Hugging Face's logo

Splend1dchan
/
wav2vecu2-t5lephone-small-NMSQA

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Splend1dchan commited on
Commit
a924cd5
·
1 Parent(s): 6517451

push

Browse files
Files changed (30) hide show
  1. checkpoint-10884/config.json +32 -0
  2. checkpoint-10884/optimizer.pt +3 -0
  3. checkpoint-10884/pytorch_model.bin +3 -0
  4. checkpoint-10884/rng_state.pth +3 -0
  5. checkpoint-10884/scheduler.pt +3 -0
  6. checkpoint-10884/trainer_state.json +142 -0
  7. checkpoint-10884/training_args.bin +3 -0
  8. checkpoint-16326/config.json +32 -0
  9. checkpoint-16326/optimizer.pt +3 -0
  10. checkpoint-16326/pytorch_model.bin +3 -0
  11. checkpoint-16326/results.csv +0 -0
  12. checkpoint-16326/rng_state.pth +3 -0
  13. checkpoint-16326/scheduler.pt +3 -0
  14. checkpoint-16326/trainer_state.json +208 -0
  15. checkpoint-16326/training_args.bin +3 -0
  16. checkpoint-5442/config.json +32 -0
  17. checkpoint-5442/optimizer.pt +3 -0
  18. checkpoint-5442/pytorch_model.bin +3 -0
  19. checkpoint-5442/rng_state.pth +3 -0
  20. checkpoint-5442/scheduler.pt +3 -0
  21. checkpoint-5442/trainer_state.json +76 -0
  22. checkpoint-5442/training_args.bin +3 -0
  23. config.json +32 -0
  24. dev_for_squad_reduce_silIsSpace_dedup.parquet +3 -0
  25. pytorch_model.bin +3 -0
  26. runs/Oct06_00-42-54_n74xq8ctr1664987455383-4gvbm/1664988189.4021654/events.out.tfevents.1664988189.n74xq8ctr1664987455383-4gvbm.468.1 +3 -0
  27. runs/Oct06_00-42-54_n74xq8ctr1664987455383-4gvbm/events.out.tfevents.1664988189.n74xq8ctr1664987455383-4gvbm.468.0 +3 -0
  28. toy_for_squad_reduce_silIsSpace_dedup.parquet +3 -0
  29. train_for_squad_reduce_silIsSpace_dedup.parquet +3 -0
  30. training_args.bin +3 -0
checkpoint-10884/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "voidful/phoneme_byt5_g2p_v1",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3584,
7
+ "d_kv": 64,
8
+ "d_model": 1472,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "gradient_checkpointing": false,
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 4,
21
+ "num_heads": 6,
22
+ "num_layers": 12,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "tokenizer_class": "ByT5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.21.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 384
32
+ }
checkpoint-10884/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac59e2ae1c5a7d3f9d50fce7ed1920b03431af482d961e6e6f94dcef6d4131b3
3
+ size 2397201625
checkpoint-10884/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453715083c168005b2bd4f2147ad3c1b958b7ffdc92ab50184c8c57cd71025e5
3
+ size 1198608045
checkpoint-10884/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b6f9ad252974284be4b520ddcf470b24f1f89f3879a5fc9927f909db404be8
3
+ size 14503
checkpoint-10884/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084f05af181f5c196ebf0588520002358d79e3d5b8cc2d7366d462af8f7704d3
3
+ size 623
checkpoint-10884/trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.999954063117277,
5
+ "global_step": 10884,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 0.0002908122013965454,
13
+ "loss": 0.65,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 0.0002816244027930907,
19
+ "loss": 0.4102,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.28,
24
+ "learning_rate": 0.0002724366041896361,
25
+ "loss": 0.3675,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.37,
30
+ "learning_rate": 0.00026324880558618153,
31
+ "loss": 0.3386,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.46,
36
+ "learning_rate": 0.00025406100698272693,
37
+ "loss": 0.3203,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.55,
42
+ "learning_rate": 0.00024487320837927233,
43
+ "loss": 0.3104,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.64,
48
+ "learning_rate": 0.00023568540977581768,
49
+ "loss": 0.3027,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.73,
54
+ "learning_rate": 0.00022649761117236308,
55
+ "loss": 0.289,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.83,
60
+ "learning_rate": 0.00021730981256890848,
61
+ "loss": 0.2876,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.92,
66
+ "learning_rate": 0.00020812201396545386,
67
+ "loss": 0.2807,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.01,
72
+ "learning_rate": 0.00019893421536199926,
73
+ "loss": 0.2665,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.1,
78
+ "learning_rate": 0.00018974641675854466,
79
+ "loss": 0.2423,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.19,
84
+ "learning_rate": 0.00018055861815509,
85
+ "loss": 0.2402,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.29,
90
+ "learning_rate": 0.0001713708195516354,
91
+ "loss": 0.2449,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.38,
96
+ "learning_rate": 0.0001621830209481808,
97
+ "loss": 0.2354,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.47,
102
+ "learning_rate": 0.0001529952223447262,
103
+ "loss": 0.2298,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.56,
108
+ "learning_rate": 0.00014380742374127156,
109
+ "loss": 0.2361,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.65,
114
+ "learning_rate": 0.00013461962513781697,
115
+ "loss": 0.2329,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.75,
120
+ "learning_rate": 0.00012543182653436237,
121
+ "loss": 0.2274,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.84,
126
