Hugging Face's logo

Woondsc
/
opus-mt-ko-en-medterm

Translation
Transformers
TensorBoard
Safetensors
Korean
English
marian
text2text-generation
Pytorch
Model card Files Metrics Community
Woondsc commited on
Commit
bc794eb
·
verified ·
1 Parent(s): fe24bd0

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +14 -0
  2. checkpoint-10275/config.json +56 -0
  3. checkpoint-10275/generation_config.json +16 -0
  4. checkpoint-10275/model.safetensors +3 -0
  5. checkpoint-10275/optimizer.pt +3 -0
  6. checkpoint-10275/rng_state.pth +3 -0
  7. checkpoint-10275/scheduler.pt +3 -0
  8. checkpoint-10275/source.spm +3 -0
  9. checkpoint-10275/special_tokens_map.json +5 -0
  10. checkpoint-10275/target.spm +3 -0
  11. checkpoint-10275/tokenizer_config.json +39 -0
  12. checkpoint-10275/trainer_state.json +248 -0
  13. checkpoint-10275/training_args.bin +3 -0
  14. checkpoint-10275/vocab.json +0 -0
  15. checkpoint-12330/config.json +56 -0
  16. checkpoint-12330/generation_config.json +16 -0
  17. checkpoint-12330/model.safetensors +3 -0
  18. checkpoint-12330/optimizer.pt +3 -0
  19. checkpoint-12330/rng_state.pth +3 -0
  20. checkpoint-12330/scheduler.pt +3 -0
  21. checkpoint-12330/source.spm +3 -0
  22. checkpoint-12330/special_tokens_map.json +5 -0
  23. checkpoint-12330/target.spm +3 -0
  24. checkpoint-12330/tokenizer_config.json +39 -0
  25. checkpoint-12330/trainer_state.json +291 -0
  26. checkpoint-12330/training_args.bin +3 -0
  27. checkpoint-12330/vocab.json +0 -0
  28. checkpoint-2055/config.json +56 -0
  29. checkpoint-2055/generation_config.json +16 -0
  30. checkpoint-2055/model.safetensors +3 -0
  31. checkpoint-2055/optimizer.pt +3 -0
  32. checkpoint-2055/rng_state.pth +3 -0
  33. checkpoint-2055/scheduler.pt +3 -0
  34. checkpoint-2055/source.spm +3 -0
  35. checkpoint-2055/special_tokens_map.json +5 -0
  36. checkpoint-2055/target.spm +3 -0
  37. checkpoint-2055/tokenizer_config.json +39 -0
  38. checkpoint-2055/trainer_state.json +76 -0
  39. checkpoint-2055/training_args.bin +3 -0
  40. checkpoint-2055/vocab.json +0 -0
  41. checkpoint-4110/config.json +56 -0
  42. checkpoint-4110/generation_config.json +16 -0
  43. checkpoint-4110/model.safetensors +3 -0
  44. checkpoint-4110/optimizer.pt +3 -0
  45. checkpoint-4110/rng_state.pth +3 -0
  46. checkpoint-4110/scheduler.pt +3 -0
  47. checkpoint-4110/source.spm +3 -0
  48. checkpoint-4110/special_tokens_map.json +5 -0
  49. checkpoint-4110/target.spm +3 -0
  50. checkpoint-4110/tokenizer_config.json +39 -0
.gitattributes CHANGED
@@ -33,3 +33,17 @@ 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
+ checkpoint-10275/source.spm filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-10275/target.spm filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-12330/source.spm filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-12330/target.spm filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-2055/source.spm filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-2055/target.spm filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-4110/source.spm filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint-4110/target.spm filter=lfs diff=lfs merge=lfs -text
44
+ checkpoint-6165/source.spm filter=lfs diff=lfs merge=lfs -text
45
+ checkpoint-6165/target.spm filter=lfs diff=lfs merge=lfs -text
46
+ checkpoint-8220/source.spm filter=lfs diff=lfs merge=lfs -text
47
+ checkpoint-8220/target.spm filter=lfs diff=lfs merge=lfs -text
48
+ source.spm filter=lfs diff=lfs merge=lfs -text
49
+ target.spm filter=lfs diff=lfs merge=lfs -text
