Hugging Face's logo

Bntuhan
/
adrest0

TensorBoard
Safetensors
t5
Model card Files
xet
 Metrics Community
Bntuhan commited on
Commit
a5b6b58
·
verified ·
1 Parent(s): 9d35ba5

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +6 -0
  2. checkpoint-1950/config.json +32 -0
  3. checkpoint-1950/generation_config.json +9 -0
  4. checkpoint-1950/model.safetensors +3 -0
  5. checkpoint-1950/optimizer.pt +3 -0
  6. checkpoint-1950/rng_state.pth +3 -0
  7. checkpoint-1950/scheduler.pt +3 -0
  8. checkpoint-1950/special_tokens_map.json +23 -0
  9. checkpoint-1950/spiece.model +3 -0
  10. checkpoint-1950/tokenizer.json +3 -0
  11. checkpoint-1950/tokenizer_config.json +39 -0
  12. checkpoint-1950/trainer_state.json +63 -0
  13. checkpoint-1950/training_args.bin +3 -0
  14. checkpoint-3900/config.json +32 -0
  15. checkpoint-3900/generation_config.json +9 -0
  16. checkpoint-3900/model.safetensors +3 -0
  17. checkpoint-3900/optimizer.pt +3 -0
  18. checkpoint-3900/rng_state.pth +3 -0
  19. checkpoint-3900/scheduler.pt +3 -0
  20. checkpoint-3900/special_tokens_map.json +23 -0
  21. checkpoint-3900/spiece.model +3 -0
  22. checkpoint-3900/tokenizer.json +3 -0
  23. checkpoint-3900/tokenizer_config.json +39 -0
  24. checkpoint-3900/trainer_state.json +99 -0
  25. checkpoint-3900/training_args.bin +3 -0
  26. checkpoint-5850/config.json +32 -0
  27. checkpoint-5850/generation_config.json +9 -0
  28. checkpoint-5850/model.safetensors +3 -0
  29. checkpoint-5850/optimizer.pt +3 -0
  30. checkpoint-5850/rng_state.pth +3 -0
  31. checkpoint-5850/scheduler.pt +3 -0
  32. checkpoint-5850/special_tokens_map.json +23 -0
  33. checkpoint-5850/spiece.model +3 -0
  34. checkpoint-5850/tokenizer.json +3 -0
  35. checkpoint-5850/tokenizer_config.json +39 -0
  36. checkpoint-5850/trainer_state.json +135 -0
  37. checkpoint-5850/training_args.bin +3 -0
  38. checkpoint-7800/config.json +32 -0
  39. checkpoint-7800/generation_config.json +9 -0
  40. checkpoint-7800/model.safetensors +3 -0
  41. checkpoint-7800/optimizer.pt +3 -0
  42. checkpoint-7800/rng_state.pth +3 -0
  43. checkpoint-7800/scheduler.pt +3 -0
  44. checkpoint-7800/special_tokens_map.json +23 -0
  45. checkpoint-7800/spiece.model +3 -0
  46. checkpoint-7800/tokenizer.json +3 -0
  47. checkpoint-7800/tokenizer_config.json +39 -0
  48. checkpoint-7800/trainer_state.json +171 -0
  49. checkpoint-7800/training_args.bin +3 -0
  50. checkpoint-9750/config.json +32 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-1950/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-3900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-5850/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-7800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-9750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-1950/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
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": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "transformers_version": "4.57.3",
30
+ "use_cache": true,
31
+ "vocab_size": 250112
32
+ }
checkpoint-1950/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": [
5
+ 1
6
+ ],
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.57.3"
9
+ }
checkpoint-1950/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65699c0ba66e3e25d6a7334a963a34012e77570b7dd3a1557ff74b72df71352f
3
+ size 4918393736
checkpoint-1950/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:316169625322ab2cfa85736ce834f7d9886f5c1ed2c165dcc255988eb045496c
3
+ size 9837144773
checkpoint-1950/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a862da08b8f225edc53eaa9e19ee88a1d9c7df39bd09491fb57b1a0c5ace171
3
+ size 14645
checkpoint-1950/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c45390918d9c37d2ef7db4f3f6c2d1833ad9962a68bc6cdea40b6a487056136
3
+ size 1465
checkpoint-1950/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-1950/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
checkpoint-1950/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2172c2b5ca792ef398c3357421498eca5b0ae7e5deb50f00f8515316e1fd8f3
3
+ size 15998308
checkpoint-1950/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "extra_ids": 0,