+ "learning_rate": 0.00011624402793090774,
127
+ "loss": 0.2213,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.93,
132
+ "learning_rate": 0.00010705622932745312,
133
+ "loss": 0.2306,
134
+ "step": 10500
135
+ }
136
+ ],
137
+ "max_steps": 16326,
138
+ "num_train_epochs": 3,
139
+ "total_flos": 3.200004777443328e+17,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }
checkpoint-10884/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1aa06d01146b6adb3d410ec5cb65fc33d307f1a3c904beb57acdd70c26859d
3
+ size 3375
checkpoint-16326/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "voidful/phoneme_byt5_g2p_v1",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3584,
7
+ "d_kv": 64,
8
+ "d_model": 1472,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "gradient_checkpointing": false,
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 4,
21
+ "num_heads": 6,
22
+ "num_layers": 12,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "tokenizer_class": "ByT5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.21.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 384
32
+ }
checkpoint-16326/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:686d69c879df729fbbeba3d0a3476f96e68396104b42ac3980a2c6e0618655f2
3
+ size 2397201625
checkpoint-16326/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b5e5a08cc92e46f1baa08b70fa4373ec121b77432e2bbeabe22588f110233d
3
+ size 1198608045
checkpoint-16326/results.csv ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16326/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6b5dc6dd6da4eb163abc7656511137ffafbd97fde9006ebfe55f98a052cf5b
3
+ size 14503
checkpoint-16326/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa463055b122898a3845e3156ecbc2c15d2d111d53d7111cf989e70aaf15cc58
3
+ size 623
checkpoint-16326/trainer_state.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.999954063117277,
5
+ "global_step": 16326,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 0.0002908122013965454,
13
+ "loss": 0.65,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 0.0002816244027930907,
19
+ "loss": 0.4102,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.28,
24
+ "learning_rate": 0.0002724366041896361,
25
+ "loss": 0.3675,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.37,
30
+ "learning_rate": 0.00026324880558618153,
31
+ "loss": 0.3386,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.46,
36
+ "learning_rate": 0.00025406100698272693,
37
+ "loss": 0.3203,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.55,
42
+ "learning_rate": 0.00024487320837927233,
43
+ "loss": 0.3104,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.64,
48
+ "learning_rate": 0.00023568540977581768,
49
+ "loss": 0.3027,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.73,
54
+ "learning_rate": 0.00022649761117236308,
55
+ "loss": 0.289,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.83,
60
+ "learning_rate": 0.00021730981256890848,
61
+ "loss": 0.2876,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.92,
66
+ "learning_rate": 0.00020812201396545386,
67
+ "loss": 0.2807,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.01,
72
+ "learning_rate": 0.00019893421536199926,
73
+ "loss": 0.2665,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.1,
78
+ "learning_rate": 0.00018974641675854466,
79
+ "loss": 0.2423,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.19,
84
+ "learning_rate": 0.00018055861815509,
85
+ "loss": 0.2402,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.29,
90
+ "learning_rate": 0.0001713708195516354,
91
+ "loss": 0.2449,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.38,
96
+ "learning_rate": 0.0001621830209481808,
97
+ "loss": 0.2354,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.47,
102
+ "learning_rate": 0.0001529952223447262,
103
+ "loss": 0.2298,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.56,
108
+ "learning_rate": 0.00014380742374127156,
109
+ "loss": 0.2361,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.65,
114
+ "learning_rate": 0.00013461962513781697,
115
+ "loss": 0.2329,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.75,
120
+ "learning_rate": 0.00012543182653436237,
121
+ "loss": 0.2274,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.84,
126
+ "learning_rate": 0.00011624402793090774,
127
+ "loss": 0.2213,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.93,
132
+ "learning_rate": 0.00010705622932745312,
133
+ "loss": 0.2306,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 2.02,
138
+ "learning_rate": 9.786843072399852e-05,
139
+ "loss": 0.2117,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 2.11,
144
+ "learning_rate": 8.868063212054391e-05,
145
+ "loss": 0.1985,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 2.21,
150
+ "learning_rate": 7.94928335170893e-05,
151
+ "loss": 0.1895,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.3,
156
+ "learning_rate": 7.030503491363469e-05,
157
+ "loss": 0.1908,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.39,
162
+ "learning_rate": 6.111723631018007e-05,
163
+ "loss": 0.1918,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.48,
168
+ "learning_rate": 5.192943770672546e-05,
169
+ "loss": 0.1918,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.57,
174
+ "learning_rate": 4.274163910327086e-05,
175
+ "loss": 0.1822,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.66,
180
+ "learning_rate": 3.355384049981624e-05,
