Hugging Face's logo

Chen42
/
test_upload

Model card Files
xet
Community
1
Chen42 commited on
Commit
3f179fd
·
verified ·
1 Parent(s): 1a119ce

Add files using upload-large-folder tool

Browse files
Files changed (49) hide show
  1. .gitattributes +4 -0
  2. checkpoint-32000/config.json +175 -0
  3. checkpoint-32000/generation_config.json +5 -0
  4. checkpoint-32000/optimizer.pt +3 -0
  5. checkpoint-32000/pytorch_model.bin +3 -0
  6. checkpoint-32000/rng_state.pth +3 -0
  7. checkpoint-32000/scheduler.pt +3 -0
  8. checkpoint-32000/trainer_state.json +0 -0
  9. checkpoint-32000/training_args.bin +3 -0
  10. checkpoint-48000/config.json +175 -0
  11. checkpoint-48000/generation_config.json +5 -0
  12. checkpoint-48000/optimizer.pt +3 -0
  13. checkpoint-48000/pytorch_model.bin +3 -0
  14. checkpoint-48000/rng_state.pth +3 -0
  15. checkpoint-48000/scheduler.pt +3 -0
  16. checkpoint-48000/trainer_state.json +0 -0
  17. checkpoint-48000/training_args.bin +3 -0
  18. checkpoint-64000/config.json +175 -0
  19. checkpoint-64000/generation_config.json +5 -0
  20. checkpoint-64000/optimizer.pt +3 -0
  21. checkpoint-64000/pytorch_model.bin +3 -0
  22. checkpoint-64000/rng_state.pth +3 -0
  23. checkpoint-64000/scheduler.pt +3 -0
  24. checkpoint-64000/trainer_state.json +3 -0
  25. checkpoint-64000/training_args.bin +3 -0
  26. checkpoint-72000/config.json +175 -0
  27. checkpoint-72000/generation_config.json +5 -0
  28. checkpoint-72000/optimizer.pt +3 -0
  29. checkpoint-72000/pytorch_model.bin +3 -0
  30. checkpoint-72000/rng_state.pth +3 -0
  31. checkpoint-72000/scheduler.pt +3 -0
  32. checkpoint-72000/trainer_state.json +3 -0
  33. checkpoint-72000/training_args.bin +3 -0
  34. checkpoint-76000/config.json +175 -0
  35. checkpoint-76000/generation_config.json +5 -0
  36. checkpoint-76000/optimizer.pt +3 -0
  37. checkpoint-76000/pytorch_model.bin +3 -0
  38. checkpoint-76000/rng_state.pth +3 -0
  39. checkpoint-76000/scheduler.pt +3 -0
  40. checkpoint-76000/trainer_state.json +3 -0
  41. checkpoint-76000/training_args.bin +3 -0
  42. checkpoint-80000/config.json +175 -0
  43. checkpoint-80000/generation_config.json +5 -0
  44. checkpoint-80000/optimizer.pt +3 -0
  45. checkpoint-80000/pytorch_model.bin +3 -0
  46. checkpoint-80000/rng_state.pth +3 -0
  47. checkpoint-80000/scheduler.pt +3 -0
  48. checkpoint-80000/trainer_state.json +3 -0
  49. checkpoint-80000/training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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-80000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-72000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-64000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-76000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
checkpoint-32000/config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "",
8
+ "add_cross_attention": true,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "type_vocab_size": 2,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 21128
83
+ },
84
+ "decoder_start_token_id": 101,
85
+ "encoder": {
86
+ "_attn_implementation_autoset": false,
87
+ "_name_or_path": "",
88
+ "add_cross_attention": false,
89
+ "architectures": [
90
+ "LiltModel"
91
+ ],
92
+ "attention_probs_dropout_prob": 0.1,
93
+ "bad_words_ids": null,
94
+ "begin_suppress_tokens": null,
95
+ "bos_token_id": 0,
96
+ "channel_shrink_ratio": 4,
97
+ "chunk_size_feed_forward": 0,
98
+ "classifier_dropout": null,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": 2,
106
+ "exponential_decay_length_penalty": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "gelu",
111
+ "hidden_dropout_prob": 0.1,
112
+ "hidden_size": 768,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3072,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "label2id": {
122
+ "LABEL_0": 0,
123
+ "LABEL_1": 1
124
+ },
125
+ "layer_norm_eps": 1e-05,
126
+ "length_penalty": 1.0,
127
+ "max_2d_position_embeddings": 1024,
128
+ "max_length": 20,
129
+ "max_position_embeddings": 514,
130
+ "min_length": 0,
131
+ "model_type": "lilt",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 12,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": 1,
142
+ "position_embedding_type": "absolute",
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "suppress_tokens": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tf_legacy_loss": false,
