.329.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12779d9cb330429f8fc1fe28d045cb2622757924e935cf0a0a1d9595b8e96bc2
3
+ size 6750
tmp-checkpoint-1600/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": true,
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": 102,
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": "4.37.0.dev0",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 105,
107
+ "xvector_output_dim": 512
108
+ }
tmp-checkpoint-1600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e34f9b54fe499326e50d26e45d884f2c7bd6733f87da5097d91155fb68ccad
3
+ size 3859270100
tmp-checkpoint-1600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d71448b32ff9e7c3542069fc93b3327a51f8dceb2206d42208320157a565641
3
+ size 18526714
tmp-checkpoint-1600/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
+ }
tmp-checkpoint-1600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd418f6cb48100ee0bb3a1497b61f130b25cfd0774294841750fabbe0c05abbb
3
+ size 14372
tmp-checkpoint-1600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87cf3284d050e0c7668f8e6ba3534922f15834d5c624cc608a88827da2e3274
3
+ size 1064
tmp-checkpoint-1600/trainer_state.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.5209125475285172,
5
+ "eval_steps": 100,
6
+ "global_step": 1600,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "learning_rate": 1.2933333333333334e-06,
14
+ "loss": 19.0829,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.1,
19
+ "eval_loss": 19.174156188964844,
20
+ "eval_runtime": 65.9422,
21
+ "eval_samples_per_second": 6.491,
22
+ "eval_steps_per_second": 0.819,
23
+ "eval_wer": 1.0007501875468867,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.19,
28
+ "learning_rate": 2.6e-06,
29
+ "loss": 18.8941,
30
+ "step": 200
31
+ },
32
+ {
33
+ "epoch": 0.19,
34
+ "eval_loss": 18.407485961914062,
35
+ "eval_runtime": 66.0283,
36
+ "eval_samples_per_second": 6.482,
37
+ "eval_steps_per_second": 0.818,
38
+ "eval_wer": 1.009627406851713,
39
+ "step": 200
40
+ },
41
+ {
42
+ "epoch": 0.29,
43
+ "learning_rate": 3.9333333333333335e-06,
44
+ "loss": 17.5359,
45
+ "step": 300
46
+ },
47
+ {
48
+ "epoch": 0.29,
49
+ "eval_loss": 17.08553123474121,
50
+ "eval_runtime": 65.7138,
51
+ "eval_samples_per_second": 6.513,
52
+ "eval_steps_per_second": 0.822,
53
+ "eval_wer": 1.248312078019505,
54
+ "step": 300
55
+ },
56
+ {
57
+ "epoch": 0.38,
58
+ "learning_rate": 5.2666666666666665e-06,
59
+ "loss": 16.0015,
60
+ "step": 400
61
+ },
62
+ {
63
+ "epoch": 0.38,
64
+ "eval_loss": 15.136056900024414,
65
+ "eval_runtime": 65.1801,
66
+ "eval_samples_per_second": 6.566,
67
+ "eval_steps_per_second": 0.828,
68
+ "eval_wer": 1.3134533633408352,
69
+ "step": 400
70
+ },
71
+ {
72
+ "epoch": 0.48,
73
+ "learning_rate": 6.5866666666666666e-06,
74
+ "loss": 13.3605,
75
+ "step": 500
76
+ },
77
+ {
78
+ "epoch": 0.48,
79
+ "eval_loss": 12.500285148620605,
80
+ "eval_runtime": 65.5504,
81
+ "eval_samples_per_second": 6.529,
82
+ "eval_steps_per_second": 0.824,
83
+ "eval_wer": 1.0840210052513128,
84
+ "step": 500
85
+ },
86
+ {
87
+ "epoch": 0.57,
88
+ "learning_rate": 7.92e-06,
89
+ "loss": 10.8925,
90
+ "step": 600
91
+ },
92
+ {
93
+ "epoch": 0.57,
94
+ "eval_loss": 9.41340160369873,
95
+ "eval_runtime": 64.6713,
96
+ "eval_samples_per_second": 6.618,
97
+ "eval_steps_per_second": 0.835,
98
+ "eval_wer": 1.0077519379844961,
99
+ "step": 600
100
+ },
101
+ {
102
+ "epoch": 0.67,
103
+ "learning_rate": 9.253333333333333e-06,
104
+ "loss": 8.1129,
105
+ "step": 700
106
+ },
107
+ {
108
+ "epoch": 0.67,
109
+ "eval_loss": 6.854950904846191,
110
+ "eval_runtime": 65.9954,
111
+ "eval_samples_per_second": 6.485,
112
+ "eval_steps_per_second": 0.818,
113
+ "eval_wer": 1.0,
114
+ "step": 700
115
+ },
116
+ {
117
+ "epoch": 0.76,
118
+ "learning_rate": 1.0586666666666668e-05,
119
+ "loss": 6.0586,
