Hugging Face's logo

Shularp
/
mt5-small-finetuned-ar-to-th

Transformers
PyTorch
TensorBoard
mt5
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
1
Shularp commited on
Commit
b69ad40
·
1 Parent(s): b3f139e

Training in progress, step 11048

Browse files
Files changed (20) hide show
  1. .gitignore +1 -0
  2. config.json +31 -0
  3. last-checkpoint/config.json +31 -0
  4. last-checkpoint/generation_config.json +7 -0
  5. last-checkpoint/optimizer.pt +3 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/special_tokens_map.json +5 -0
  10. last-checkpoint/spiece.model +3 -0
  11. last-checkpoint/tokenizer_config.json +12 -0
  12. last-checkpoint/trainer_state.json +148 -0
  13. last-checkpoint/training_args.bin +3 -0
  14. pytorch_model.bin +3 -0
  15. runs/Jan26_09-04-05_e112ce585155/1674723897.3927884/events.out.tfevents.1674723897.e112ce585155.6073.1 +3 -0
  16. runs/Jan26_09-04-05_e112ce585155/events.out.tfevents.1674723897.e112ce585155.6073.0 +3 -0
  17. special_tokens_map.json +5 -0
  18. spiece.model +3 -0
  19. tokenizer_config.json +12 -0
  20. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-small",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
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
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "mt5",
19
+ "num_decoder_layers": 8,
20
+ "num_heads": 6,
21
+ "num_layers": 8,
22
+ "pad_token_id": 0,
23
+ "relative_attention_max_distance": 128,
24
+ "relative_attention_num_buckets": 32,
25
+ "tie_word_embeddings": false,
26
+ "tokenizer_class": "T5Tokenizer",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.26.0",
29
+ "use_cache": true,
30
+ "vocab_size": 250112
31
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-small",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
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
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "mt5",
19
+ "num_decoder_layers": 8,
20
+ "num_heads": 6,
21
+ "num_layers": 8,
22
+ "pad_token_id": 0,
23
+ "relative_attention_max_distance": 128,
24
+ "relative_attention_num_buckets": 32,
25
+ "tie_word_embeddings": false,
26
+ "tokenizer_class": "T5Tokenizer",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.26.0",
29
+ "use_cache": true,
30
+ "vocab_size": 250112
31
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.26.0"
7
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f98febe60615c325c19302ad0b105f669a167da187b0242acd20b3dabf556c
3
+ size 2401526789
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9284f44ebb41ded731fc768d6f38127b634b2056626e8ff2f4ab58c77e51ec0
3
+ size 1200772485
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab570d200150eeb95213ef2a1e7e82a249bdb59c0c1280dabda6019b9514357
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333da44acf9f47ace0b44a0573dd6c7f77e7228741751eb9577c99a12cd8a56e
3
+ size 627
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
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_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "eos_token": "</s>",
4
+ "extra_ids": 0,
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "google/mt5-small",
7
+ "pad_token": "<pad>",
8
+ "sp_model_kwargs": {},
9
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
10
+ "tokenizer_class": "T5Tokenizer",
11
+ "unk_token": "<unk>"
12
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.88384,
5
+ "global_step": 11048,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 1.9733333333333336e-05,
13
+ "loss": 14.1239,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "learning_rate": 1.9466666666666668e-05,
19
+ "loss": 6.6454,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.12,
24
+ "learning_rate": 1.9200000000000003e-05,
25
+ "loss": 5.9138,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.16,
30
+ "learning_rate": 1.8933333333333334e-05,
31
+ "loss": 5.5971,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.2,
36
+ "learning_rate": 1.866666666666667e-05,
37
+ "loss": 5.4037,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.24,
42
+ "learning_rate": 1.8400000000000003e-05,
43
+ "loss": 5.2453,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.28,
48
+ "learning_rate": 1.8133333333333335e-05,
49
+ "loss": 5.1776,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.32,
54
+ "learning_rate": 1.7866666666666666e-05,
55
+ "loss": 5.0923,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.36,
60
+ "learning_rate": 1.76e-05,
61
+ "loss": 5.0219,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.4,
66
+ "learning_rate": 1.7333333333333336e-05,
67
+ "loss": 4.9679,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.44,
72
+ "learning_rate": 1.706666666666667e-05,
73
+ "loss": 4.8737,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.48,
78
+ "learning_rate": 1.6800000000000002e-05,
79
+ "loss": 4.8347,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.52,
84
+ "learning_rate": 1.6533333333333333e-05,
85
+ "loss": 4.7651,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.56,
90
+ "learning_rate": 1.6266666666666668e-05,
91
+ "loss": 4.7169,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.6,
96
+ "learning_rate": 1.6000000000000003e-05,
97
+ "loss": 4.7314,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.64,
102
+ "learning_rate": 1.5733333333333334e-05,
103
+ "loss": 4.6803,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.68,
108
+ "learning_rate": 1.546666666666667e-05,
109
+ "loss": 4.627,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.72,
114
+ "learning_rate": 1.5200000000000002e-05,
115
+ "loss": 4.5979,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.76,
120
+ "learning_rate": 1.4933333333333335e-05,
121
+ "loss": 4.546,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.8,
126
+ "learning_rate": 1.4666666666666666e-05,
127
+ "loss": 4.557,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.84,
132
+ "learning_rate": 1.4400000000000001e-05,
133
+ "loss": 4.5273,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.88,
138
+ "learning_rate": 1.4133333333333334e-05,
139
+ "loss": 4.4533,
140
+ "step": 11000
141
+ }
142
+ ],
143
+ "max_steps": 37500,
144
+ "num_train_epochs": 3,
145
+ "total_flos": 1.225046113886208e+16,
146
+ "trial_name": null,
147
+ "trial_params": null
148
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad52c16538319a22a2678757517656a5b363f33d0a783ef91256d9af1c175a3f
3
+ size 3643
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9284f44ebb41ded731fc768d6f38127b634b2056626e8ff2f4ab58c77e51ec0
3
+ size 1200772485
runs/Jan26_09-04-05_e112ce585155/1674723897.3927884/events.out.tfevents.1674723897.e112ce585155.6073.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4456dc5c66682641de388735516895724325587c7cd8ce1b43098cd01259045f
3
+ size 5929
runs/Jan26_09-04-05_e112ce585155/events.out.tfevents.1674723897.e112ce585155.6073.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05288d5d371d533430c73704ac78fcaeaec27754306f7b8210e08aee60e22c0
3
+ size 7523
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "eos_token": "</s>",
4
+ "extra_ids": 0,
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "google/mt5-small",
7
+ "pad_token": "<pad>",
8
+ "sp_model_kwargs": {},
9
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
10
+ "tokenizer_class": "T5Tokenizer",
11
+ "unk_token": "<unk>"
12
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad52c16538319a22a2678757517656a5b363f33d0a783ef91256d9af1c175a3f
3
+ size 3643