33
+ "extra_special_tokens": {},
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<pad>",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "T5Tokenizer",
38
+ "unk_token": "<unk>"
39
+ }
checkpoint-1950/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1950,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2564102564102564,
14
+ "grad_norm": 0.3748186528682709,
15
+ "learning_rate": 0.0018976410256410258,
16
+ "loss": 0.4066,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.5128205128205128,
21
+ "grad_norm": 0.34374505281448364,
22
+ "learning_rate": 0.001795076923076923,
23
+ "loss": 0.1902,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.7692307692307693,
28
+ "grad_norm": 0.29863688349723816,
29
+ "learning_rate": 0.0016925128205128206,
30
+ "loss": 0.1362,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_loss": 0.0691862627863884,
36
+ "eval_runtime": 22.7429,
37
+ "eval_samples_per_second": 304.799,
38
+ "eval_steps_per_second": 9.541,
39
+ "step": 1950
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 9750,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 5,
46
+ "save_steps": 500,
47
+ "stateful_callbacks": {
48
+ "TrainerControl": {
49
+ "args": {
50
+ "should_epoch_stop": false,
51
+ "should_evaluate": false,
52
+ "should_log": false,
53
+ "should_save": true,
54
+ "should_training_stop": false
55
+ },
56
+ "attributes": {}
57
+ }
58
+ },
59
+ "total_flos": 1.43681419874304e+16,
60
+ "train_batch_size": 32,
61
+ "trial_name": null,
62
+ "trial_params": null
63
+ }
checkpoint-1950/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73d4d8893aacc3b19d15094a5e455c243203b7b56efb63dba156a34ea1cbcd8
3
+ size 5969
checkpoint-3900/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
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": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "transformers_version": "4.57.3",
30
+ "use_cache": true,
31
+ "vocab_size": 250112
32
+ }
checkpoint-3900/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": [
5
+ 1
6
+ ],
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.57.3"
9
+ }
checkpoint-3900/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d27c579cf168a9cdb0ab3e6f3f04ca9f014d5e5349ec31a667f41c2d114924
3
+ size 4918393736
checkpoint-3900/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b566910d98032f444868e9f36c9d9bf6d8e9fe5ae52bad90ecdc941e44d8ed3
3
+ size 9837144773
checkpoint-3900/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c61f401eeec93efdeed1dad9261a291c521a8ed80c18d55f197ad39c5ae716
3
+ size 14645
checkpoint-3900/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb637261de25fa0125d3ad5ea14cc0e272698b486bac389c82cfcdf93573527
3
+ size 1465
checkpoint-3900/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-3900/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
checkpoint-3900/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2172c2b5ca792ef398c3357421498eca5b0ae7e5deb50f00f8515316e1fd8f3
3
+ size 15998308
checkpoint-3900/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "extra_ids": 0,
33
+ "extra_special_tokens": {},
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<pad>",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "T5Tokenizer",
38
+ "unk_token": "<unk>"
39
+ }
checkpoint-3900/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3900,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2564102564102564,
14
+ "grad_norm": 0.3748186528682709,
15
+ "learning_rate": 0.0018976410256410258,
16
+ "loss": 0.4066,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.5128205128205128,
21
+ "grad_norm": 0.34374505281448364,
22
+ "learning_rate": 0.001795076923076923,
23
+ "loss": 0.1902,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.7692307692307693,
28
+ "grad_norm": 0.29863688349723816,
29
+ "learning_rate": 0.0016925128205128206,
30
+ "loss": 0.1362,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_loss": 0.0691862627863884,
36
+ "eval_runtime": 22.7429,
37
+ "eval_samples_per_second": 304.799,
38
+ "eval_steps_per_second": 9.541,
39
+ "step": 1950
40
+ },
41
+ {
42
+ "epoch": 1.0256410256410255,
43
+ "grad_norm": 0.25807419419288635,
44