checkpoint-10275/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ko-en",
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": 65000,
20
+ "decoder_vocab_size": 65001,
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": 65001,
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": 65000,
49
+ "scale_embedding": true,
50
+ "share_encoder_decoder_embeddings": true,
51
+ "static_position_embeddings": true,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.48.2",
54
+ "use_cache": true,
55
+ "vocab_size": 65001
56
+ }
checkpoint-10275/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 65000
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 65000,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 6,
13
+ "pad_token_id": 65000,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.48.2"
16
+ }
checkpoint-10275/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f4e3f7789d38c105efa2c6e6e04d38e30c63f68011e6683c2d5e8185a72ba58
3
+ size 309965092
checkpoint-10275/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9cd1e1259bafae641c5c4ab25bb14c443c63d628045ff7a2df9f330f266e95d
3
+ size 619563642
checkpoint-10275/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ccb58965489e6c35cc01e2cf60c91337706ca229a2b669da1c88d9dba64aea8
3
+ size 14244
checkpoint-10275/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81ae6b013192aa31c073f7f95d5ab45856e22196a63e3761f7ccf395a42e1e8
3
+ size 1064
checkpoint-10275/source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9496f7c2be9aecb84c751ae9f35a875915dde8e3892f652a5c76811ab2a0f49
3
+ size 841805
checkpoint-10275/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-10275/target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1531ac8576fe64267dfca0dc33950a6e9a2d3fd9e05346558ad7ea5ee0e65bf
3
+ size 813126
checkpoint-10275/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "65000": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": false,
29
+ "eos_token": "</s>",
30
+ "extra_special_tokens": {},
31
+ "model_max_length": 512,
32
+ "pad_token": "<pad>",
33
+ "separate_vocabs": false,
34
+ "source_lang": "kor",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "eng",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }
checkpoint-10275/trainer_state.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 10275,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.24330900243309003,
13
+ "grad_norm": 14.526427268981934,
14
+ "learning_rate": 1.9195458231954583e-05,
15
+ "loss": 3.5943,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.48661800486618007,
20
+ "grad_norm": 16.526565551757812,
21
+ "learning_rate": 1.8384428223844285e-05,
22
+ "loss": 3.1431,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.7299270072992701,
27
+ "grad_norm": 11.656450271606445,
28
+ "learning_rate": 1.7573398215733984e-05,
29
+ "loss": 2.9201,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.9732360097323601,
34
+ "grad_norm": 13.380396842956543,
35
+ "learning_rate": 1.6762368207623682e-05,
36
+ "loss": 2.7711,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_bleu": 12.810223940577195,
42
+ "eval_loss": 2.420867681503296,
43
+ "eval_rouge": {
44
+ "rouge1": 0.30991633445023503,
45
+ "rouge2": 0.11181858129315748,
46
+ "rougeL": 0.3092627118644087,
47
+ "rougeLsum": 0.30911397265634744
48
+ },
49
+ "eval_runtime": 264.2267,
50
+ "eval_samples_per_second": 33.494,
51
+ "eval_steps_per_second": 2.097,
52
+ "step": 2055
53
+ },
54
+ {
55
+ "epoch": 1.2165450121654502,
56
+ "grad_norm": 13.43653392791748,
57
