bowphs commited on
Commit
c829ebf
·
verified ·
1 Parent(s): 9815087

Upload folder using huggingface_hub

Browse files
Files changed (40) hide show
  1. checkpoint-349372/config.json +33 -0
  2. checkpoint-349372/generation_config.json +6 -0
  3. checkpoint-349372/model.safetensors +3 -0
  4. checkpoint-349372/optimizer.pt +3 -0
  5. checkpoint-349372/rng_state.pth +3 -0
  6. checkpoint-349372/scheduler.pt +3 -0
  7. checkpoint-349372/special_tokens_map.json +16 -0
  8. checkpoint-349372/tokenizer.json +0 -0
  9. checkpoint-349372/tokenizer_config.json +0 -0
  10. checkpoint-349372/trainer_state.json +0 -0
  11. checkpoint-349372/training_args.bin +3 -0
  12. checkpoint-422924/config.json +33 -0
  13. checkpoint-422924/generation_config.json +6 -0
  14. checkpoint-422924/model.safetensors +3 -0
  15. checkpoint-422924/optimizer.pt +3 -0
  16. checkpoint-422924/rng_state.pth +3 -0
  17. checkpoint-422924/scheduler.pt +3 -0
  18. checkpoint-422924/special_tokens_map.json +16 -0
  19. checkpoint-422924/tokenizer.json +0 -0
  20. checkpoint-422924/tokenizer_config.json +0 -0
  21. checkpoint-422924/trainer_state.json +0 -0
  22. checkpoint-422924/training_args.bin +3 -0
  23. checkpoint-441312/config.json +33 -0
  24. checkpoint-441312/generation_config.json +6 -0
  25. checkpoint-441312/model.safetensors +3 -0
  26. checkpoint-441312/optimizer.pt +3 -0
  27. checkpoint-441312/rng_state.pth +3 -0
  28. checkpoint-441312/scheduler.pt +3 -0
  29. checkpoint-441312/special_tokens_map.json +16 -0
  30. checkpoint-441312/tokenizer.json +0 -0
  31. checkpoint-441312/tokenizer_config.json +0 -0
  32. checkpoint-441312/trainer_state.json +0 -0
  33. checkpoint-441312/training_args.bin +3 -0
  34. config.json +33 -0
  35. generation_config.json +6 -0
  36. model.safetensors +3 -0
  37. special_tokens_map.json +16 -0
  38. tokenizer.json +0 -0
  39. tokenizer_config.json +0 -0
  40. training_args.bin +3 -0
checkpoint-349372/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bowphs/evacun2025-1",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.0,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_bf16": true,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.45.1",
31
+ "use_cache": true,
32
+ "vocab_size": 7118
33
+ }
checkpoint-349372/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.45.1"
6
+ }
checkpoint-349372/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee06a5fa02a1c4e25f5a3e8e4d03a997c7429258922c881c4d67901c25544a0d
3
+ size 836683624
checkpoint-349372/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3944d06aa16c8f6c87452c1e27f1037a95d80e79d1b0947c76d9ac0f19fb79f5
3
+ size 1673537530
checkpoint-349372/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3bee375dbffc19e7ae4d2b9b3f8b3d6ba77d6bad92c15a5accdea90679ca58d
3
+ size 14244
checkpoint-349372/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12fed5907d0dcceb6e04673997b7cb4b034dcae6acff7298928a020ad6fcd1ca
3
+ size 1064
checkpoint-349372/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "[EOS]",
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
+ }
checkpoint-349372/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-349372/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-349372/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-349372/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65be66679726c9840eb59c00fdda5cbc2601365fd018fa8a25668c2a31cf3860
3
+ size 5368
checkpoint-422924/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bowphs/evacun2025-1",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.0,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_bf16": true,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.45.1",
31
+ "use_cache": true,
32
+ "vocab_size": 7118
33
+ }
checkpoint-422924/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.45.1"
6
+ }
checkpoint-422924/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21b577effe6bea0eb0aa3b1c8be8e70a341f02ad704697a045b7e56d66af694
3
+ size 836683624
checkpoint-422924/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb7b8cb8c7f8953728f10a29193e299ad61554d300fd4bb680aa935aed21f54
3
+ size 1673537530
checkpoint-422924/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1bf3a813ce4fac8e5e5bdcb598e4f6a5d14f201cd8080172c6061b6460a851b
3
+ size 14244
checkpoint-422924/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0d6e0e3eb217c8c9946fbe7d3e1cba7df2b3fd7ffb5c22ecd58f10930ce5ac
3
+ size 1064
checkpoint-422924/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "[EOS]",
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
+ }
checkpoint-422924/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-422924/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-422924/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-422924/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65be66679726c9840eb59c00fdda5cbc2601365fd018fa8a25668c2a31cf3860
3
+ size 5368
checkpoint-441312/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bowphs/evacun2025-1",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.0,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_bf16": true,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.45.1",
31
+ "use_cache": true,
32
+ "vocab_size": 7118
33
+ }
checkpoint-441312/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.45.1"
6
+ }
checkpoint-441312/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016c734dc6292c84a8115d8d5057ba5b3bed335a778edde73dbb2457dc06feaa
3
+ size 836683624
checkpoint-441312/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:facfbc03b103e2a6331fdbddf672e00a6ec6ff91ea114e3f822d2478d878c747
3
+ size 1673537530
checkpoint-441312/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d1c7ff1305d160136d0a90bcf7ffbb36cb81bdf8323c8cc76457494feb58b93
3
+ size 14244
checkpoint-441312/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1aab33efd1623d0587bc9769d141edf86badaf14de46fb6ec70e4d0f157a99a
3
+ size 1064
checkpoint-441312/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "[EOS]",
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
+ }
checkpoint-441312/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-441312/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-441312/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-441312/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65be66679726c9840eb59c00fdda5cbc2601365fd018fa8a25668c2a31cf3860
3
+ size 5368
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bowphs/evacun2025-1",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.0,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_bf16": true,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.45.1",
31
+ "use_cache": true,
32
+ "vocab_size": 7118
33
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.45.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee06a5fa02a1c4e25f5a3e8e4d03a997c7429258922c881c4d67901c25544a0d
3
+ size 836683624
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "[EOS]",
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65be66679726c9840eb59c00fdda5cbc2601365fd018fa8a25668c2a31cf3860
3
+ size 5368