+ "learning_rate": 0.001589948717948718,
45
+ "loss": 0.1005,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 1.282051282051282,
50
+ "grad_norm": 0.24320101737976074,
51
+ "learning_rate": 0.0014873846153846152,
52
+ "loss": 0.0615,
53
+ "step": 2500
54
+ },
55
+ {
56
+ "epoch": 1.5384615384615383,
57
+ "grad_norm": 0.24260133504867554,
58
+ "learning_rate": 0.001384820512820513,
59
+ "loss": 0.0562,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 1.7948717948717947,
64
+ "grad_norm": 0.4375219941139221,
65
+ "learning_rate": 0.0012822564102564103,
66
+ "loss": 0.0466,
67
+ "step": 3500
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_loss": 0.03345639631152153,
72
+ "eval_runtime": 23.0664,
73
+ "eval_samples_per_second": 300.523,
74
+ "eval_steps_per_second": 9.408,
75
+ "step": 3900
76
+ }
77
+ ],
78
+ "logging_steps": 500,
79
+ "max_steps": 9750,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 5,
82
+ "save_steps": 500,
83
+ "stateful_callbacks": {
84
+ "TrainerControl": {
85
+ "args": {
86
+ "should_epoch_stop": false,
87
+ "should_evaluate": false,
88
+ "should_log": false,
89
+ "should_save": true,
90
+ "should_training_stop": false
91
+ },
92
+ "attributes": {}
93
+ }
94
+ },
95
+ "total_flos": 2.87428490268672e+16,
96
+ "train_batch_size": 32,
97
+ "trial_name": null,
98
+ "trial_params": null
99
+ }
checkpoint-3900/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73d4d8893aacc3b19d15094a5e455c243203b7b56efb63dba156a34ea1cbcd8
3
+ size 5969
checkpoint-5850/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
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": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "transformers_version": "4.57.3",
30
+ "use_cache": true,
31
+ "vocab_size": 250112
32
+ }
checkpoint-5850/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": [
5
+ 1
6
+ ],
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.57.3"
9
+ }
checkpoint-5850/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccfeb23e4b69c5896f61fd9ed3757fd7b6a766fbd3c41786f3454d48887dd9d4
3
+ size 4918393736
checkpoint-5850/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28401f930f1e4773e6f482beb75739607df729e310f9c244b0c0fcce613793ae
3
+ size 9837144773
checkpoint-5850/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc886c9bdcb6be0db1eb3ed20ad206c4c4dd798ee9ec039675102c80fc1e27f
3
+ size 14645
checkpoint-5850/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ec5234b7eb4a306f2b4dab2d0f6718a72f0a92f8cc912cc35e4326697998d3
3
+ size 1465
checkpoint-5850/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-5850/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
checkpoint-5850/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2172c2b5ca792ef398c3357421498eca5b0ae7e5deb50f00f8515316e1fd8f3
3
+ size 15998308
checkpoint-5850/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "extra_ids": 0,
33
+ "extra_special_tokens": {},
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<pad>",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "T5Tokenizer",
38
+ "unk_token": "<unk>"
39
+ }
checkpoint-5850/trainer_state.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 5850,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2564102564102564,
14
+ "grad_norm": 0.3748186528682709,
15
+ "learning_rate": 0.0018976410256410258,
16
+ "loss": 0.4066,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.5128205128205128,
21
+ "grad_norm": 0.34374505281448364,
22
+ "learning_rate": 0.001795076923076923,
23
+ "loss": 0.1902,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.7692307692307693,
28
+ "grad_norm": 0.29863688349723816,
29
+ "learning_rate": 0.0016925128205128206,
30
+ "loss": 0.1362,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_loss": 0.0691862627863884,
36
+ "eval_runtime": 22.7429,
37
+ "eval_samples_per_second": 304.799,
38
+ "eval_steps_per_second": 9.541,
39
+ "step": 1950
40
+ },
41
+ {
42
+ "epoch": 1.0256410256410255,
43
+ "grad_norm": 0.25807419419288635,
44
+ "learning_rate": 0.001589948717948718,
45
+ "loss": 0.1005,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 1.282051282051282,
50
+ "grad_norm": 0.24320101737976074,
51