+ "learning_rate": 1.5951338199513384e-05,
58
+ "loss": 2.3949,
59
+ "step": 2500
60
+ },
61
+ {
62
+ "epoch": 1.4598540145985401,
63
+ "grad_norm": 13.36623764038086,
64
+ "learning_rate": 1.5140308191403083e-05,
65
+ "loss": 2.2468,
66
+ "step": 3000
67
+ },
68
+ {
69
+ "epoch": 1.7031630170316303,
70
+ "grad_norm": 12.249001502990723,
71
+ "learning_rate": 1.4329278183292783e-05,
72
+ "loss": 2.2239,
73
+ "step": 3500
74
+ },
75
+ {
76
+ "epoch": 1.94647201946472,
77
+ "grad_norm": 14.571913719177246,
78
+ "learning_rate": 1.3518248175182482e-05,
79
+ "loss": 2.1585,
80
+ "step": 4000
81
+ },
82
+ {
83
+ "epoch": 2.0,
84
+ "eval_bleu": 18.428136367860084,
85
+ "eval_loss": 2.1254029273986816,
86
+ "eval_rouge": {
87
+ "rouge1": 0.3476506591337114,
88
+ "rouge2": 0.13975840731772934,
89
+ "rougeL": 0.34719576719576883,
90
+ "rougeLsum": 0.3470716527665696
91
+ },
92
+ "eval_runtime": 264.8536,
93
+ "eval_samples_per_second": 33.415,
94
+ "eval_steps_per_second": 2.092,
95
+ "step": 4110
96
+ },
97
+ {
98
+ "epoch": 2.18978102189781,
99
+ "grad_norm": 12.905760765075684,
100
+ "learning_rate": 1.2707218167072182e-05,
101
+ "loss": 1.9148,
102
+ "step": 4500
103
+ },
104
+ {
105
+ "epoch": 2.4330900243309004,
106
+ "grad_norm": 13.12757682800293,
107
+ "learning_rate": 1.1896188158961884e-05,
108
+ "loss": 1.8616,
109
+ "step": 5000
110
+ },
111
+ {
112
+ "epoch": 2.67639902676399,
113
+ "grad_norm": 13.198368072509766,
114
+ "learning_rate": 1.1085158150851583e-05,
115
+ "loss": 1.8182,
116
+ "step": 5500
117
+ },
118
+ {
119
+ "epoch": 2.9197080291970803,
120
+ "grad_norm": 11.821575164794922,
121
+ "learning_rate": 1.0274128142741283e-05,
122
+ "loss": 1.8343,
123
+ "step": 6000
124
+ },
125
+ {
126
+ "epoch": 3.0,
127
+ "eval_bleu": 20.618391393580144,
128
+ "eval_loss": 1.9738637208938599,
129
+ "eval_rouge": {
130
+ "rouge1": 0.3669825372367759,
131
+ "rouge2": 0.153052954891938,
132
+ "rougeL": 0.3663996747132363,
133
+ "rougeLsum": 0.36649283390808984
134
+ },
135
+ "eval_runtime": 277.0353,
136
+ "eval_samples_per_second": 31.945,
137
+ "eval_steps_per_second": 2.0,
138
+ "step": 6165
139
+ },
140
+ {
141
+ "epoch": 3.1630170316301705,
142
+ "grad_norm": 9.874231338500977,
143
+ "learning_rate": 9.463098134630983e-06,
144
+ "loss": 1.652,
145
+ "step": 6500
146
+ },
147
+ {
148
+ "epoch": 3.40632603406326,
149
+ "grad_norm": 13.481595993041992,
150
+ "learning_rate": 8.652068126520682e-06,
151
+ "loss": 1.5882,
152
+ "step": 7000
153
+ },
154
+ {
155
+ "epoch": 3.6496350364963503,
156
+ "grad_norm": 12.598729133605957,
157
+ "learning_rate": 7.841038118410382e-06,
158
+ "loss": 1.5795,
159
+ "step": 7500
160
+ },
161
+ {
162
+ "epoch": 3.8929440389294405,
163
+ "grad_norm": 10.078117370605469,
164
+ "learning_rate": 7.030008110300081e-06,
165
+ "loss": 1.6081,
166
+ "step": 8000
167
+ },
168
+ {
169
+ "epoch": 4.0,
170
+ "eval_bleu": 21.371071937079442,
171
+ "eval_loss": 1.8978888988494873,
172
+ "eval_rouge": {
173
+ "rouge1": 0.3791688230162823,
174
+ "rouge2": 0.16206698950766746,
175
+ "rougeL": 0.37860440156203046,
176
+ "rougeLsum": 0.3785680330341368
177
+ },
178
+ "eval_runtime": 270.921,
179
+ "eval_samples_per_second": 32.666,
180
+ "eval_steps_per_second": 2.045,
181
+ "step": 8220
182
+ },
183
+ {
184
+ "epoch": 4.13625304136253,
185
+ "grad_norm": 13.678194999694824,
186
+ "learning_rate": 6.2206001622060015e-06,
187
+ "loss": 1.5118,
188
+ "step": 8500
189
+ },
190
+ {
191
+ "epoch": 4.37956204379562,
192
+ "grad_norm": 11.986939430236816,
193
+ "learning_rate": 5.409570154095703e-06,
194
