Hugging Face's logo

WhirlwindAI
/
Translate-25T

Translation
Transformers
Safetensors
mt5
text2text-generation
machine-translation
whirlwindai
Model card Files
xet
 Community
QuantaSparkLabs commited on
Commit
932e959
·
verified ·
1 Parent(s): 7482db9

checkpoint-1000

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. config.json +33 -0
  3. generation_config.json +9 -0
  4. model.safetensors +3 -0
  5. optimizer.pt +3 -0
  6. rng_state.pth +3 -0
  7. scaler.pt +3 -0
  8. scheduler.pt +3 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +115 -0
  11. trainer_state.json +120 -0
  12. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MT5ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 1024,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "dtype": "float32",
14
+ "eos_token_id": 1,
15
+ "feed_forward_proj": "gated-gelu",
16
+ "initializer_factor": 1.0,
17
+ "is_decoder": false,
18
+ "is_encoder_decoder": true,
19
+ "is_gated_act": true,
20
+ "layer_norm_epsilon": 1e-06,
21
+ "model_type": "mt5",
22
+ "num_decoder_layers": 8,
23
+ "num_heads": 6,
24
+ "num_layers": 8,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "tokenizer_class": "T5Tokenizer",
30
+ "transformers_version": "5.0.0",
31
+ "use_cache": false,
32
+ "vocab_size": 250112
33
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": [
5
+ 1
6
+ ],
7
+ "pad_token_id": 0,
8
+ "transformers_version": "5.0.0"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90e99624dce86337250bcd202329c7cc3d53036669376bfd9dde00f8a1d3273b
3
+ size 2225188480
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7c903d14db7692a5392e6b0356ebd658f9b6733440f820e03e1c40894d67ab
3
+ size 4450498267
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d31788affe3f24d7df3bd8b2a884292e41621d159bf18af08e50032e5040657
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02915332e6ecb039bb47c526bf2f9bc2e7c16a67dc5fad9c1b3eafa9884c62af
3
+ size 1465
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5e8e19bbf7837de5e1b06cbaaa9ba452ef92c2d719a8035166a92429d93402
3
+ size 16033083
tokenizer_config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "eos_token": "</s>",
4
+ "extra_ids": 0,
5
+ "extra_special_tokens": [
6
+ "<pad>",
7
+ "</s>",
8
+ "▁<extra_id_99>",
9
+ "▁<extra_id_98>",
10
+ "▁<extra_id_97>",
11
+ "▁<extra_id_96>",
12
+ "▁<extra_id_95>",
13
+ "▁<extra_id_94>",
14
+ "▁<extra_id_93>",
15
+ "▁<extra_id_92>",
16
+ "▁<extra_id_91>",
17
+ "▁<extra_id_90>",
18
+ "▁<extra_id_89>",
19
+ "▁<extra_id_88>",
20
+ "▁<extra_id_87>",
21
+ "▁<extra_id_86>",
22
+ "▁<extra_id_85>",
23
+ "▁<extra_id_84>",
24
+ "▁<extra_id_83>",
25
+ "▁<extra_id_82>",
26
+ "▁<extra_id_81>",
27
+ "▁<extra_id_80>",
28
+ "▁<extra_id_79>",
29
+ "▁<extra_id_78>",
30
+ "▁<extra_id_77>",
31
+ "▁<extra_id_76>",
32
+ "▁<extra_id_75>",
33
+ "▁<extra_id_74>",
34
+ "▁<extra_id_73>",
35
+ "▁<extra_id_72>",
36
+ "▁<extra_id_71>",
37
+ "▁<extra_id_70>",
38
+ "▁<extra_id_69>",
39
+ "▁<extra_id_68>",
40
+ "▁<extra_id_67>",
41
+ "▁<extra_id_66>",
42
+ "▁<extra_id_65>",
43
+ "▁<extra_id_64>",
44
+ "▁<extra_id_63>",
45
+ "▁<extra_id_62>",
46
+ "▁<extra_id_61>",
47
+ "▁<extra_id_60>",
48
+ "▁<extra_id_59>",
49
+ "▁<extra_id_58>",
50
+ "▁<extra_id_57>",
51
+ "▁<extra_id_56>",
52
+ "▁<extra_id_55>",
53
+ "▁<extra_id_54>",
54
+ "▁<extra_id_53>",
55
+ "▁<extra_id_52>",
56
+ "▁<extra_id_51>",
57
+ "▁<extra_id_50>",
58
+ "▁<extra_id_49>",
59
+ "▁<extra_id_48>",
60
+ "▁<extra_id_47>",
61
+ "▁<extra_id_46>",
62
+ "▁<extra_id_45>",
63
+ "▁<extra_id_44>",
64
+ "▁<extra_id_43>",
65
+ "▁<extra_id_42>",
66
+ "▁<extra_id_41>",
67
+ "▁<extra_id_40>",
68
+ "▁<extra_id_39>",
69
+ "▁<extra_id_38>",
70
+ "▁<extra_id_37>",
71
+ "▁<extra_id_36>",
72
+ "▁<extra_id_35>",
73
+ "▁<extra_id_34>",
74
+ "▁<extra_id_33>",
75
+ "▁<extra_id_32>",
76
+ "▁<extra_id_31>",
77
+ "▁<extra_id_30>",
78
+ "▁<extra_id_29>",
79
+ "▁<extra_id_28>",
