Hugging Face's logo

mosama
/
wav2vec2-xls-r-300m-ar_test

Safetensors
wav2vec2
Model card Files
xet
Community
mosama commited on
Commit
d84bf76
·
verified ·
1 Parent(s): ad1e18d

Training in progress, step 20, checkpoint

Browse files
Files changed (8) hide show
  1. checkpoint-20/config.json +108 -0
  2. checkpoint-20/model.safetensors +3 -0
  3. checkpoint-20/optimizer.pt +3 -0
  4. checkpoint-20/preprocessor_config.json +10 -0
  5. checkpoint-20/rng_state.pth +3 -0
  6. checkpoint-20/scheduler.pt +3 -0
  7. checkpoint-20/trainer_state.json +219 -0
  8. checkpoint-20/training_args.bin +3 -0
checkpoint-20/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "adapter_attn_dim": null,
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": 768,
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": 0.0,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.0,
58
+ "hidden_size": 1024,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 4096,
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": 24,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1024,
80
+ "pad_token_id": 35,
81
+ "proj_codevector_dim": 768,
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": "4.53.0",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 38,
107
+ "xvector_output_dim": 512
108
+ }
checkpoint-20/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7262fb980a2637b0ca40500b783e8169f34b67080e019b4c8d1536f27d7b4b75
3
+ size 1261963280
checkpoint-20/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c34da350374d00b6a435aa2f004cc67237673bf7fc65474474a6a3d394bd27
3
+ size 2490471751
checkpoint-20/preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
checkpoint-20/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd6e11cdcf0c599d6c3a1bced7d7d39ff466689b0b753987cf4326356f18720
3
+ size 14709
checkpoint-20/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55036c8c679fdf0524ebc76883ba877bbf26f2baa288d1a4f854e3736af6a64
3
+ size 1465
checkpoint-20/trainer_state.json ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 20,
3
+ "best_metric": 1.0,
4
+ "best_model_checkpoint": "/home/jupyter/wav2vec2-xls-r-300m-bfloat16-trained-test/checkpoints/checkpoint-20",
5
+ "epoch": 4.2,
6
+ "eval_steps": 4,
7
+ "global_step": 20,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.05,
14
+ "grad_norm": 26.8810977935791,
15
+ "learning_rate": 0.0,
16
+ "loss": 23.4044,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.1,
21
+ "grad_norm": 13.647429466247559,
22
+ "learning_rate": 6.666666666666667e-08,
23
+ "loss": 15.7161,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.15,
28
+ "grad_norm": 9.556838035583496,
29
+ "learning_rate": 1.3333333333333334e-07,
30
+ "loss": 13.7542,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.2,
35
+ "grad_norm": 23.727840423583984,
36
+ "learning_rate": 2.0000000000000002e-07,
37
+ "loss": 23.3498,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.2,
42
+ "eval_loss": 11.243566513061523,
43
+ "eval_runtime": 5.1037,
44
+ "eval_samples_per_second": 12.54,
45
+ "eval_steps_per_second": 3.135,
46
+ "eval_wer": 1.0029940119760479,
47
+ "step": 4
48
+ },
49
+ {
50
+ "epoch": 1.05,
51
+ "grad_norm": 27.989702224731445,
52
+ "learning_rate": 2.6666666666666667e-07,
53
+ "loss": 28.0155,
54
+ "step": 5
55
+ },
56
+ {
57
+ "epoch": 1.1,
58
+ "grad_norm": 11.38569450378418,
59
+ "learning_rate": 3.3333333333333335e-07,
60
+ "loss": 14.0151,
61
+ "step": 6
62
+ },
63
+ {
64
+ "epoch": 1.15,
65
+ "grad_norm": 10.933781623840332,
66
+ "learning_rate": 4.0000000000000003e-07,
67
+ "loss": 13.2631,
68
+ "step": 7
69
+ },
70
+ {
71
+ "epoch": 1.2,
72
+ "grad_norm": 13.671080589294434,
73