+ "loss": 1.445,
195
+ "step": 9000
196
+ },
197
+ {
198
+ "epoch": 4.622871046228711,
199
+ "grad_norm": 12.918234825134277,
200
+ "learning_rate": 4.598540145985402e-06,
201
+ "loss": 1.447,
202
+ "step": 9500
203
+ },
204
+ {
205
+ "epoch": 4.866180048661801,
206
+ "grad_norm": 10.726964950561523,
207
+ "learning_rate": 3.7875101378751015e-06,
208
+ "loss": 1.406,
209
+ "step": 10000
210
+ },
211
+ {
212
+ "epoch": 5.0,
213
+ "eval_bleu": 22.3831585320865,
214
+ "eval_loss": 1.859816074371338,
215
+ "eval_rouge": {
216
+ "rouge1": 0.3916949600932663,
217
+ "rouge2": 0.16823271455474847,
218
+ "rougeL": 0.39121746928526785,
219
+ "rougeLsum": 0.39116348309568805
220
+ },
221
+ "eval_runtime": 277.4168,
222
+ "eval_samples_per_second": 31.901,
223
+ "eval_steps_per_second": 1.997,
224
+ "step": 10275
225
+ }
226
+ ],
227
+ "logging_steps": 500,
228
+ "max_steps": 12330,
229
+ "num_input_tokens_seen": 0,
230
+ "num_train_epochs": 6,
231
+ "save_steps": 500,
232
+ "stateful_callbacks": {
233
+ "TrainerControl": {
234
+ "args": {
235
+ "should_epoch_stop": false,
236
+ "should_evaluate": false,
237
+ "should_log": false,
238
+ "should_save": true,
239
+ "should_training_stop": false
240
+ },
241
+ "attributes": {}
242
+ }
243
+ },
244
+ "total_flos": 859319313629184.0,
245
+ "train_batch_size": 16,
246
+ "trial_name": null,
247
+ "trial_params": null
248
+ }
checkpoint-10275/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f23aa42f71fb49bdefda103a1093e935cb64d8290342e3b02d230058bfcccbc
3
+ size 5432
checkpoint-10275/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12330/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ko-en",
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": 65000,
20
+ "decoder_vocab_size": 65001,
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": 65001,
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": 65000,
49
+ "scale_embedding": true,
50
+ "share_encoder_decoder_embeddings": true,
51
+ "static_position_embeddings": true,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.48.2",
54
+ "use_cache": true,
55
+ "vocab_size": 65001
56
+ }
checkpoint-12330/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 65000
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 65000,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 6,
13
+ "pad_token_id": 65000,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.48.2"
16
+ }
checkpoint-12330/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b026240c8ec3e2f82cad42ffd832821afecfc924fd7dfdf35fa9dcefa9e8f18
3
+ size 309965092
checkpoint-12330/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197f5138030a4addd203dceaeccca75f703ae995bbadb4516d43442ec2123b0c
3
+ size 619563642
checkpoint-12330/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd47ba0a7e6ce7e5ee851ca82a5aefd6a5a08aec1886890e8730f3e5cb008eee
3
+ size 14244
checkpoint-12330/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc590f19d55470cfe8087ce46f286ba7419d17991cd31666230d9d7d3795f09
3
+ size 1064
checkpoint-12330/source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9496f7c2be9aecb84c751ae9f35a875915dde8e3892f652a5c76811ab2a0f49
3
+ size 841805
checkpoint-12330/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-12330/target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1531ac8576fe64267dfca0dc33950a6e9a2d3fd9e05346558ad7ea5ee0e65bf
3
+ size 813126
checkpoint-12330/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "65000": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": false,
29
+ "eos_token": "</s>",
30
