Hugging Face's logo

Splend1dchan
/
g2p-t5lephone-small_textsquad

Transformers
PyTorch
TensorBoard
t5
text2text-generation
text-generation-inference
Model card Files
xet
 Metrics Community
Splend1dchan commited on
Commit
0fe4dd4
·
1 Parent(s): 3cf1e17

init

Browse files
Files changed (26) hide show
  1. checkpoint-10950/config.json +32 -0
  2. checkpoint-10950/optimizer.pt +3 -0
  3. checkpoint-10950/pytorch_model.bin +3 -0
  4. checkpoint-10950/rng_state.pth +3 -0
  5. checkpoint-10950/scheduler.pt +3 -0
  6. checkpoint-10950/trainer_state.json +142 -0
  7. checkpoint-10950/training_args.bin +3 -0
  8. checkpoint-16425/config.json +32 -0
  9. checkpoint-16425/optimizer.pt +3 -0
  10. checkpoint-16425/pytorch_model.bin +3 -0
  11. checkpoint-16425/rng_state.pth +3 -0
  12. checkpoint-16425/scheduler.pt +3 -0
  13. checkpoint-16425/trainer_state.json +208 -0
  14. checkpoint-16425/training_args.bin +3 -0
  15. checkpoint-5475/config.json +32 -0
  16. checkpoint-5475/optimizer.pt +3 -0
  17. checkpoint-5475/pytorch_model.bin +3 -0
  18. checkpoint-5475/rng_state.pth +3 -0
  19. checkpoint-5475/scheduler.pt +3 -0
  20. checkpoint-5475/trainer_state.json +76 -0
  21. checkpoint-5475/training_args.bin +3 -0
  22. config.json +32 -0
  23. pytorch_model.bin +3 -0
  24. runs/Oct07_22-45-42_pbm8m8ctr1665152816683-2g8bj/1665154019.8732357/events.out.tfevents.1665154019.pbm8m8ctr1665152816683-2g8bj.285.1 +3 -0
  25. runs/Oct07_22-45-42_pbm8m8ctr1665152816683-2g8bj/events.out.tfevents.1665154019.pbm8m8ctr1665152816683-2g8bj.285.0 +3 -0
  26. training_args.bin +3 -0
checkpoint-10950/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-10950/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8396d1147f897271339368091fd3e661eea7e2df0885924966067af6b642214a
3
+ size 2397201625
checkpoint-10950/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb5fcbd54359d070aecdbc1f18fdf3d229a9b47fe2d51aa1d0424c3edde01e53
3
+ size 1198608045
checkpoint-10950/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62dae836734a2145e4fb2fbb4943ea7771d1a3c14dfaabb0f1c9f8d3b27f71da
3
+ size 14503
checkpoint-10950/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0fa903f018d2dd85784f2fc2cf74441cb6674b4a2267220fc5e6f30d67cca52
3
+ size 623
checkpoint-10950/trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 10950,
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": 0.00029086757990867576,
13
+ "loss": 0.4741,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 0.0002817351598173516,
19
+ "loss": 0.2543,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 0.0002726027397260274,
25
+ "loss": 0.2336,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.37,
30
+ "learning_rate": 0.00026347031963470317,
31
+ "loss": 0.21,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.46,
36
+ "learning_rate": 0.00025433789954337895,
37
+ "loss": 0.2007,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.55,
42
+ "learning_rate": 0.0002452054794520548,
43
+ "loss": 0.183,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.64,
48
+ "learning_rate": 0.00023607305936073058,
49
+ "loss": 0.1879,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.73,
54
+ "learning_rate": 0.00022694063926940636,
55
+ "loss": 0.1723,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.82,
60
+ "learning_rate": 0.00021780821917808218,
61
+ "loss": 0.1769,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.91,
66
+ "learning_rate": 0.000208675799086758,
67
+ "loss": 0.1656,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.0,
72
+ "learning_rate": 0.00019954337899543377,
73
+ "loss": 0.1722,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.1,
78
+ "learning_rate": 0.0001904109589041096,
79
+ "loss": 0.1434,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.19,
84
+ "learning_rate": 0.00018127853881278537,
85
+ "loss": 0.1427,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.28,
90
+ "learning_rate": 0.00017214611872146118,
91
+ "loss": 0.1394,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.37,
96
+ "learning_rate": 0.00016301369863013697,
97
+ "loss": 0.1316,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.46,
102
+ "learning_rate": 0.00015388127853881278,
103
+ "loss": 0.1404,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.55,
108
+ "learning_rate": 0.00014474885844748857,
109
+ "loss": 0.1345,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.64,
