Hugging Face's logo

HealthTeam
/
mt5-small-finetuned-MultiHead-230207-finetuned-MultiHead-230210-finetuned-MultiHead-230214

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
HealthTeam commited on
Commit
ca81d39
•
1 Parent(s): 3d02416

Training in progress, step 11048

Browse files
Files changed (22) hide show
  1. .gitignore +1 -0
  2. added_tokens.json +6 -0
  3. config.json +32 -0
  4. last-checkpoint/added_tokens.json +6 -0
  5. last-checkpoint/config.json +32 -0
  6. last-checkpoint/generation_config.json +8 -0
  7. last-checkpoint/optimizer.pt +3 -0
  8. last-checkpoint/pytorch_model.bin +3 -0
  9. last-checkpoint/rng_state.pth +3 -0
  10. last-checkpoint/scheduler.pt +3 -0
  11. last-checkpoint/special_tokens_map.json +11 -0
  12. last-checkpoint/spiece.model +3 -0
  13. last-checkpoint/tokenizer_config.json +12 -0
  14. last-checkpoint/trainer_state.json +148 -0
  15. last-checkpoint/training_args.bin +3 -0
  16. pytorch_model.bin +3 -0
  17. runs/Feb14_18-29-07_39730b194efc/1676399391.0992281/events.out.tfevents.1676399391.39730b194efc.3664.1 +3 -0
  18. runs/Feb14_18-29-07_39730b194efc/events.out.tfevents.1676399391.39730b194efc.3664.0 +3 -0
  19. special_tokens_map.json +11 -0
  20. spiece.model +3 -0
  21. tokenizer_config.json +12 -0
  22. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "translate Arabic to English:": 250101,
3
+ "translate Arabic to Thai:": 250100,
4
+ "translate Thai to Arabic:": 250102,
5
+ "translate Thai to English:": 250103
6
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Shularp/mt5-small-finetuned-MultiHead-230207-finetuned-MultiHead-230210",
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
+ "max_length": 1024,
19
+ "model_type": "mt5",
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
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": "T5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.26.1",
30
+ "use_cache": true,
31
+ "vocab_size": 250104
32
+ }
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "translate Arabic to English:": 250101,
3
+ "translate Arabic to Thai:": 250100,
4
+ "translate Thai to Arabic:": 250102,
5
+ "translate Thai to English:": 250103
6
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Shularp/mt5-small-finetuned-MultiHead-230207-finetuned-MultiHead-230210",
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
+ "max_length": 1024,
19
+ "model_type": "mt5",
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
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": "T5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.26.1",
30
+ "use_cache": true,
31
+ "vocab_size": 250104
32
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "max_length": 300,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.26.1"
8
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67d2fc17b2f4bc59d07576e003ad10f8eddbc3ae0db956991fd8874b93eab0e9
3
+ size 2401461253
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d28cd520a4e867deb95159919981e7230b151f0d187a73951a31cd6430227f
3
+ size 1200739717
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86bb859ee24859d101f2d75f72db6f4e08f2cbd10d16040696764241ab44371d
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604b54cab7492d9d0802b99e0519acf1f5952791d736af32968b684da5a8a554
3
+ size 627
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "translate Arabic to Thai:",
4
+ "translate Arabic to English:",
5
+ "translate Thai to Arabic:",
6
+ "translate Thai to English:"
7
+ ],
8
+ "eos_token": "</s>",
9
+ "pad_token": "<pad>",
10
+ "unk_token": "<unk>"
11
+ }
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": "Shularp/mt5-small-finetuned-MultiHead-230207-finetuned-MultiHead-230210",
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": 0.3287019130641754,
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": 0.01,
12
+ "learning_rate": 1.9900826118433453e-05,
13
+ "loss": 2.5088,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 1.9801652236866898e-05,
19
+ "loss": 2.4955,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.04,
24
+ "learning_rate": 1.970247835530035e-05,
25
+ "loss": 2.5035,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 1.96033044737338e-05,
31
+ "loss": 2.4969,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.07,
36
+ "learning_rate": 1.9504130592167246e-05,
37
+ "loss": 2.4963,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.09,
42
+ "learning_rate": 1.9404956710600698e-05,
43
+ "loss": 2.5023,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.1,
48
+ "learning_rate": 1.930578282903415e-05,
49
+ "loss": 2.5007,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.12,
54
+ "learning_rate": 1.9206608947467594e-05,
55
+ "loss": 2.4953,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.13,
60
+ "learning_rate": 1.9107435065901046e-05,
61
+ "loss": 2.499,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.15,
66
+ "learning_rate": 1.9008261184334497e-05,
67
+ "loss": 2.4919,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.16,
72
+ "learning_rate": 1.8909087302767945e-05,
73
+ "loss": 2.4988,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.18,
78
+ "learning_rate": 1.8809913421201393e-05,
79
+ "loss": 2.5076,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.19,
84
+ "learning_rate": 1.8710739539634845e-05,
85
+ "loss": 2.4915,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.21,
90
+ "learning_rate": 1.8611565658068293e-05,
91
+ "loss": 2.4823,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.22,
96
+ "learning_rate": 1.851239177650174e-05,
97
+ "loss": 2.4859,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.24,
102
+ "learning_rate": 1.8413217894935193e-05,
103
+ "loss": 2.4951,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.25,
108
+ "learning_rate": 1.831404401336864e-05,
109
+ "loss": 2.4816,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.27,
114
+ "learning_rate": 1.821487013180209e-05,
115
+ "loss": 2.485,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.28,
120
+ "learning_rate": 1.811569625023554e-05,
121
+ "loss": 2.4889,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.3,
126
+ "learning_rate": 1.801652236866899e-05,
127
+ "loss": 2.4812,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.31,
132
+ "learning_rate": 1.7917348487102437e-05,
133
+ "loss": 2.4774,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.33,
138
+ "learning_rate": 1.781817460553589e-05,
139
+ "loss": 2.4796,
140
+ "step": 11000
141
+ }
142
+ ],
143
+ "max_steps": 100833,
144
+ "num_train_epochs": 3,
145
+ "total_flos": 2.972249387945165e+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 sha256:25d27f125b86e4c017aefda34e143225bc4d6c87bc4f71d560b204a01dacffa1
3
+ size 3771
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d28cd520a4e867deb95159919981e7230b151f0d187a73951a31cd6430227f
3
+ size 1200739717
runs/Feb14_18-29-07_39730b194efc/1676399391.0992281/events.out.tfevents.1676399391.39730b194efc.3664.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6477b39d06150e6238aa7c90c3799e7456b204b9b8816d9946b2c189e1f31ec1
3
+ size 6119
runs/Feb14_18-29-07_39730b194efc/events.out.tfevents.1676399391.39730b194efc.3664.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:735ca1df34160d5d6746811c02fdc51b05898700b6d5236474ebcea9b415e22b
3
+ size 7817
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "translate Arabic to Thai:",
4
+ "translate Arabic to English:",
5
+ "translate Thai to Arabic:",
6
+ "translate Thai to English:"
7
+ ],
8
+ "eos_token": "</s>",
9
+ "pad_token": "<pad>",
10
+ "unk_token": "<unk>"
11
+ }
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": "Shularp/mt5-small-finetuned-MultiHead-230207-finetuned-MultiHead-230210",
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 sha256:25d27f125b86e4c017aefda34e143225bc4d6c87bc4f71d560b204a01dacffa1
3
+ size 3771