+ "learning_rate": 0.0014873846153846152,
52
+ "loss": 0.0615,
53
+ "step": 2500
54
+ },
55
+ {
56
+ "epoch": 1.5384615384615383,
57
+ "grad_norm": 0.24260133504867554,
58
+ "learning_rate": 0.001384820512820513,
59
+ "loss": 0.0562,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 1.7948717948717947,
64
+ "grad_norm": 0.4375219941139221,
65
+ "learning_rate": 0.0012822564102564103,
66
+ "loss": 0.0466,
67
+ "step": 3500
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_loss": 0.03345639631152153,
72
+ "eval_runtime": 23.0664,
73
+ "eval_samples_per_second": 300.523,
74
+ "eval_steps_per_second": 9.408,
75
+ "step": 3900
76
+ },
77
+ {
78
+ "epoch": 2.051282051282051,
79
+ "grad_norm": 0.20671938359737396,
80
+ "learning_rate": 0.0011796923076923076,
81
+ "loss": 0.038,
82
+ "step": 4000
83
+ },
84
+ {
85
+ "epoch": 2.3076923076923075,
86
+ "grad_norm": 0.16543850302696228,
87
+ "learning_rate": 0.0010771282051282051,
88
+ "loss": 0.0222,
89
+ "step": 4500
90
+ },
91
+ {
92
+ "epoch": 2.564102564102564,
93
+ "grad_norm": 0.12343248724937439,
94
+ "learning_rate": 0.0009745641025641025,
95
+ "loss": 0.0223,
96
+ "step": 5000
97
+ },
98
+ {
99
+ "epoch": 2.8205128205128203,
100
+ "grad_norm": 0.11194447427988052,
101
+ "learning_rate": 0.000872,
102
+ "loss": 0.0194,
103
+ "step": 5500
104
+ },
105
+ {
106
+ "epoch": 3.0,
107
+ "eval_loss": 0.020821645855903625,
108
+ "eval_runtime": 22.9804,
109
+ "eval_samples_per_second": 301.649,
110
+ "eval_steps_per_second": 9.443,
111
+ "step": 5850
112
+ }
113
+ ],
114
+ "logging_steps": 500,
115
+ "max_steps": 9750,
116
+ "num_input_tokens_seen": 0,
117
+ "num_train_epochs": 5,
118
+ "save_steps": 500,
119
+ "stateful_callbacks": {
120
+ "TrainerControl": {
121
+ "args": {
122
+ "should_epoch_stop": false,
123
+ "should_evaluate": false,
124
+ "should_log": false,
125
+ "should_save": true,
126
+ "should_training_stop": false
127
+ },
128
+ "attributes": {}
129
+ }
130
+ },
131
+ "total_flos": 4.31158388729856e+16,
132
+ "train_batch_size": 32,
133
+ "trial_name": null,
134
+ "trial_params": null
135
+ }
checkpoint-5850/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73d4d8893aacc3b19d15094a5e455c243203b7b56efb63dba156a34ea1cbcd8
3
+ size 5969
checkpoint-7800/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
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": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "transformers_version": "4.57.3",
30
+ "use_cache": true,
31
+ "vocab_size": 250112
32
+ }
checkpoint-7800/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": [
5
+ 1
6
+ ],
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.57.3"
9
+ }
checkpoint-7800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00377684bcbac60e371b2a935a0187d8c15f1ffb1d9d9790d650aa88a0c4121
3
+ size 4918393736
checkpoint-7800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c993f2bfba23164e0ba15ec8a1a1995032769986ea5e5953144bb9037fbc4be0
3
+ size 9837144773
checkpoint-7800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea02df094d7642fb17a3262c001750829e0c46883e7af59bdbfc87226b4a46f
3
+ size 14645
checkpoint-7800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147a87ed60ccf137a2bc842b9c61b4b8c5e52d8e347a77772870ca3385383ce2
3
+ size 1465
checkpoint-7800/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-7800/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
checkpoint-7800/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2172c2b5ca792ef398c3357421498eca5b0ae7e5deb50f00f8515316e1fd8f3
3
+ size 15998308
checkpoint-7800/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "extra_ids": 0,
33
+ "extra_special_tokens": {},
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<pad>",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "T5Tokenizer",
38
+ "unk_token": "<unk>"
39
+ }
checkpoint-7800/trainer_state.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 7800,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2564102564102564,
14
+ "grad_norm": 0.3748186528682709,
15
+ "learning_rate": 0.0018976410256410258,
16
+ "loss": 0.4066,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.5128205128205128,
21
