Hugging Face's logo

versae
/
mt5-base-finetuned-modernisa

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
versae commited on
Commit
0575fb5
•
1 Parent(s): 64a5d4e

Training in progress, step 10000

Browse files
Files changed (21) hide show
  1. .gitignore +1 -0
  2. config.json +29 -0
  3. last-checkpoint/config.json +29 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/pytorch_model.bin +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scheduler.pt +3 -0
  8. last-checkpoint/special_tokens_map.json +1 -0
  9. last-checkpoint/spiece.model +3 -0
  10. last-checkpoint/tokenizer.json +0 -0
  11. last-checkpoint/tokenizer_config.json +1 -0
  12. last-checkpoint/trainer_state.json +146 -0
  13. last-checkpoint/training_args.bin +3 -0
  14. pytorch_model.bin +3 -0
  15. runs/Nov12_15-49-11_17f1a7550854/1636732174.9082901/events.out.tfevents.1636732174.17f1a7550854.84.1 +3 -0
  16. runs/Nov12_15-49-11_17f1a7550854/events.out.tfevents.1636732174.17f1a7550854.84.0 +3 -0
  17. special_tokens_map.json +1 -0
  18. spiece.model +3 -0
  19. tokenizer.json +0 -0
  20. tokenizer_config.json +1 -0
  21. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-base",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "mt5",
17
+ "num_decoder_layers": 12,
18
+ "num_heads": 12,
19
+ "num_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "relative_attention_num_buckets": 32,
23
+ "tie_word_embeddings": false,
24
+ "tokenizer_class": "T5Tokenizer",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.13.0.dev0",
27
+ "use_cache": true,
28
+ "vocab_size": 250112
29
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-base",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "mt5",
17
+ "num_decoder_layers": 12,
18
+ "num_heads": 12,
19
+ "num_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "relative_attention_num_buckets": 32,
23
+ "tie_word_embeddings": false,
24
+ "tokenizer_class": "T5Tokenizer",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.13.0.dev0",
27
+ "use_cache": true,
28
+ "vocab_size": 250112
29
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae5259d25e6f99bf596a6ec0fa9c7dd5dfaf2d79c46a5dec8c1ecc0836bbbf10
3
+ size 4659376733
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c31c4891c84594d92a7fc2c0c8d65bc297a38d3b98a472a3a84bd3fa1bb8b5df
3
+ size 2329732045
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5356547849e2b94f1f0d272f5260ab3742fc5e28f3e41bae5cfcdd497345006e
3
+ size 14503
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea4719bf4579360c2d2e9bd88999d25d3a9ef68a96f71f474e58bf3471a5127
3
+ size 623
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
last-checkpoint/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-base", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.35454706612302783,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 9.940908822312829e-05,
13
+ "loss": 3.0242,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 9.881817644625659e-05,
19
+ "loss": 1.0439,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 9.822726466938487e-05,
25
+ "loss": 0.8026,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.07,
30
+ "learning_rate": 9.763635289251316e-05,
31
+ "loss": 0.695,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.09,
36
+ "learning_rate": 9.704544111564144e-05,
37
+ "loss": 0.6169,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.11,
42
+ "learning_rate": 9.645452933876972e-05,
43
+ "loss": 0.5837,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "learning_rate": 9.586361756189801e-05,
49
+ "loss": 0.5781,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.14,
54
+ "learning_rate": 9.52727057850263e-05,
55
+ "loss": 0.5525,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.16,
60
+ "learning_rate": 9.468179400815459e-05,
61
+ "loss": 0.5367,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.18,
66
+ "learning_rate": 9.409088223128288e-05,
67
+ "loss": 0.5494,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.2,
72
+ "learning_rate": 9.349997045441116e-05,
73
+ "loss": 0.5067,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.21,
78
+ "learning_rate": 9.290905867753945e-05,
79
+ "loss": 0.4961,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.23,
84
+ "learning_rate": 9.231814690066773e-05,
85
+ "loss": 0.5102,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.25,
90
+ "learning_rate": 9.172723512379601e-05,
91
+ "loss": 0.4824,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.27,
96
+ "learning_rate": 9.113632334692431e-05,
97
+ "loss": 0.4854,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.28,
102
+ "learning_rate": 9.05454115700526e-05,
103
+ "loss": 0.5103,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.3,
108
+ "learning_rate": 8.995449979318088e-05,
109
+ "loss": 0.4474,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.32,
114
+ "learning_rate": 8.936358801630918e-05,
115
+ "loss": 0.477,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.34,
120
+ "learning_rate": 8.877267623943746e-05,
121
+ "loss": 0.4577,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.35,
126
+ "learning_rate": 8.818176446256575e-05,
127
+ "loss": 0.4588,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.35,
132
+ "eval_bleu": 78.1616,
133
+ "eval_gen_len": 11.1577,
134
+ "eval_loss": 0.40234658122062683,
135
+ "eval_runtime": 1250.9737,
136
+ "eval_samples_per_second": 11.273,
137
+ "eval_steps_per_second": 2.819,
138
+ "step": 10000
139
+ }
140
+ ],
141
+ "max_steps": 84615,
142
+ "num_train_epochs": 3,
143
+ "total_flos": 2394907297136640.0,
144
+ "trial_name": null,
145
+ "trial_params": null
146
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca666819c790c1e9fb11e31f6ec8ca8b95c55e19c9c5036d9590ff65c2b3954
3
+ size 2991
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c31c4891c84594d92a7fc2c0c8d65bc297a38d3b98a472a3a84bd3fa1bb8b5df
3
+ size 2329732045
runs/Nov12_15-49-11_17f1a7550854/1636732174.9082901/events.out.tfevents.1636732174.17f1a7550854.84.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d7dda5337126d3e37af742c098bf9c10671fa9ab8c0d3ae959a74460d0ae0d6
3
+ size 4802
runs/Nov12_15-49-11_17f1a7550854/events.out.tfevents.1636732174.17f1a7550854.84.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c9f1300f3eeb69fa99de574bdc2d2863987f87510438de18efc7277372311f
3
+ size 6878
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-base", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca666819c790c1e9fb11e31f6ec8ca8b95c55e19c9c5036d9590ff65c2b3954
3
+ size 2991