120
+ "step": 800
121
+ },
122
+ {
123
+ "epoch": 0.76,
124
+ "eval_loss": 5.390443801879883,
125
+ "eval_runtime": 65.312,
126
+ "eval_samples_per_second": 6.553,
127
+ "eval_steps_per_second": 0.827,
128
+ "eval_wer": 1.0,
129
+ "step": 800
130
+ },
131
+ {
132
+ "epoch": 0.86,
133
+ "learning_rate": 1.1920000000000001e-05,
134
+ "loss": 5.1935,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.86,
139
+ "eval_loss": 4.793299674987793,
140
+ "eval_runtime": 66.778,
141
+ "eval_samples_per_second": 6.409,
142
+ "eval_steps_per_second": 0.809,
143
+ "eval_wer": 1.0,
144
+ "step": 900
145
+ },
146
+ {
147
+ "epoch": 0.95,
148
+ "learning_rate": 1.3253333333333334e-05,
149
+ "loss": 4.7315,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.95,
154
+ "eval_loss": 4.52764368057251,
155
+ "eval_runtime": 66.1481,
156
+ "eval_samples_per_second": 6.47,
157
+ "eval_steps_per_second": 0.816,
158
+ "eval_wer": 0.9998749687421855,
159
+ "step": 1000
160
+ },
161
+ {
162
+ "epoch": 1.05,
163
+ "learning_rate": 1.4586666666666667e-05,
164
+ "loss": 4.4273,
165
+ "step": 1100
166
+ },
167
+ {
168
+ "epoch": 1.05,
169
+ "eval_loss": 4.082287788391113,
170
+ "eval_runtime": 65.6019,
171
+ "eval_samples_per_second": 6.524,
172
+ "eval_steps_per_second": 0.823,
173
+ "eval_wer": 1.0303825956489123,
174
+ "step": 1100
175
+ },
176
+ {
177
+ "epoch": 1.14,
178
+ "learning_rate": 1.5920000000000003e-05,
179
+ "loss": 4.0406,
180
+ "step": 1200
181
+ },
182
+ {
183
+ "epoch": 1.14,
184
+ "eval_loss": 3.9247243404388428,
185
+ "eval_runtime": 64.106,
186
+ "eval_samples_per_second": 6.676,
187
+ "eval_steps_per_second": 0.842,
188
+ "eval_wer": 1.0102525631407853,
189
+ "step": 1200
190
+ },
191
+ {
192
+ "epoch": 1.24,
193
+ "learning_rate": 1.7253333333333336e-05,
194
+ "loss": 3.9165,
195
+ "step": 1300
196
+ },
197
+ {
198
+ "epoch": 1.24,
199
+ "eval_loss": 3.870806932449341,
200
+ "eval_runtime": 65.1335,
201
+ "eval_samples_per_second": 6.571,
202
+ "eval_steps_per_second": 0.829,
203
+ "eval_wer": 1.0046261565391348,
204
+ "step": 1300
205
+ },
206
+ {
207
+ "epoch": 1.33,
208
+ "learning_rate": 1.858666666666667e-05,
209
+ "loss": 3.9965,
210
+ "step": 1400
211
+ },
212
+ {
213
+ "epoch": 1.33,
214
+ "eval_loss": 3.8457767963409424,
215
+ "eval_runtime": 65.82,
216
+ "eval_samples_per_second": 6.503,
217
+ "eval_steps_per_second": 0.82,
218
+ "eval_wer": 1.0012503125781445,
219
+ "step": 1400
220
+ },
221
+ {
222
+ "epoch": 1.43,
223
+ "learning_rate": 1.9920000000000002e-05,
224
+ "loss": 3.8683,
225
+ "step": 1500
226
+ },
227
+ {
228
+ "epoch": 1.43,
229
+ "eval_loss": 3.8101820945739746,
230
+ "eval_runtime": 65.6088,
231
+ "eval_samples_per_second": 6.524,
232
+ "eval_steps_per_second": 0.823,
233
+ "eval_wer": 1.0,
234
+ "step": 1500
235
+ },
236
+ {
237
+ "epoch": 1.52,
238
+ "learning_rate": 2.1253333333333335e-05,
239
+ "loss": 3.8863,
240
+ "step": 1600
241
+ },
242
+ {
243
+ "epoch": 1.52,
244
+ "eval_loss": 3.795001268386841,
245
+ "eval_runtime": 65.0097,
246
+ "eval_samples_per_second": 6.584,
247
+ "eval_steps_per_second": 0.831,
248
+ "eval_wer": 1.0037509377344336,
249
+ "step": 1600
250
+ }
251
+ ],
252
+ "logging_steps": 100,
253
+ "max_steps": 21040,
254
+ "num_input_tokens_seen": 0,
255
+ "num_train_epochs": 20,
256
+ "save_steps": 200,
257
+ "total_flos": 3.1104086860681257e+18,
258
+ "train_batch_size": 2,
259
+ "trial_name": null,
260
+ "trial_params": null
261
+ }
tmp-checkpoint-1600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7505b0c5224abc16f82f3dcabf83ff20ff04c2bf002c1a457c9a1f2dce4319b3
3
+ size 4728
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7505b0c5224abc16f82f3dcabf83ff20ff04c2bf002c1a457c9a1f2dce4319b3
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8196e156d5d190c35c6b1bb27c4ccd67fb5197a5f3965339e3be5b325eb19b8
3
  size 4728