Sag1012 commited on
Commit
fb3ffa7
·
verified ·
1 Parent(s): b94f2d5

Upload model finetune MarianMT - ver1

Browse files
MarianMT/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-vi",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "swish",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "MarianMTModel"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 512,
15
+ "decoder_attention_heads": 8,
16
+ "decoder_ffn_dim": 2048,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 53684,
20
+ "decoder_vocab_size": 53685,
21
+ "dropout": 0.1,
22
+ "encoder_attention_heads": 8,
23
+ "encoder_ffn_dim": 2048,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 0,
27
+ "extra_pos_embeddings": 53685,
28
+ "forced_eos_token_id": 0,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_length": null,
42
+ "max_position_embeddings": 512,
43
+ "model_type": "marian",
44
+ "normalize_before": false,
45
+ "normalize_embedding": false,
46
+ "num_beams": null,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 53684,
49
+ "scale_embedding": true,
50
+ "share_encoder_decoder_embeddings": true,
51
+ "static_position_embeddings": true,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.46.3",
54
+ "use_cache": true,
55
+ "vocab_size": 53685
56
+ }
MarianMT/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 53684
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 53684,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 53684,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.46.3"
16
+ }
MarianMT/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff66be42b5c739bcce500ed364e8ddc19428a432660e6c57ba5b247844d8d21
3
+ size 286744660
MarianMT/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0b621c760ba933a9c48ee1f96cc3fc8c9d77e23b4e650f3607251d4efb1476
3
+ size 573213242
MarianMT/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cdc831de453ce7358217699e19f2b9b2a46abb1fe2c2d456532cc183559e3cc
3
+ size 14244
MarianMT/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c26d2fddec2567544b401f62d9f42c610aa12b3e5768cb59a77e9ae328a9aff6
3
+ size 1064
MarianMT/trainer_state.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 9307,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05372300419039433,
13
+ "grad_norm": 2.991044759750366,
14
+ "learning_rate": 4.7313849790480286e-05,
15
+ "loss": 1.8861,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.10744600838078866,
20
+ "grad_norm": 5.196695804595947,
21
+ "learning_rate": 4.462769958096057e-05,
22
+ "loss": 1.7948,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.161169012571183,
27
+ "grad_norm": 3.814988136291504,
28
+ "learning_rate": 4.194154937144085e-05,
29
+ "loss": 1.7804,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.21489201676157732,
34
+ "grad_norm": 2.7339048385620117,
35
+ "learning_rate": 3.9255399161921137e-05,
36
+ "loss": 1.747,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.26861502095197165,
41
+ "grad_norm": 3.035710096359253,
42
+ "learning_rate": 3.656924895240142e-05,
43
+ "loss": 1.721,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.322338025142366,
48
+ "grad_norm": 2.720536708831787,
49
+ "learning_rate": 3.3883098742881704e-05,
50
+ "loss": 1.7191,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.3760610293327603,
55
+ "grad_norm": 3.523932695388794,
56
+ "learning_rate": 3.119694853336199e-05,
57
+ "loss": 1.7057,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.42978403352315464,
62
+ "grad_norm": 2.8171215057373047,
63
+ "learning_rate": 2.851079832384227e-05,
64
+ "loss": 1.7023,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.4835070377135489,
69
+ "grad_norm": 3.2410666942596436,
70
+ "learning_rate": 2.5824648114322554e-05,
71
+ "loss": 1.6839,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.5372300419039433,
76
+ "grad_norm": 2.8419201374053955,
77
+ "learning_rate": 2.3138497904802838e-05,
78
+ "loss": 1.6678,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.5909530460943376,
83
+ "grad_norm": 3.81278657913208,
84
+ "learning_rate": 2.045234769528312e-05,
85
+ "loss": 1.6508,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.644676050284732,
90
+ "grad_norm": 3.6869781017303467,
91
+ "learning_rate": 1.7766197485763405e-05,
92
+ "loss": 1.6397,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.6983990544751263,
97
+ "grad_norm": 3.0194380283355713,
98
+ "learning_rate": 1.5080047276243688e-05,
99
+ "loss": 1.6355,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.7521220586655206,
104
+ "grad_norm": 3.7461318969726562,
105
+ "learning_rate": 1.2393897066723972e-05,
106
+ "loss": 1.6324,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.805845062855915,
111
+ "grad_norm": 2.7630088329315186,
112
+ "learning_rate": 9.707746857204256e-06,
113
+ "loss": 1.6115,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.8595680670463093,
118
+ "grad_norm": 3.0207743644714355,
119
+ "learning_rate": 7.021596647684539e-06,
120
+ "loss": 1.6415,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.9132910712367036,
125
+ "grad_norm": 2.8768997192382812,
126
+ "learning_rate": 4.335446438164823e-06,
127
+ "loss": 1.6103,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.9670140754270978,
132
+ "grad_norm": 2.9209845066070557,
133
+ "learning_rate": 1.6492962286451057e-06,
134
+ "loss": 1.6273,
135
+ "step": 9000
136
+ }
137
+ ],
138
+ "logging_steps": 500,
139
+ "max_steps": 9307,
140
+ "num_input_tokens_seen": 0,
141
+ "num_train_epochs": 1,
142
+ "save_steps": 500,
143
+ "stateful_callbacks": {
144
+ "EarlyStoppingCallback": {
145
+ "args": {
146
+ "early_stopping_patience": 2,
147
+ "early_stopping_threshold": 0.0
148
+ },
149
+ "attributes": {
150
+ "early_stopping_patience_counter": 0
151
+ }
152
+ },
153
+ "TrainerControl": {
154
+ "args": {
155
+ "should_epoch_stop": false,
156
+ "should_evaluate": false,
157
+ "should_log": false,
158
+ "should_save": true,
159
+ "should_training_stop": true
160
+ },
161
+ "attributes": {}
162
+ }
163
+ },
164
+ "total_flos": 5047449588596736.0,
165
+ "train_batch_size": 32,
166
+ "trial_name": null,
167
+ "trial_params": null
168
+ }
MarianMT/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95e2f8c6939482b26b946f678aeabef2b773040cfa2965e756a46de2b067669
3
+ size 5432