+ "extra_special_tokens": {},
31
+ "model_max_length": 512,
32
+ "pad_token": "<pad>",
33
+ "separate_vocabs": false,
34
+ "source_lang": "kor",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "eng",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }
checkpoint-12330/trainer_state.json ADDED
@@ -0,0 +1,291 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 12330,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.24330900243309003,
13
+ "grad_norm": 14.526427268981934,
14
+ "learning_rate": 1.9195458231954583e-05,
15
+ "loss": 3.5943,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.48661800486618007,
20
+ "grad_norm": 16.526565551757812,
21
+ "learning_rate": 1.8384428223844285e-05,
22
+ "loss": 3.1431,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.7299270072992701,
27
+ "grad_norm": 11.656450271606445,
28
+ "learning_rate": 1.7573398215733984e-05,
29
+ "loss": 2.9201,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.9732360097323601,
34
+ "grad_norm": 13.380396842956543,
35
+ "learning_rate": 1.6762368207623682e-05,
36
+ "loss": 2.7711,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_bleu": 12.810223940577195,
42
+ "eval_loss": 2.420867681503296,
43
+ "eval_rouge": {
44
+ "rouge1": 0.30991633445023503,
45
+ "rouge2": 0.11181858129315748,
46
+ "rougeL": 0.3092627118644087,
47
+ "rougeLsum": 0.30911397265634744
48
+ },
49
+ "eval_runtime": 264.2267,
50
+ "eval_samples_per_second": 33.494,
51
+ "eval_steps_per_second": 2.097,
52
+ "step": 2055
53
+ },
54
+ {
55
+ "epoch": 1.2165450121654502,
56
+ "grad_norm": 13.43653392791748,
57
+ "learning_rate": 1.5951338199513384e-05,
58
+ "loss": 2.3949,
59
+ "step": 2500
60
+ },
61
+ {
62
+ "epoch": 1.4598540145985401,
63
+ "grad_norm": 13.36623764038086,
64
+ "learning_rate": 1.5140308191403083e-05,
65
+ "loss": 2.2468,
66
+ "step": 3000
67
+ },
68
+ {
69
+ "epoch": 1.7031630170316303,
70
+ "grad_norm": 12.249001502990723,
71
+ "learning_rate": 1.4329278183292783e-05,
72
+ "loss": 2.2239,
73
+ "step": 3500
74
+ },
75
+ {
76
+ "epoch": 1.94647201946472,
77
+ "grad_norm": 14.571913719177246,
78
+ "learning_rate": 1.3518248175182482e-05,
79
+ "loss": 2.1585,
80
+ "step": 4000
81
+ },
82
+ {
83
+ "epoch": 2.0,
84
+ "eval_bleu": 18.428136367860084,
85
+ "eval_loss": 2.1254029273986816,
86
+ "eval_rouge": {
87
+ "rouge1": 0.3476506591337114,
88
+ "rouge2": 0.13975840731772934,
89
+ "rougeL": 0.34719576719576883,
90
+ "rougeLsum": 0.3470716527665696
91
+ },
92
+ "eval_runtime": 264.8536,
93
+ "eval_samples_per_second": 33.415,
94
+ "eval_steps_per_second": 2.092,
95
+ "step": 4110
96
+ },
97
+ {
98
+ "epoch": 2.18978102189781,
99
+ "grad_norm": 12.905760765075684,
100
+ "learning_rate": 1.2707218167072182e-05,
101
+ "loss": 1.9148,
102
+ "step": 4500
103
+ },
104
+ {
105
+ "epoch": 2.4330900243309004,
106
+ "grad_norm": 13.12757682800293,
107
+ "learning_rate": 1.1896188158961884e-05,
108
+ "loss": 1.8616,
109
+ "step": 5000
110
+ },
111
+ {
112
+ "epoch": 2.67639902676399,
113
+ "grad_norm": 13.198368072509766,
114
+ "learning_rate": 1.1085158150851583e-05,
115
+ "loss": 1.8182,
116
+ "step": 5500
117
+ },
118
+ {
119
+ "epoch": 2.9197080291970803,
120
+ "grad_norm": 11.821575164794922,
121
+ "learning_rate": 1.0274128142741283e-05,
122
+ "loss": 1.8343,
123
+ "step": 6000
124
+ },
125
+ {
126
+ "epoch": 3.0,
127
+ "eval_bleu": 20.618391393580144,
128
+ "eval_loss": 1.9738637208938599,
129
+ "eval_rouge": {
130
+ "rouge1": 0.3669825372367759,
131
+ "rouge2": 0.153052954891938,
132
+ "rougeL": 0.3663996747132363,
133
+ "rougeLsum": 0.36649283390808984