80
+ "▁<extra_id_27>",
81
+ "▁<extra_id_26>",
82
+ "▁<extra_id_25>",
83
+ "▁<extra_id_24>",
84
+ "▁<extra_id_23>",
85
+ "▁<extra_id_22>",
86
+ "▁<extra_id_21>",
87
+ "▁<extra_id_20>",
88
+ "▁<extra_id_19>",
89
+ "▁<extra_id_18>",
90
+ "▁<extra_id_17>",
91
+ "▁<extra_id_16>",
92
+ "▁<extra_id_15>",
93
+ "▁<extra_id_14>",
94
+ "▁<extra_id_13>",
95
+ "▁<extra_id_12>",
96
+ "▁<extra_id_11>",
97
+ "▁<extra_id_10>",
98
+ "▁<extra_id_9>",
99
+ "▁<extra_id_8>",
100
+ "▁<extra_id_7>",
101
+ "▁<extra_id_6>",
102
+ "▁<extra_id_5>",
103
+ "▁<extra_id_4>",
104
+ "▁<extra_id_3>",
105
+ "▁<extra_id_2>",
106
+ "▁<extra_id_1>",
107
+ "▁<extra_id_0>"
108
+ ],
109
+ "is_local": false,
110
+ "model_max_length": 1000000000000000019884624838656,
111
+ "pad_token": "<pad>",
112
+ "tokenizer_class": "T5Tokenizer",
113
+ "unk_id": 2,
114
+ "unk_token": "<unk>"
115
+ }
trainer_state.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.6734006734006734,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06734006734006734,
14
+ "grad_norm": 1277.759765625,
15
+ "learning_rate": 0.00014849999999999998,
16
+ "loss": 306.280546875,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.13468013468013468,
21
+ "grad_norm": 45.35179138183594,
22
+ "learning_rate": 0.0002985,
23
+ "loss": 116.630830078125,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.20202020202020202,
28
+ "grad_norm": 38.45261764526367,
29
+ "learning_rate": 0.00029301997649823735,
30
+ "loss": 81.141572265625,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.26936026936026936,
35
+ "grad_norm": 30.12755584716797,
36
+ "learning_rate": 0.0002859694477085781,
37
+ "loss": 71.679775390625,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.3367003367003367,
42
+ "grad_norm": 26.099262237548828,
43
+ "learning_rate": 0.0002789189189189189,
44
+ "loss": 67.6156201171875,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.3367003367003367,
49
+ "eval_loss": 6.426710605621338,
50
+ "eval_runtime": 71.9526,
51
+ "eval_samples_per_second": 13.342,
52
+ "eval_steps_per_second": 3.336,
53
+ "step": 500
54
+ },
55
+ {
56
+ "epoch": 0.40404040404040403,
57
+ "grad_norm": 25.531190872192383,
58
+ "learning_rate": 0.00027186839012925966,
59
+ "loss": 65.3996484375,
60
+ "step": 600
61
+ },
62
+ {
63
+ "epoch": 0.4713804713804714,
64
+ "grad_norm": 25.456987380981445,
65
+ "learning_rate": 0.00026481786133960043,
66
+ "loss": 63.7711328125,
67
+ "step": 700
68
+ },
69
+ {
70
+ "epoch": 0.5387205387205387,
71
+ "grad_norm": 24.871572494506836,
72
+ "learning_rate": 0.00025776733254994125,
73
+ "loss": 62.25517578125,
74
+ "step": 800
75
+ },
76
+ {
77
+ "epoch": 0.6060606060606061,
78
+ "grad_norm": 29.645320892333984,
79
+ "learning_rate": 0.000250716803760282,
80
+ "loss": 60.900390625,
81
+ "step": 900
82
+ },
83
+ {
84
+ "epoch": 0.6734006734006734,
85
+ "grad_norm": 25.431486129760742,
86
+ "learning_rate": 0.00024366627497062276,
87
+ "loss": 60.542490234375,
88
+ "step": 1000
89
+ },
90
+ {
91
+ "epoch": 0.6734006734006734,
92
+ "eval_loss": 5.928141117095947,
93
+ "eval_runtime": 71.83,
94
+ "eval_samples_per_second": 13.365,
95
+ "eval_steps_per_second": 3.341,
96
+ "step": 1000
97
+ }
98
+ ],
99
+ "logging_steps": 100,
100
+ "max_steps": 4455,
101
+ "num_input_tokens_seen": 0,
102
+ "num_train_epochs": 3,
103
+ "save_steps": 1000,
104
+ "stateful_callbacks": {
105
+ "TrainerControl": {
106
+ "args": {
107
+ "should_epoch_stop": false,
108
+ "should_evaluate": false,
109
+ "should_log": false,
110
+ "should_save": true,
111
+ "should_training_stop": false
112
+ },
113
+ "attributes": {}
114
+ }
115
+ },
116
+ "total_flos": 3857038975549440.0,
117
+ "train_batch_size": 8,
118
+ "trial_name": null,
119
+ "trial_params": null
120
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a4c16ea673b8d89654d8d1ba2bab528bba3bb695f6bdd28d54f78ab30bfb17
3
+ size 5137