+ "learning_rate": 4.666666666666667e-07,
74
+ "loss": 16.3699,
75
+ "step": 8
76
+ },
77
+ {
78
+ "epoch": 1.2,
79
+ "eval_loss": 11.2361421585083,
80
+ "eval_runtime": 5.3019,
81
+ "eval_samples_per_second": 12.071,
82
+ "eval_steps_per_second": 3.018,
83
+ "eval_wer": 1.0029940119760479,
84
+ "step": 8
85
+ },
86
+ {
87
+ "epoch": 2.05,
88
+ "grad_norm": 12.261064529418945,
89
+ "learning_rate": 5.333333333333333e-07,
90
+ "loss": 13.7451,
91
+ "step": 9
92
+ },
93
+ {
94
+ "epoch": 2.1,
95
+ "grad_norm": 14.111751556396484,
96
+ "learning_rate": 6.000000000000001e-07,
97
+ "loss": 16.4979,
98
+ "step": 10
99
+ },
100
+ {
101
+ "epoch": 2.15,
102
+ "grad_norm": 15.027251243591309,
103
+ "learning_rate": 6.666666666666667e-07,
104
+ "loss": 15.1573,
105
+ "step": 11
106
+ },
107
+ {
108
+ "epoch": 2.2,
109
+ "grad_norm": 11.976419448852539,
110
+ "learning_rate": 7.333333333333333e-07,
111
+ "loss": 13.3081,
112
+ "step": 12
113
+ },
114
+ {
115
+ "epoch": 2.2,
116
+ "eval_loss": 11.223762512207031,
117
+ "eval_runtime": 5.1899,
118
+ "eval_samples_per_second": 12.332,
119
+ "eval_steps_per_second": 3.083,
120
+ "eval_wer": 1.0029940119760479,
121
+ "step": 12
122
+ },
123
+ {
124
+ "epoch": 3.05,
125
+ "grad_norm": 10.190653800964355,
126
+ "learning_rate": 8.000000000000001e-07,
127
+ "loss": 14.3285,
128
+ "step": 13
129
+ },
130
+ {
131
+ "epoch": 3.1,
132
+ "grad_norm": 10.525323867797852,
133
+ "learning_rate": 8.666666666666667e-07,
134
+ "loss": 14.0348,
135
+ "step": 14
136
+ },
137
+ {
138
+ "epoch": 3.15,
139
+ "grad_norm": 8.292677879333496,
140
+ "learning_rate": 9.333333333333334e-07,
141
+ "loss": 11.2145,
142
+ "step": 15
143
+ },
144
+ {
145
+ "epoch": 3.2,
146
+ "grad_norm": 9.087738990783691,
147
+ "learning_rate": 1.0000000000000002e-06,
148
+ "loss": 14.0511,
149
+ "step": 16
150
+ },
151
+ {
152
+ "epoch": 3.2,
153
+ "eval_loss": 11.206008911132812,
154
+ "eval_runtime": 5.1678,
155
+ "eval_samples_per_second": 12.384,
156
+ "eval_steps_per_second": 3.096,
157
+ "eval_wer": 1.0029940119760479,
158
+ "step": 16
159
+ },
160
+ {
161
+ "epoch": 4.05,
162
+ "grad_norm": 11.053936958312988,
163
+ "learning_rate": 1.0666666666666667e-06,
164
+ "loss": 13.6394,
165
+ "step": 17
166
+ },
167
+ {
168
+ "epoch": 4.1,
169
+ "grad_norm": 12.242379188537598,
170
+ "learning_rate": 1.1333333333333334e-06,
171
+ "loss": 14.9119,
172
+ "step": 18
173
+ },
174
+ {
175
+ "epoch": 4.15,
176
+ "grad_norm": 10.784377098083496,
177
+ "learning_rate": 1.2000000000000002e-06,
178
+ "loss": 13.2801,
179
+ "step": 19
180
+ },
181
+ {
182
+ "epoch": 4.2,
183
+ "grad_norm": 12.148858070373535,
184
+ "learning_rate": 1.2666666666666667e-06,
185
+ "loss": 13.7862,
186
+ "step": 20
187
+ },
188
+ {
189
+ "epoch": 4.2,
190
+ "eval_loss": 11.182676315307617,
191
+ "eval_runtime": 4.9755,
192
+ "eval_samples_per_second": 12.863,
193
+ "eval_steps_per_second": 3.216,
194
+ "eval_wer": 1.0,
195
+ "step": 20
196
+ }
197
+ ],
198
+ "logging_steps": 1,
199
+ "max_steps": 20,
200
+ "num_input_tokens_seen": 0,
201
+ "num_train_epochs": 9223372036854775807,
202
+ "save_steps": 4,
203
+ "stateful_callbacks": {
204
+ "TrainerControl": {
205
+ "args": {
206
+ "should_epoch_stop": false,
207
+ "should_evaluate": false,
208
+ "should_log": false,
209
+ "should_save": true,
210
+ "should_training_stop": true
211
+ },
212
+ "attributes": {}
213
+ }
214
+ },
215
+ "total_flos": 1.224933794681436e+17,
216
+ "train_batch_size": 4,
217
+ "trial_name": null,
218
+ "trial_params": null
219
+ }
checkpoint-20/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d331ebdb6d4acc429af968f1d608962935143aa00a943700acfd397ca73158
3
+ size 5969