155
+ "tie_encoder_decoder": false,
156
+ "tie_word_embeddings": true,
157
+ "tokenizer_class": null,
158
+ "top_k": 50,
159
+ "top_p": 1.0,
160
+ "torch_dtype": "float32",
161
+ "torchscript": false,
162
+ "type_vocab_size": 1,
163
+ "typical_p": 1.0,
164
+ "use_bfloat16": false,
165
+ "use_cache": true,
166
+ "vocab_size": 50265
167
+ },
168
+ "eos_token_id": 0,
169
+ "is_encoder_decoder": true,
170
+ "model_type": "encoder-decoder",
171
+ "pad_token_id": 0,
172
+ "torch_dtype": "float32",
173
+ "transformers_version": "4.46.3",
174
+ "vocab_size": 21128
175
+ }
checkpoint-32000/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.46.3"
5
+ }
checkpoint-32000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0755cd01b437521e41f7b02cf5590cd4ffca8c27636a9177aa30b724002da6a4
3
+ size 2084199838
checkpoint-32000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3071e8be0745af8a6bb64674383dd9e57564ffd6a0a9006fa8239d79db8cb307
3
+ size 1045902034
checkpoint-32000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfff40427d42bcfa3f5224daf5747cee490ff2d449eeb9e5ca3eb7b5648e82cf
3
+ size 14244
checkpoint-32000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0517228be3ff44e50a22f4daece1cbb9594acdde10851ccd84bb882a441d00
3
+ size 1064
checkpoint-32000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-32000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdf5eae39a7d284a1d8f174a6033461fe03593f519150d0033884476d857a2e
3
+ size 5432
checkpoint-48000/config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "",
8
+ "add_cross_attention": true,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "type_vocab_size": 2,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 21128
83
+ },
84
+ "decoder_start_token_id": 101,
85
+ "encoder": {
86
+ "_attn_implementation_autoset": false,
87
+ "_name_or_path": "",
88
+ "add_cross_attention": false,
89
+ "architectures": [
90
+ "LiltModel"
91
+ ],
92
+ "attention_probs_dropout_prob": 0.1,
93
+ "bad_words_ids": null,
94
+ "begin_suppress_tokens": null,
95
+ "bos_token_id": 0,
96
+ "channel_shrink_ratio": 4,
97
+ "chunk_size_feed_forward": 0,
98
+ "classifier_dropout": null,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": 2,
106
+ "exponential_decay_length_penalty": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "gelu",
111
+ "hidden_dropout_prob": 0.1,
112
+ "hidden_size": 768,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3072,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "label2id": {
122
+ "LABEL_0": 0,
123
+ "LABEL_1": 1
124
+ },
125
+ "layer_norm_eps": 1e-05,
126
+ "length_penalty": 1.0,
127
+ "max_2d_position_embeddings": 1024,
128
+ "max_length": 20,
129
+ "max_position_embeddings": 514,
130
+ "min_length": 0,
131
+ "model_type": "lilt",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 12,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": 1,
142
+ "position_embedding_type": "absolute",
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "suppress_tokens": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tf_legacy_loss": false,
155
+ "tie_encoder_decoder": false,
156
+ "tie_word_embeddings": true,
157
+ "tokenizer_class": null,
158
+ "top_k": 50,
159
+ "top_p": 1.0,
160
+ "torch_dtype": "float32",
161
+ "torchscript": false,
162
+ "type_vocab_size": 1,
163
+ "typical_p": 1.0,
164
+ "use_bfloat16": false,
165
+ "use_cache": true,
166
+ "vocab_size": 50265
167
+ },
168
+ "eos_token_id": 0,
169
+ "is_encoder_decoder": true,
170
+ "model_type": "encoder-decoder",
171
+ "pad_token_id": 0,
172
+ "torch_dtype": "float32",
173
+ "transformers_version": "4.46.3",
174
+ "vocab_size": 21128
175
+ }
checkpoint-48000/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.46.3"
5
+ }
checkpoint-48000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93b97c2982e736ec88aa12e395ed7016f28bf4e9bb19086e4706acfee0051a4d
3
+ size 2084199838
checkpoint-48000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e338d6c11ef26b5803271700d9968cd8b4d9b6485f9e90123056953a062274
3
+ size 1045902034
checkpoint-48000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6ce009b43a0f06492906027072284599eaed72d5a46936c5f1bde71055122b
3
+ size 14244
checkpoint-48000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3919444662b7e5b5456e466b2890b35e40cbe099a04e79dd7a06b9e30461d672
