Hugging Face's logo

Splend1dchan
/
t5lephone-small-textsquad

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
Splend1dchan commited on
Commit
8d32850
•
1 Parent(s): 2fc60ba

init

Browse files
Files changed (32) hide show
  1. checkpoint-1368/config.json +32 -0
  2. checkpoint-1368/optimizer.pt +3 -0
  3. checkpoint-1368/pytorch_model.bin +3 -0
  4. checkpoint-1368/rng_state.pth +3 -0
  5. checkpoint-1368/scheduler.pt +3 -0
  6. checkpoint-1368/trainer_state.json +28 -0
  7. checkpoint-1368/training_args.bin +3 -0
  8. checkpoint-2052/config.json +32 -0
  9. checkpoint-2052/optimizer.pt +3 -0
  10. checkpoint-2052/pytorch_model.bin +3 -0
  11. checkpoint-2052/rng_state.pth +3 -0
  12. checkpoint-2052/scheduler.pt +3 -0
  13. checkpoint-2052/trainer_state.json +40 -0
  14. checkpoint-2052/training_args.bin +3 -0
  15. checkpoint-684/config.json +32 -0
  16. checkpoint-684/optimizer.pt +3 -0
  17. checkpoint-684/pytorch_model.bin +3 -0
  18. checkpoint-684/rng_state.pth +3 -0
  19. checkpoint-684/scheduler.pt +3 -0
  20. checkpoint-684/trainer_state.json +22 -0
  21. checkpoint-684/training_args.bin +3 -0
  22. config.json +32 -0
  23. pytorch_model.bin +3 -0
  24. runs/Jun24_13-05-09_muly1yctr1656009252205-x452b/1656047123.9714088/events.out.tfevents.1656047123.muly1yctr1656009252205-x452b.26574.1 +3 -0
  25. runs/Jun24_13-05-09_muly1yctr1656009252205-x452b/events.out.tfevents.1656047123.muly1yctr1656009252205-x452b.26574.0 +3 -0
  26. runs/Jun24_13-18-31_muly1yctr1656009252205-x452b/1656047924.6050408/events.out.tfevents.1656047924.muly1yctr1656009252205-x452b.32335.1 +3 -0
  27. runs/Jun24_13-18-31_muly1yctr1656009252205-x452b/events.out.tfevents.1656047924.muly1yctr1656009252205-x452b.32335.0 +3 -0
  28. runs/Jun24_13-42-09_muly1yctr1656009252205-x452b/1656049341.8317244/events.out.tfevents.1656049341.muly1yctr1656009252205-x452b.32423.1 +3 -0
  29. runs/Jun24_13-42-09_muly1yctr1656009252205-x452b/events.out.tfevents.1656049341.muly1yctr1656009252205-x452b.32423.0 +3 -0
  30. special_tokens_map.json +150 -0
  31. tokenizer_config.json +157 -0
  32. training_args.bin +3 -0
checkpoint-1368/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "voidful/phoneme_byt5",
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-1368/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3656c0e3c4be585266ff710509fc8e87ce34df332bf314e7b0ada7cb1bdac8
3
+ size 2397201625
checkpoint-1368/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8d4cdbfbcf1bceccfa16ed12236bf44bc2a5fdada641f3eeb93dbde0f1c276
3
+ size 1198608045
checkpoint-1368/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ebbbcb6e0e44eded8f6fb6b8ac8d9f83ad72e15e9db575f521c5f48866d018
3
+ size 21579
checkpoint-1368/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02957e7861590610d60b88da154059528fca11745cee2f512e1d7ad0db0dca0a
3
+ size 623
checkpoint-1368/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9992695398100804,
5
+ "global_step": 1368,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.73,
12
+ "learning_rate": 0.0002269005847953216,
13
+ "loss": 0.2802,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.46,
18
+ "learning_rate": 0.00015380116959064327,
19
+ "loss": 0.1572,
20
+ "step": 1000
21
+ }
22
+ ],
23
+ "max_steps": 2052,
24
+ "num_train_epochs": 3,
25
+ "total_flos": 3.2192617685817754e+17,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-1368/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df93c7bc7a33ddde9f11571232a2b760fa3a5dfe16f9e5fac7aa6808726a3a35
3
+ size 3311
checkpoint-2052/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "voidful/phoneme_byt5",
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-2052/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40722904334f6bf50d5d5cd29a4e5ee5973899c12842995303621f1fe6c96ed0
3
+ size 2397201625
checkpoint-2052/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd583fd039546db404a60e41a285b856606912484255f320adc4480e1465580a
3
+ size 1198608045
checkpoint-2052/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eae23ec8acd9a45d706840aeca7d11607e7db99717c32668101423db4aa7be5
3
+ size 21579
checkpoint-2052/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62cfb1be7e1d4b3e4b051ac2e136616b962a5de9f156f8c4cd9bcd5ae625db0e
3
+ size 623
checkpoint-2052/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.99926953981008,
5
+ "global_step": 2052,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.73,
12
+ "learning_rate": 0.0002269005847953216,
13
+ "loss": 0.2802,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.46,
18
+ "learning_rate": 0.00015380116959064327,
19
+ "loss": 0.1572,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.19,
24
+ "learning_rate": 8.07017543859649e-05,
25
+ "loss": 0.1381,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.92,
30
+ "learning_rate": 7.6023391812865485e-06,
31
+ "loss": 0.1231,
32
+ "step": 2000
33
+ }
34
+ ],
35
+ "max_steps": 2052,
36
+ "num_train_epochs": 3,
37