134
+ },
135
+ "eval_runtime": 277.0353,
136
+ "eval_samples_per_second": 31.945,
137
+ "eval_steps_per_second": 2.0,
138
+ "step": 6165
139
+ },
140
+ {
141
+ "epoch": 3.1630170316301705,
142
+ "grad_norm": 9.874231338500977,
143
+ "learning_rate": 9.463098134630983e-06,
144
+ "loss": 1.652,
145
+ "step": 6500
146
+ },
147
+ {
148
+ "epoch": 3.40632603406326,
149
+ "grad_norm": 13.481595993041992,
150
+ "learning_rate": 8.652068126520682e-06,
151
+ "loss": 1.5882,
152
+ "step": 7000
153
+ },
154
+ {
155
+ "epoch": 3.6496350364963503,
156
+ "grad_norm": 12.598729133605957,
157
+ "learning_rate": 7.841038118410382e-06,
158
+ "loss": 1.5795,
159
+ "step": 7500
160
+ },
161
+ {
162
+ "epoch": 3.8929440389294405,
163
+ "grad_norm": 10.078117370605469,
164
+ "learning_rate": 7.030008110300081e-06,
165
+ "loss": 1.6081,
166
+ "step": 8000
167
+ },
168
+ {
169
+ "epoch": 4.0,
170
+ "eval_bleu": 21.371071937079442,
171
+ "eval_loss": 1.8978888988494873,
172
+ "eval_rouge": {
173
+ "rouge1": 0.3791688230162823,
174
+ "rouge2": 0.16206698950766746,
175
+ "rougeL": 0.37860440156203046,
176
+ "rougeLsum": 0.3785680330341368
177
+ },
178
+ "eval_runtime": 270.921,
179
+ "eval_samples_per_second": 32.666,
180
+ "eval_steps_per_second": 2.045,
181
+ "step": 8220
182
+ },
183
+ {
184
+ "epoch": 4.13625304136253,
185
+ "grad_norm": 13.678194999694824,
186
+ "learning_rate": 6.2206001622060015e-06,
187
+ "loss": 1.5118,
188
+ "step": 8500
189
+ },
190
+ {
191
+ "epoch": 4.37956204379562,
192
+ "grad_norm": 11.986939430236816,
193
+ "learning_rate": 5.409570154095703e-06,
194
+ "loss": 1.445,
195
+ "step": 9000
196
+ },
197
+ {
198
+ "epoch": 4.622871046228711,
199
+ "grad_norm": 12.918234825134277,
200
+ "learning_rate": 4.598540145985402e-06,
201
+ "loss": 1.447,
202
+ "step": 9500
203
+ },
204
+ {
205
+ "epoch": 4.866180048661801,
206
+ "grad_norm": 10.726964950561523,
207
+ "learning_rate": 3.7875101378751015e-06,
208
+ "loss": 1.406,
209
+ "step": 10000
210
+ },
211
+ {
212
+ "epoch": 5.0,
213
+ "eval_bleu": 22.3831585320865,
214
+ "eval_loss": 1.859816074371338,
215
+ "eval_rouge": {
216
+ "rouge1": 0.3916949600932663,
217
+ "rouge2": 0.16823271455474847,
218
+ "rougeL": 0.39121746928526785,
219
+ "rougeLsum": 0.39116348309568805
220
+ },
221
+ "eval_runtime": 277.4168,
222
+ "eval_samples_per_second": 31.901,
223
+ "eval_steps_per_second": 1.997,
224
+ "step": 10275
225
+ },
226
+ {
227
+ "epoch": 5.109489051094891,
228
+ "grad_norm": 15.405741691589355,
229
+ "learning_rate": 2.979724249797243e-06,
230
+ "loss": 1.4047,
231
+ "step": 10500
232
+ },
233
+ {
234
+ "epoch": 5.35279805352798,
235
+ "grad_norm": 10.873234748840332,
236
+ "learning_rate": 2.1686942416869423e-06,
237
+ "loss": 1.3599,
238
+ "step": 11000
239
+ },
240
+ {
241
+ "epoch": 5.59610705596107,
242
+ "grad_norm": 10.827215194702148,
243
+ "learning_rate": 1.3576642335766423e-06,
244
+ "loss": 1.33,
245
+ "step": 11500
246
+ },
247
+ {
248
+ "epoch": 5.839416058394161,
249
+ "grad_norm": 12.577991485595703,
250
+ "learning_rate": 5.466342254663423e-07,
251
+ "loss": 1.3453,
252
+ "step": 12000
253
+ },
254
+ {
255
+ "epoch": 6.0,
256
+ "eval_bleu": 23.393142474562815,
257
+ "eval_loss": 1.8506520986557007,
258
+ "eval_rouge": {
259
+ "rouge1": 0.3935306250560502,
260
+ "rouge2": 0.16916814635458705,
261
+ "rougeL": 0.393161689534573,
262
+ "rougeLsum": 0.3930333602367517
263
+ },
264
+ "eval_runtime": 268.6729,
265
+ "eval_samples_per_second": 32.94,
266
+ "eval_steps_per_second": 2.062,
267
+ "step": 12330
268
+ }
269
+ ],