114
+ "learning_rate": 0.00013561643835616435,
115
+ "loss": 0.136,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.74,
120
+ "learning_rate": 0.00012648401826484017,
121
+ "loss": 0.1333,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.83,
126
+ "learning_rate": 0.00011735159817351596,
127
+ "loss": 0.1314,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.92,
132
+ "learning_rate": 0.00010821917808219176,
133
+ "loss": 0.1297,
134
+ "step": 10500
135
+ }
136
+ ],
137
+ "max_steps": 16425,
138
+ "num_train_epochs": 3,
139
+ "total_flos": 3.2192617685817754e+17,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }
checkpoint-10950/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a505469e5ce49e07d54cba5caf55540c540ee137652dbd3e04c005ba00eef9
3
+ size 3311
checkpoint-16425/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-16425/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde22fd78c8f045d091d68051ae1dcdfe4f8a87c4bfb8986bd218c82cd762f0e
3
+ size 2397201625
checkpoint-16425/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb984e06d5cc3a002944242ed830076d3807ab059dce03327394add3bc50ab9
3
+ size 1198608045
checkpoint-16425/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbab2261442a3e5f485760e0a0c61cec6203b9e25fca160502ca20f025ab8e78
3
+ size 14503
checkpoint-16425/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d97576c4da698f251f1a819576b18015e3a372a42de48074a4d3f351c34ee106
3
+ size 623
checkpoint-16425/trainer_state.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 16425,
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": 0.00029086757990867576,
13
+ "loss": 0.4741,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 0.0002817351598173516,
19
+ "loss": 0.2543,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 0.0002726027397260274,
25
+ "loss": 0.2336,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.37,
30
+ "learning_rate": 0.00026347031963470317,
31
+ "loss": 0.21,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.46,
36
+ "learning_rate": 0.00025433789954337895,
37
+ "loss": 0.2007,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.55,
42
+ "learning_rate": 0.0002452054794520548,
43
+ "loss": 0.183,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.64,
48
+ "learning_rate": 0.00023607305936073058,
49
+ "loss": 0.1879,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.73,
54
+ "learning_rate": 0.00022694063926940636,
55
+ "loss": 0.1723,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.82,
60
+ "learning_rate": 0.00021780821917808218,
61
+ "loss": 0.1769,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.91,
66
+ "learning_rate": 0.000208675799086758,
67
+ "loss": 0.1656,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.0,
72
+ "learning_rate": 0.00019954337899543377,
73
+ "loss": 0.1722,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.1,
78
+ "learning_rate": 0.0001904109589041096,
79
+ "loss": 0.1434,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.19,
84
+ "learning_rate": 0.00018127853881278537,
85
+ "loss": 0.1427,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.28,
90
+ "learning_rate": 0.00017214611872146118,
91
+ "loss": 0.1394,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.37,
96
+ "learning_rate": 0.00016301369863013697,
97
+ "loss": 0.1316,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.46,
102
+ "learning_rate": 0.00015388127853881278,
103
+ "loss": 0.1404,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.55,
108
+ "learning_rate": 0.00014474885844748857,
109
+ "loss": 0.1345,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.64,
114
+ "learning_rate": 0.00013561643835616435,
115
+ "loss": 0.136,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.74,
120
+ "learning_rate": 0.00012648401826484017,
121
+ "loss": 0.1333,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.83,
126
+ "learning_rate": 0.00011735159817351596,
127
+ "loss": 0.1314,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.92,
132
+ "learning_rate": 0.00010821917808219176,
133
+ "loss": 0.1297,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 2.01,
138
+ "learning_rate": 9.908675799086756e-05,
139
+ "loss": 0.1235,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 2.1,
144
+ "learning_rate": 8.995433789954336e-05,
145
+ "loss": 0.1053,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 2.19,
150