3
+ size 1064
checkpoint-48000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-48000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdf5eae39a7d284a1d8f174a6033461fe03593f519150d0033884476d857a2e
3
+ size 5432
checkpoint-64000/config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "",
8
+ "add_cross_attention": true,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "type_vocab_size": 2,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 21128
83
+ },
84
+ "decoder_start_token_id": 101,
85
+ "encoder": {
86
+ "_attn_implementation_autoset": false,
87
+ "_name_or_path": "",
88
+ "add_cross_attention": false,
89
+ "architectures": [
90
+ "LiltModel"
91
+ ],
92
+ "attention_probs_dropout_prob": 0.1,
93
+ "bad_words_ids": null,
94
+ "begin_suppress_tokens": null,
95
+ "bos_token_id": 0,
96
+ "channel_shrink_ratio": 4,
97
+ "chunk_size_feed_forward": 0,
98
+ "classifier_dropout": null,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": 2,
106
+ "exponential_decay_length_penalty": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "gelu",
111
+ "hidden_dropout_prob": 0.1,
112
+ "hidden_size": 768,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3072,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "label2id": {
122
+ "LABEL_0": 0,
123
+ "LABEL_1": 1
124
+ },
125
+ "layer_norm_eps": 1e-05,
126
+ "length_penalty": 1.0,
127
+ "max_2d_position_embeddings": 1024,
128
+ "max_length": 20,
129
+ "max_position_embeddings": 514,
130
+ "min_length": 0,
131
+ "model_type": "lilt",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 12,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": 1,
142
+ "position_embedding_type": "absolute",
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "suppress_tokens": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tf_legacy_loss": false,
155
+ "tie_encoder_decoder": false,
156
+ "tie_word_embeddings": true,
157
+ "tokenizer_class": null,
158
+ "top_k": 50,
159
+ "top_p": 1.0,
160
+ "torch_dtype": "float32",
161
+ "torchscript": false,
162
+ "type_vocab_size": 1,
163
+ "typical_p": 1.0,
164
+ "use_bfloat16": false,
165
+ "use_cache": true,
166
+ "vocab_size": 50265
167
+ },
168
+ "eos_token_id": 0,
169
+ "is_encoder_decoder": true,
170
+ "model_type": "encoder-decoder",
171
+ "pad_token_id": 0,
172
+ "torch_dtype": "float32",
173
+ "transformers_version": "4.46.3",
174
+ "vocab_size": 21128
175
+ }
checkpoint-64000/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.46.3"
5
+ }
checkpoint-64000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6335505147998d295f4d0fba47213f8ff72502485d4d73708353fb61da714ba
3
+ size 2084199838
checkpoint-64000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:758553d9113771e3441596973d49c5dd58aea3264489e90e2259bc38c938943d
3
+ size 1045902034
checkpoint-64000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a40da86f2c0400083921bd616ced76a77115370f05399c922fed1d4e9cdb08d
3
+ size 14244
checkpoint-64000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0523a5ee7a262d438b82ce907c3c577181d25b08c5e3719c3baf6e3a4050fb5
3
+ size 1064
checkpoint-64000/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1953f5d57dcbde8f4688aa81cfebab9c2eedb428376711915c4a10d648b2aed
3
+ size 10981674
checkpoint-64000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdf5eae39a7d284a1d8f174a6033461fe03593f519150d0033884476d857a2e
3
+ size 5432
checkpoint-72000/config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "",
8
+ "add_cross_attention": true,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "type_vocab_size": 2,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 21128
83
+ },
84
+ "decoder_start_token_id": 101,
85
+ "encoder": {
86
+ "_attn_implementation_autoset": false,
87
+ "_name_or_path": "",
88
+ "add_cross_attention": false,
89
+ "architectures": [
90
+ "LiltModel"
91
+ ],
92
+ "attention_probs_dropout_prob": 0.1,
93
+ "bad_words_ids": null,
94
+ "begin_suppress_tokens": null,
95
+ "bos_token_id": 0,
96
+ "channel_shrink_ratio": 4,
97
+ "chunk_size_feed_forward": 0,
98
+ "classifier_dropout": null,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": 2,
106
+ "exponential_decay_length_penalty": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "gelu",
111