270
+ "logging_steps": 500,
271
+ "max_steps": 12330,
272
+ "num_input_tokens_seen": 0,
273
+ "num_train_epochs": 6,
274
+ "save_steps": 500,
275
+ "stateful_callbacks": {
276
+ "TrainerControl": {
277
+ "args": {
278
+ "should_epoch_stop": false,
279
+ "should_evaluate": false,
280
+ "should_log": false,
281
+ "should_save": true,
282
+ "should_training_stop": true
283
+ },
284
+ "attributes": {}
285
+ }
286
+ },
287
+ "total_flos": 1030951237386240.0,
288
+ "train_batch_size": 16,
289
+ "trial_name": null,
290
+ "trial_params": null
291
+ }
checkpoint-12330/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f23aa42f71fb49bdefda103a1093e935cb64d8290342e3b02d230058bfcccbc
3
+ size 5432
checkpoint-12330/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2055/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ko-en",
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": 65000,
20
+ "decoder_vocab_size": 65001,
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": 65001,
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": 65000,
49
+ "scale_embedding": true,
50
+ "share_encoder_decoder_embeddings": true,
51
+ "static_position_embeddings": true,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.48.2",
54
+ "use_cache": true,
55
+ "vocab_size": 65001
56
+ }
checkpoint-2055/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 65000
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 65000,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 6,
13
+ "pad_token_id": 65000,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.48.2"
16
+ }
checkpoint-2055/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38bdf0d55e3029bb0bdb30889b9d3a6de6b214d908934fcd75b8d5c9a6ea361f
3
+ size 309965092
checkpoint-2055/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4509248cd7da9bce63249bfda68d323a34384fad362ea7b04471e6e37a70fe85
3
+ size 619563642
checkpoint-2055/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42cdf8930165de9a08694ccec3e966908836cc2bbbe74efe9e31c7ca0498492
3
+ size 14244
checkpoint-2055/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1a94c4f6c1e886e8b654ad897d78869269c7a42d041cf138af0708606a1ab7
3
+ size 1064
checkpoint-2055/source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9496f7c2be9aecb84c751ae9f35a875915dde8e3892f652a5c76811ab2a0f49
3
+ size 841805
checkpoint-2055/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-2055/target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1531ac8576fe64267dfca0dc33950a6e9a2d3fd9e05346558ad7ea5ee0e65bf
3
+ size 813126
checkpoint-2055/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "65000": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": false,
29
+ "eos_token": "</s>",
30
+ "extra_special_tokens": {},
31
+ "model_max_length": 512,
32
+ "pad_token": "<pad>",
33
+ "separate_vocabs": false,
34
+ "source_lang": "kor",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "eng",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }
checkpoint-2055/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2055,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.24330900243309003,
13
+ "grad_norm": 14.526427268981934,
14
+ "learning_rate": 1.9195458231954583e-05,
15
+ "loss": 3.5943,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.48661800486618007,
20
+ "grad_norm": 16.526565551757812,
21
+ "learning_rate": 1.8384428223844285e-05,
22
+ "loss": 3.1431,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.7299270072992701,
27
+ "grad_norm": 11.656450271606445,
28
+ "learning_rate": 1.7573398215733984e-05,