+ "grad_norm": 0.34374505281448364,
22
+ "learning_rate": 0.001795076923076923,
23
+ "loss": 0.1902,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.7692307692307693,
28
+ "grad_norm": 0.29863688349723816,
29
+ "learning_rate": 0.0016925128205128206,
30
+ "loss": 0.1362,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_loss": 0.0691862627863884,
36
+ "eval_runtime": 22.7429,
37
+ "eval_samples_per_second": 304.799,
38
+ "eval_steps_per_second": 9.541,
39
+ "step": 1950
40
+ },
41
+ {
42
+ "epoch": 1.0256410256410255,
43
+ "grad_norm": 0.25807419419288635,
44
+ "learning_rate": 0.001589948717948718,
45
+ "loss": 0.1005,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 1.282051282051282,
50
+ "grad_norm": 0.24320101737976074,
51
+ "learning_rate": 0.0014873846153846152,
52
+ "loss": 0.0615,
53
+ "step": 2500
54
+ },
55
+ {
56
+ "epoch": 1.5384615384615383,
57
+ "grad_norm": 0.24260133504867554,
58
+ "learning_rate": 0.001384820512820513,
59
+ "loss": 0.0562,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 1.7948717948717947,
64
+ "grad_norm": 0.4375219941139221,
65
+ "learning_rate": 0.0012822564102564103,
66
+ "loss": 0.0466,
67
+ "step": 3500
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_loss": 0.03345639631152153,
72
+ "eval_runtime": 23.0664,
73
+ "eval_samples_per_second": 300.523,
74
+ "eval_steps_per_second": 9.408,
75
+ "step": 3900
76
+ },
77
+ {
78
+ "epoch": 2.051282051282051,
79
+ "grad_norm": 0.20671938359737396,
80
+ "learning_rate": 0.0011796923076923076,
81
+ "loss": 0.038,
82
+ "step": 4000
83
+ },
84
+ {
85
+ "epoch": 2.3076923076923075,
86
+ "grad_norm": 0.16543850302696228,
87
+ "learning_rate": 0.0010771282051282051,
88
+ "loss": 0.0222,
89
+ "step": 4500
90
+ },
91
+ {
92
+ "epoch": 2.564102564102564,
93
+ "grad_norm": 0.12343248724937439,
94
+ "learning_rate": 0.0009745641025641025,
95
+ "loss": 0.0223,
96
+ "step": 5000
97
+ },
98
+ {
99
+ "epoch": 2.8205128205128203,
100
+ "grad_norm": 0.11194447427988052,
101
+ "learning_rate": 0.000872,
102
+ "loss": 0.0194,
103
+ "step": 5500
104
+ },
105
+ {
106
+ "epoch": 3.0,
107
+ "eval_loss": 0.020821645855903625,
108
+ "eval_runtime": 22.9804,
109
+ "eval_samples_per_second": 301.649,
110
+ "eval_steps_per_second": 9.443,
111
+ "step": 5850
112
+ },
113
+ {
114
+ "epoch": 3.076923076923077,
115
+ "grad_norm": 0.07755649834871292,
116
+ "learning_rate": 0.0007694358974358975,
117
+ "loss": 0.0145,
118
+ "step": 6000
119
+ },
120
+ {
121
+ "epoch": 3.3333333333333335,
122
+ "grad_norm": 0.0282865259796381,
123
+ "learning_rate": 0.0006668717948717949,
124
+ "loss": 0.0087,
125
+ "step": 6500
126
+ },
127
+ {
128
+ "epoch": 3.58974358974359,
129
+ "grad_norm": 0.18944522738456726,
130
+ "learning_rate": 0.0005643076923076923,
131
+ "loss": 0.0076,
132
+ "step": 7000
133
+ },
134
+ {
135
+ "epoch": 3.8461538461538463,
136
+ "grad_norm": 0.13857877254486084,
137
+ "learning_rate": 0.00046174358974358977,
138
+ "loss": 0.0073,
139
+ "step": 7500
140
+ },
141
+ {
142
+ "epoch": 4.0,
143
+ "eval_loss": 0.016552278771996498,
144
+ "eval_runtime": 22.8045,
145
+ "eval_samples_per_second": 303.975,
146
+ "eval_steps_per_second": 9.516,
147
+ "step": 7800
148
+ }
149
+ ],
150
+ "logging_steps": 500,
151
+ "max_steps": 9750,
152
+ "num_input_tokens_seen": 0,
153
+ "num_train_epochs": 5,
154
+ "save_steps": 500,
155
+ "stateful_callbacks": {
156
+ "TrainerControl": {
157
+ "args": {
158
+ "should_epoch_stop": false,
159
+ "should_evaluate": false,
160
+ "should_log": false,
161
+ "should_save": true,
162
+ "should_training_stop": false
163
+ },
164
+ "attributes": {}
165
+ }
166
+ },
167
+ "total_flos": 5.74915563697152e+16,
168
+ "train_batch_size": 32,
169
+ "trial_name": null,
170
+ "trial_params": null
171
+ }
checkpoint-7800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73d4d8893aacc3b19d15094a5e455c243203b7b56efb63dba156a34ea1cbcd8
3
+ size 5969
checkpoint-9750/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
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": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "transformers_version": "4.57.3",
30
+ "use_cache": true,
31
+ "vocab_size": 250112
32
+ }