+ "learning_rate": 8.082191780821917e-05,
151
+ "loss": 0.108,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.28,
156
+ "learning_rate": 7.168949771689497e-05,
157
+ "loss": 0.104,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.37,
162
+ "learning_rate": 6.255707762557077e-05,
163
+ "loss": 0.105,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.47,
168
+ "learning_rate": 5.342465753424657e-05,
169
+ "loss": 0.1053,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.56,
174
+ "learning_rate": 4.429223744292237e-05,
175
+ "loss": 0.1029,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.65,
180
+ "learning_rate": 3.515981735159817e-05,
181
+ "loss": 0.103,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.74,
186
+ "learning_rate": 2.602739726027397e-05,
187
+ "loss": 0.1012,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.83,
192
+ "learning_rate": 1.6894977168949768e-05,
193
+ "loss": 0.0993,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 2.92,
198
+ "learning_rate": 7.76255707762557e-06,
199
+ "loss": 0.0973,
200
+ "step": 16000
201
+ }
202
+ ],
203
+ "max_steps": 16425,
204
+ "num_train_epochs": 3,
205
+ "total_flos": 4.828892652872663e+17,
206
+ "trial_name": null,
207
+ "trial_params": null
208
+ }
checkpoint-16425/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a505469e5ce49e07d54cba5caf55540c540ee137652dbd3e04c005ba00eef9
3
+ size 3311
checkpoint-5475/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-5475/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8da375ac3be3942a3d43a73fe2da599d97c5519dfd5297288ffaf6ee562cd5
3
+ size 2397201625
checkpoint-5475/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70da5a0f3b11e815da56954d9c33c887105aacbf895b178238706ca0e6c6048a
3
+ size 1198608045
checkpoint-5475/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc4eea2dc68be902f7c48a75211c06f53a8f57f0f8e89c6cde228997e3fbf57
3
+ size 14503
checkpoint-5475/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f96569a2b0e107e2bc4dc44117501300e3a19a77ea9262e413974d9ded929b
3
+ size 623
checkpoint-5475/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 5475,
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": 0.00029086757990867576,
13
+ "loss": 0.4741,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 0.0002817351598173516,
19
+ "loss": 0.2543,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 0.0002726027397260274,
25
+ "loss": 0.2336,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.37,
30
+ "learning_rate": 0.00026347031963470317,
31
+ "loss": 0.21,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.46,
36
+ "learning_rate": 0.00025433789954337895,
37
+ "loss": 0.2007,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.55,
42
+ "learning_rate": 0.0002452054794520548,
43
+ "loss": 0.183,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.64,
48
+ "learning_rate": 0.00023607305936073058,
49
+ "loss": 0.1879,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.73,
54
+ "learning_rate": 0.00022694063926940636,
55
+ "loss": 0.1723,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.82,
60
+ "learning_rate": 0.00021780821917808218,
61
+ "loss": 0.1769,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.91,
66
+ "learning_rate": 0.000208675799086758,
67
+ "loss": 0.1656,
68
+ "step": 5000
69
+ }
70
+ ],
71
+ "max_steps": 16425,
72
+ "num_train_epochs": 3,
73
+ "total_flos": 1.6096308842908877e+17,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
checkpoint-5475/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a505469e5ce49e07d54cba5caf55540c540ee137652dbd3e04c005ba00eef9
3
+ size 3311
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb984e06d5cc3a002944242ed830076d3807ab059dce03327394add3bc50ab9
3
+ size 1198608045
runs/Oct07_22-45-42_pbm8m8ctr1665152816683-2g8bj/1665154019.8732357/events.out.tfevents.1665154019.pbm8m8ctr1665152816683-2g8bj.285.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eeb2719038949f8a8458ca45990d454e36f10a6f69050e7908426ee0b552653
3
+ size 5360
runs/Oct07_22-45-42_pbm8m8ctr1665152816683-2g8bj/events.out.tfevents.1665154019.pbm8m8ctr1665152816683-2g8bj.285.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ced98ded5f5a10d93ad5a7ae590b637927af4af847585b029d2ab6de29c4c31
3
+ size 9205
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a505469e5ce49e07d54cba5caf55540c540ee137652dbd3e04c005ba00eef9
3
+ size 3311