29
+ "loss": 2.9201,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.9732360097323601,
34
+ "grad_norm": 13.380396842956543,
35
+ "learning_rate": 1.6762368207623682e-05,
36
+ "loss": 2.7711,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_bleu": 12.810223940577195,
42
+ "eval_loss": 2.420867681503296,
43
+ "eval_rouge": {
44
+ "rouge1": 0.30991633445023503,
45
+ "rouge2": 0.11181858129315748,
46
+ "rougeL": 0.3092627118644087,
47
+ "rougeLsum": 0.30911397265634744
48
+ },
49
+ "eval_runtime": 264.2267,
50
+ "eval_samples_per_second": 33.494,
51
+ "eval_steps_per_second": 2.097,
52
+ "step": 2055
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 12330,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 6,
59
+ "save_steps": 500,
60
+ "stateful_callbacks": {
61
+ "TrainerControl": {
62
+ "args": {
63
+ "should_epoch_stop": false,
64
+ "should_evaluate": false,
65
+ "should_log": false,
66
+ "should_save": true,
67
+ "should_training_stop": false
68
+ },
69
+ "attributes": {}
70
+ }
71
+ },
72
+ "total_flos": 172120801738752.0,
73
+ "train_batch_size": 16,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
checkpoint-2055/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f23aa42f71fb49bdefda103a1093e935cb64d8290342e3b02d230058bfcccbc
3
+ size 5432
checkpoint-2055/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4110/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ko-en",
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": 65000,
20
+ "decoder_vocab_size": 65001,
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": 65001,
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": 65000,
49
+ "scale_embedding": true,
50
+ "share_encoder_decoder_embeddings": true,
51
+ "static_position_embeddings": true,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.48.2",
54
+ "use_cache": true,
55
+ "vocab_size": 65001
56
+ }
checkpoint-4110/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 65000
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 65000,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 6,
13
+ "pad_token_id": 65000,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.48.2"
16
+ }
checkpoint-4110/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4845d86a1d166e372636c50ba7afd2dbb8207d0c43a87650c04be7bbbf316db5
3
+ size 309965092
checkpoint-4110/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ac2fba4b592bb1c58e6561231ccf8d7717aaa78ec3a37f276214c52e1dcda6
3
+ size 619563642
checkpoint-4110/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e591177b805f0c379b730544849b0bea9f7c43f8b57876d46ca1e63747a4f1e
3
+ size 14244
checkpoint-4110/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10dc2a776ee952c1f08a2eca5de9a8899edc33950a9b8759306e974c3bd30dcf
3
+ size 1064
checkpoint-4110/source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9496f7c2be9aecb84c751ae9f35a875915dde8e3892f652a5c76811ab2a0f49
3
+ size 841805
checkpoint-4110/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-4110/target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1531ac8576fe64267dfca0dc33950a6e9a2d3fd9e05346558ad7ea5ee0e65bf
3
+ size 813126
checkpoint-4110/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "65000": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": false,
29
+ "eos_token": "</s>",
30
+ "extra_special_tokens": {},
31
+ "model_max_length": 512,
32
+ "pad_token": "<pad>",
33
+ "separate_vocabs": false,
34
+ "source_lang": "kor",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "eng",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }