Hugging Face's logo

HealthTeam
/
mt5-small-finetuned-MultiHead-230207

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
HealthTeam commited on
Commit
7663274
•
1 Parent(s): ff1faac

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 +7 -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/Feb07_05-04-07_5214b674e698/1675746342.8134184/events.out.tfevents.1675746342.5214b674e698.342.1 +3 -0
  18. runs/Feb07_05-04-07_5214b674e698/events.out.tfevents.1675746342.5214b674e698.342.0 +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": "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
+ "max_length": 300,
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": "4.26.0",
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": "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
+ "max_length": 300,
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": "4.26.0",
30
+ "use_cache": true,
31
+ "vocab_size": 250104
32
+ }
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 sha256:2faf10bbe735665360db1a2dae820f2e02b3fde2b0f4f64c031ba406d5f10ed7
3
+ size 2401461253
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc065def13b6d58597abaa2251b47905a943f30a5a831ca31bd52dfcdb6eac6
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:f1ff9a2e5fca65416da9145619be52c48b30cc736bd1ce5a402acc84ea0b5e2f
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f90e33afe424209b512a3a0351a3ca2273b5bf67f108ec6f4b5f26d5d25a5dd
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": "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": 0.1643509565320877,
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": 1.9950413059216727e-05,
13
+ "loss": 14.0627,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 1.9900826118433453e-05,
19
+ "loss": 6.3799,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 1.9851239177650176e-05,
25
+ "loss": 5.31,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 1.9801652236866898e-05,
31
+ "loss": 4.9781,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.04,
36
+ "learning_rate": 1.9752065296083624e-05,
37
+ "loss": 4.7392,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.04,
42
+ "learning_rate": 1.970247835530035e-05,
43
+ "loss": 4.5779,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.05,
48
+ "learning_rate": 1.9652891414517075e-05,
49
+ "loss": 4.4691,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.06,
54
+ "learning_rate": 1.96033044737338e-05,
55
+ "loss": 4.3745,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.07,
60
+ "learning_rate": 1.9553717532950524e-05,
61
+ "loss": 4.2883,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.07,
66
+ "learning_rate": 1.9504130592167246e-05,
67
+ "loss": 4.2342,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.08,
72
+ "learning_rate": 1.9454543651383972e-05,
73
+ "loss": 4.1614,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.09,
78
+ "learning_rate": 1.9404956710600698e-05,
79
+ "loss": 4.1279,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.1,
84
+ "learning_rate": 1.9355369769817423e-05,
85
+ "loss": 4.0802,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.1,
90
+ "learning_rate": 1.930578282903415e-05,
91
+ "loss": 4.0298,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.11,
96
+ "learning_rate": 1.925619588825087e-05,
97
+ "loss": 3.9697,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.12,
102
+ "learning_rate": 1.9206608947467594e-05,
103
+ "loss": 3.9584,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.13,
108
+ "learning_rate": 1.915702200668432e-05,
109
+ "loss": 3.9196,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.13,
114
+ "learning_rate": 1.9107435065901046e-05,
115
+ "loss": 3.9081,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.14,
120
+ "learning_rate": 1.905784812511777e-05,
121
+ "loss": 3.8419,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.15,
126
+ "learning_rate": 1.9008261184334497e-05,
127
+ "loss": 3.8363,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.16,
132
+ "learning_rate": 1.895867424355122e-05,
133
+ "loss": 3.8047,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.16,
138
+ "learning_rate": 1.8909087302767945e-05,
139
+ "loss": 3.7728,
140
+ "step": 11000
141
+ }
142
+ ],
143
+ "max_steps": 201666,
144
+ "num_train_epochs": 3,
145
+ "total_flos": 1.298603121721344e+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:b850b2abccaa9cb6b0c14aaa89493109b9ac553fd3b9208268f6ca150829be14
3
+ size 3643
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc065def13b6d58597abaa2251b47905a943f30a5a831ca31bd52dfcdb6eac6
3
+ size 1200739717
runs/Feb07_05-04-07_5214b674e698/1675746342.8134184/events.out.tfevents.1675746342.5214b674e698.342.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c4fad205e591338f7fe2e40adeafd5d08640c4209b6dff7f4980c76d3fec2b5
3
+ size 5956
runs/Feb07_05-04-07_5214b674e698/events.out.tfevents.1675746342.5214b674e698.342.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f6435689479137c29cbcbeb8777592cbb4a6f944b8700cc5e575eb965d16d8
3
+ size 7571
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": "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:b850b2abccaa9cb6b0c14aaa89493109b9ac553fd3b9208268f6ca150829be14
3
+ size 3643