181
+ "loss": 0.1858,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.76,
186
+ "learning_rate": 2.4366041896361628e-05,
187
+ "loss": 0.1884,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.85,
192
+ "learning_rate": 1.5178243292907018e-05,
193
+ "loss": 0.1864,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 2.94,
198
+ "learning_rate": 5.990444689452407e-06,
199
+ "loss": 0.1851,
200
+ "step": 16000
201
+ }
202
+ ],
203
+ "max_steps": 16326,
204
+ "num_train_epochs": 3,
205
+ "total_flos": 4.799952041190359e+17,
206
+ "trial_name": null,
207
+ "trial_params": null
208
+ }
checkpoint-16326/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1aa06d01146b6adb3d410ec5cb65fc33d307f1a3c904beb57acdd70c26859d
3
+ size 3375
checkpoint-5442/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "voidful/phoneme_byt5_g2p_v1",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3584,
7
+ "d_kv": 64,
8
+ "d_model": 1472,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "gradient_checkpointing": false,
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 4,
21
+ "num_heads": 6,
22
+ "num_layers": 12,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "tokenizer_class": "ByT5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.21.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 384
32
+ }
checkpoint-5442/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519d4a1495789bb18f4b791fa84b0b22d4a915186d290140175def5551acd72e
3
+ size 2397201625
checkpoint-5442/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ba7c5c62bc1127036bc84a25df42d3875f990b36cdc0bb93b5a861603223cb
3
+ size 1198608045
checkpoint-5442/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e680a46c4f16070ab26cdb564a5284231f978e506e33a7ac2bbc3d115972322
3
+ size 14503
checkpoint-5442/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0df5dadebe6bd2882ebd53860677576d02e7039eedf90343eb9e1a045c02c949
3
+ size 623
checkpoint-5442/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9999540631172769,
5
+ "global_step": 5442,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 0.0002908122013965454,
13
+ "loss": 0.65,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 0.0002816244027930907,
19
+ "loss": 0.4102,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.28,
24
+ "learning_rate": 0.0002724366041896361,
25
+ "loss": 0.3675,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.37,
30
+ "learning_rate": 0.00026324880558618153,
31
+ "loss": 0.3386,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.46,
36
+ "learning_rate": 0.00025406100698272693,
37
+ "loss": 0.3203,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.55,
42
+ "learning_rate": 0.00024487320837927233,
43
+ "loss": 0.3104,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.64,
48
+ "learning_rate": 0.00023568540977581768,
49
+ "loss": 0.3027,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.73,
54
+ "learning_rate": 0.00022649761117236308,
55
+ "loss": 0.289,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.83,
60
+ "learning_rate": 0.00021730981256890848,
61
+ "loss": 0.2876,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.92,
66
+ "learning_rate": 0.00020812201396545386,
67
+ "loss": 0.2807,
68
+ "step": 5000
69
+ }
70
+ ],
71
+ "max_steps": 16326,
72
+ "num_train_epochs": 3,
73
+ "total_flos": 1.600002388721664e+17,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
checkpoint-5442/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1aa06d01146b6adb3d410ec5cb65fc33d307f1a3c904beb57acdd70c26859d
3
+ size 3375
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "voidful/phoneme_byt5_g2p_v1",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3584,
7
+ "d_kv": 64,
8
+ "d_model": 1472,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "gradient_checkpointing": false,
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 4,
21
+ "num_heads": 6,
22
+ "num_layers": 12,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "tokenizer_class": "ByT5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.21.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 384
32
+ }
dev_for_squad_reduce_silIsSpace_dedup.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e7b2defed499175c6bfc2054d237f35bba871ceeddb586bc5a0cc1469c3ba4b
3
+ size 17075385
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b5e5a08cc92e46f1baa08b70fa4373ec121b77432e2bbeabe22588f110233d
3
+ size 1198608045
runs/Oct06_00-42-54_n74xq8ctr1664987455383-4gvbm/1664988189.4021654/events.out.tfevents.1664988189.n74xq8ctr1664987455383-4gvbm.468.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba734a91e229e56523e2cb15b8793d10909dc4b6288555bfe04902c4353ebfa8
3
+ size 5381
runs/Oct06_00-42-54_n74xq8ctr1664987455383-4gvbm/events.out.tfevents.1664988189.n74xq8ctr1664987455383-4gvbm.468.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a272d6a9006094f82f2cf79c1ff98bf782b5b245388b9010a7a57859d211ba98
3
+ size 9214
toy_for_squad_reduce_silIsSpace_dedup.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccf557e85c216bed7f34f12d7110681671946d1d410b475c3581e1ae58b6f92
3
+ size 49877
train_for_squad_reduce_silIsSpace_dedup.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1377b1664748e8037d19e79ef7a117728d9be15855de873c31f429a342d857c9
3
+ size 92520532
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1aa06d01146b6adb3d410ec5cb65fc33d307f1a3c904beb57acdd70c26859d
3
+ size 3375