+ "total_flos": 4.82802902827008e+17,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-2052/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df93c7bc7a33ddde9f11571232a2b760fa3a5dfe16f9e5fac7aa6808726a3a35
3
+ size 3311
checkpoint-684/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "voidful/phoneme_byt5",
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-684/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ad430e5696456896a4f2263645d52d55d089254dbb70633255455f10d027c3
3
+ size 2397201625
checkpoint-684/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed85bdeee4545d656a79942d0c3ed07a0cfb5f21bf5fdc50ca98819f8135d98b
3
+ size 1198608045
checkpoint-684/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ade4b087f7b21cd9241e565231def91ef309f2a9e788b3ec19a0469130571eb
3
+ size 21579
checkpoint-684/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408be700a73614a79a295cc01b992eddbf0a4d68a80c25a2f5f21beb2f9f5a2f
3
+ size 623
checkpoint-684/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9992695398100804,
5
+ "global_step": 684,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.73,
12
+ "learning_rate": 0.0002269005847953216,
13
+ "loss": 0.2802,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 2052,
18
+ "num_train_epochs": 3,
19
+ "total_flos": 1.6096308842908877e+17,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
checkpoint-684/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df93c7bc7a33ddde9f11571232a2b760fa3a5dfe16f9e5fac7aa6808726a3a35
3
+ size 3311
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "voidful/phoneme_byt5",
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:dd583fd039546db404a60e41a285b856606912484255f320adc4480e1465580a
3
+ size 1198608045
runs/Jun24_13-05-09_muly1yctr1656009252205-x452b/1656047123.9714088/events.out.tfevents.1656047123.muly1yctr1656009252205-x452b.26574.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec64de1842c3fefd6b5c67703d134b2480f1ebf8ac5be801881cc628e464c78
3
+ size 5348
runs/Jun24_13-05-09_muly1yctr1656009252205-x452b/events.out.tfevents.1656047123.muly1yctr1656009252205-x452b.26574.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3d732954f0579d020cc7217ff1d9b043c6fdaaeec4cd7a7f88298c3a4612fe
3
+ size 3804
runs/Jun24_13-18-31_muly1yctr1656009252205-x452b/1656047924.6050408/events.out.tfevents.1656047924.muly1yctr1656009252205-x452b.32335.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf38577306fc54a990bdcc7143b372e576bb4daddb0bedc9d09345a0a3e80e0c
3
+ size 5348
runs/Jun24_13-18-31_muly1yctr1656009252205-x452b/events.out.tfevents.1656047924.muly1yctr1656009252205-x452b.32335.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57cc14c5a9caeedfaff9263c56bf01824f9c7a37b8a47a9e7d4a91d813e6bcfe
3
+ size 3803
runs/Jun24_13-42-09_muly1yctr1656009252205-x452b/1656049341.8317244/events.out.tfevents.1656049341.muly1yctr1656009252205-x452b.32423.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a0808458c65485186e96b5e2495f112b9d292a2a98a0f9b780f3bcfb77aed3
3
+ size 5348
runs/Jun24_13-42-09_muly1yctr1656009252205-x452b/events.out.tfevents.1656049341.muly1yctr1656009252205-x452b.32423.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b70236ace438623d465d06a8582c46b52c2f500ca0f805e058710d0a62496a
3
+ size 4784
special_tokens_map.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>",
119
+ "<extra_id_116>",
120
+ "<extra_id_117>",
121
+ "<extra_id_118>",
122
+ "<extra_id_119>",
123
+ "<extra_id_120>",
124
+ "<extra_id_121>",
125
+ "<extra_id_122>",
126
+ "<extra_id_123>",
127
+ "<extra_id_124>"
128
+ ],
129
+ "eos_token": {
130
+ "content": "</s>",
131
+ "lstrip": false,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ "pad_token": {
137
+ "content": "<pad>",
138
+ "lstrip": false,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ "unk_token": {
144
+ "content": "<unk>",
145
+ "lstrip": false,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ }
150
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>",
119
+ "<extra_id_116>",
120
+ "<extra_id_117>",
121
+ "<extra_id_118>",
122
+ "<extra_id_119>",
123
+ "<extra_id_120>",
124
+ "<extra_id_121>",
125
+ "<extra_id_122>",
126
+ "<extra_id_123>",
127
+ "<extra_id_124>"
128
+ ],
129
+ "eos_token": {
130
+ "__type": "AddedToken",
131
+ "content": "</s>",
132
+ "lstrip": false,
133
+ "normalized": true,
134
+ "rstrip": false,
135
+ "single_word": false
136
+ },
137
+ "extra_ids": 125,
138
+ "name_or_path": "google/byt5-small",
139
+ "pad_token": {
140
+ "__type": "AddedToken",
141
+ "content": "<pad>",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false
146
+ },
147
+ "special_tokens_map_file": "/home/twskvfb446/.cache/huggingface/transformers/3715c3de7f5eda8f5c9274c55ea8e8632fe6e4cdfdf8e9066ae173b956cd9b80.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109",
148
+ "tokenizer_class": "ByT5Tokenizer",
149
+ "unk_token": {
150
+ "__type": "AddedToken",
151
+ "content": "<unk>",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ }
157
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df93c7bc7a33ddde9f11571232a2b760fa3a5dfe16f9e5fac7aa6808726a3a35
3
+ size 3311