+ "hidden_dropout_prob": 0.1,
112
+ "hidden_size": 768,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3072,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "label2id": {
122
+ "LABEL_0": 0,
123
+ "LABEL_1": 1
124
+ },
125
+ "layer_norm_eps": 1e-05,
126
+ "length_penalty": 1.0,
127
+ "max_2d_position_embeddings": 1024,
128
+ "max_length": 20,
129
+ "max_position_embeddings": 514,
130
+ "min_length": 0,
131
+ "model_type": "lilt",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 12,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": 1,
142
+ "position_embedding_type": "absolute",
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "suppress_tokens": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tf_legacy_loss": false,
155
+ "tie_encoder_decoder": false,
156
+ "tie_word_embeddings": true,
157
+ "tokenizer_class": null,
158
+ "top_k": 50,
159
+ "top_p": 1.0,
160
+ "torch_dtype": "float32",
161
+ "torchscript": false,
162
+ "type_vocab_size": 1,
163
+ "typical_p": 1.0,
164
+ "use_bfloat16": false,
165
+ "use_cache": true,
166
+ "vocab_size": 50265
167
+ },
168
+ "eos_token_id": 0,
169
+ "is_encoder_decoder": true,
170
+ "model_type": "encoder-decoder",
171
+ "pad_token_id": 0,
172
+ "torch_dtype": "float32",
173
+ "transformers_version": "4.46.3",
174
+ "vocab_size": 21128
175
+ }
checkpoint-72000/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.46.3"
5
+ }
checkpoint-72000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c328c0731a50d9621bba4deb54dbfe7f1920725da8bf427f97598090651da608
3
+ size 2084199838
checkpoint-72000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0412980697a54ea133d83e57e40824bf772cb65e082ea7acafbcbe7d1a80d81c
3
+ size 1045902034
checkpoint-72000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc50bcbdbe49ba2c6ef6545793e434f0effc1eaf5753944e62fff20a43bf635
3
+ size 14244
checkpoint-72000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ef8780d4ec07d1fe7b0a87b6ea6acfa8cec8761940b6d8bc4033a0e11ba6a1
3
+ size 1064
checkpoint-72000/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ac921f4fed8979d4491dff4a108d8cb91db806143123faaf1f97a4b6256b3b
3
+ size 12370669
checkpoint-72000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdf5eae39a7d284a1d8f174a6033461fe03593f519150d0033884476d857a2e
3
+ size 5432
checkpoint-76000/config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "",
8
+ "add_cross_attention": true,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "type_vocab_size": 2,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 21128
83
+ },
84
+ "decoder_start_token_id": 101,
85
+ "encoder": {
86
+ "_attn_implementation_autoset": false,
87
+ "_name_or_path": "",
88
+ "add_cross_attention": false,
89
+ "architectures": [
90
+ "LiltModel"
91
+ ],
92
+ "attention_probs_dropout_prob": 0.1,
93
+ "bad_words_ids": null,
94
+ "begin_suppress_tokens": null,
95
+ "bos_token_id": 0,
96
+ "channel_shrink_ratio": 4,
97
+ "chunk_size_feed_forward": 0,
98
+ "classifier_dropout": null,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": 2,
106
+ "exponential_decay_length_penalty": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "gelu",
111
+ "hidden_dropout_prob": 0.1,
112
+ "hidden_size": 768,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3072,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "label2id": {
122
+ "LABEL_0": 0,
123
+ "LABEL_1": 1
124
+ },
125
+ "layer_norm_eps": 1e-05,
126
+ "length_penalty": 1.0,
127
+ "max_2d_position_embeddings": 1024,
128
+ "max_length": 20,
129
+ "max_position_embeddings": 514,
130
+ "min_length": 0,
131
+ "model_type": "lilt",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 12,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": 1,
142
+ "position_embedding_type": "absolute",
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "suppress_tokens": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tf_legacy_loss": false,
155
+ "tie_encoder_decoder": false,
156
+ "tie_word_embeddings": true,
157
+ "tokenizer_class": null,
158
+ "top_k": 50,
159
+ "top_p": 1.0,
160
+ "torch_dtype": "float32",
161
+ "torchscript": false,
162
+ "type_vocab_size": 1,
163
+ "typical_p": 1.0,
164
+ "use_bfloat16": false,
165
+ "use_cache": true,
166
+ "vocab_size": 50265
167
+ },
168
+ "eos_token_id": 0,
169
+ "is_encoder_decoder": true,
170
+ "model_type": "encoder-decoder",
171
+ "pad_token_id": 0,
172
+ "torch_dtype": "float32",
173
+ "transformers_version": "4.46.3",
174
+ "vocab_size": 21128
175
+ }
checkpoint-76000/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.46.3"
5
+ }
checkpoint-76000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b2432421018d9398ebb3e03fcb7a23196be067d67aad0fc76cbd7c0c5a8810
3
+ size 2084199838
checkpoint-76000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:688d587aaf7dd9e734a059446ece05be78014b4f7c9c7325fae67a130a9aa90b
3
+ size 1045902034
checkpoint-76000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f786f38c5dcd972dd93d3bea37ccc4e931096c5ae375f0c1089c1c44fa90b0f
3
+ size 14244
checkpoint-76000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a84843e33d474ac7de4df3ee13e964d9da95eef6e3f89585a9d248aa69652e4c
3
+ size 1064
checkpoint-76000/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91e4477c7886999944e908e093645f6f2a6ea12d8cfecc52891282f9e1835e98
3
+ size 13063345
checkpoint-76000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdf5eae39a7d284a1d8f174a6033461fe03593f519150d0033884476d857a2e
3
+ size 5432
checkpoint-80000/config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "",
8
+ "add_cross_attention": true,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "type_vocab_size": 2,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 21128
83
+ },
84
+ "decoder_start_token_id": 101,
85
+ "encoder": {
86
+ "_attn_implementation_autoset": false,
87
+ "_name_or_path": "",
88
+ "add_cross_attention": false,
89
+ "architectures": [
90
+ "LiltModel"
91
+ ],
92
+ "attention_probs_dropout_prob": 0.1,
93
+ "bad_words_ids": null,
94
+ "begin_suppress_tokens": null,
95
+ "bos_token_id": 0,
96
+ "channel_shrink_ratio": 4,
97
+ "chunk_size_feed_forward": 0,
98
+ "classifier_dropout": null,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": 2,
106
+ "exponential_decay_length_penalty": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "gelu",
111
+ "hidden_dropout_prob": 0.1,
112
+ "hidden_size": 768,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3072,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "label2id": {
122
+ "LABEL_0": 0,
123
+ "LABEL_1": 1
124
+ },
125
+ "layer_norm_eps": 1e-05,
126
+ "length_penalty": 1.0,
127
+ "max_2d_position_embeddings": 1024,
128
+ "max_length": 20,
129
+ "max_position_embeddings": 514,
130
+ "min_length": 0,
131
+ "model_type": "lilt",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 12,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": 1,
142
+ "position_embedding_type": "absolute",
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "suppress_tokens": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tf_legacy_loss": false,
155
+ "tie_encoder_decoder": false,
156
+ "tie_word_embeddings": true,
157
+ "tokenizer_class": null,
158
+ "top_k": 50,
159
+ "top_p": 1.0,
160
+ "torch_dtype": "float32",
161
+ "torchscript": false,
162
+ "type_vocab_size": 1,
163
+ "typical_p": 1.0,
164
+ "use_bfloat16": false,
165
+ "use_cache": true,
166
+ "vocab_size": 50265
167
+ },
168
+ "eos_token_id": 0,
169
+ "is_encoder_decoder": true,
170
+ "model_type": "encoder-decoder",
171
+ "pad_token_id": 0,
172
+ "torch_dtype": "float32",
173
+ "transformers_version": "4.46.3",
174
+ "vocab_size": 21128
175
+ }
checkpoint-80000/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.46.3"
5
+ }
checkpoint-80000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80eedfaf960febd9667b151ea027e3164430f46118f36b3a1ea2bde5a06d93bc
3
+ size 2084199838
checkpoint-80000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50fa8b8e595bd6822a708cc9f2228690e08b96f1c3be274e39850404707b2fda
3
+ size 1045902034
checkpoint-80000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77190922f4bf9fe65d49bff4380c8874f5529118f2a224f1ab65e450ba6936e
3
+ size 14244
checkpoint-80000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68df95c3248b59ba8dd0f0236575857c3c2929f9e378ad71d5b0ff01d14fbd44
3
+ size 1064
checkpoint-80000/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7593496ba63b7f285c49bc48bf94387c438c3b74b217a468bda1842f608f8d9e
3
+ size 13756065
checkpoint-80000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdf5eae39a7d284a1d8f174a6033461fe03593f519150d0033884476d857a2e
3
+ size 5432