Hugging Face's logo

nberkowitz
/
gpn_balanced_grass

PyTorch
GPN
Generated from Trainer
Model card Files
xet
 Community
nberkowitz commited on
Commit
fbf5fc5
·
verified ·
1 Parent(s): 499f77d

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. README.md +61 -0
  2. all_results.json +12 -0
  3. checkpoint-10000/config.json +42 -0
  4. checkpoint-10000/optimizer.pt +3 -0
  5. checkpoint-10000/pytorch_model.bin +3 -0
  6. checkpoint-10000/rng_state.pth +3 -0
  7. checkpoint-10000/scheduler.pt +3 -0
  8. checkpoint-10000/special_tokens_map.json +5 -0
  9. checkpoint-10000/tokenizer.json +61 -0
  10. checkpoint-10000/tokenizer_config.json +8 -0
  11. checkpoint-10000/trainer_state.json +616 -0
  12. checkpoint-10000/training_args.bin +3 -0
  13. checkpoint-100000/config.json +42 -0
  14. checkpoint-100000/optimizer.pt +3 -0
  15. checkpoint-100000/pytorch_model.bin +3 -0
  16. checkpoint-100000/rng_state.pth +3 -0
  17. checkpoint-100000/scheduler.pt +3 -0
  18. checkpoint-100000/special_tokens_map.json +5 -0
  19. checkpoint-100000/tokenizer.json +61 -0
  20. checkpoint-100000/tokenizer_config.json +8 -0
  21. checkpoint-100000/trainer_state.json +0 -0
  22. checkpoint-100000/training_args.bin +3 -0
  23. checkpoint-110000/config.json +42 -0
  24. checkpoint-110000/optimizer.pt +3 -0
  25. checkpoint-110000/pytorch_model.bin +3 -0
  26. checkpoint-110000/rng_state.pth +3 -0
  27. checkpoint-110000/scheduler.pt +3 -0
  28. checkpoint-110000/special_tokens_map.json +5 -0
  29. checkpoint-110000/tokenizer.json +61 -0
  30. checkpoint-110000/tokenizer_config.json +8 -0
  31. checkpoint-110000/trainer_state.json +0 -0
  32. checkpoint-110000/training_args.bin +3 -0
  33. checkpoint-120000/config.json +42 -0
  34. checkpoint-120000/optimizer.pt +3 -0
  35. checkpoint-120000/pytorch_model.bin +3 -0
  36. checkpoint-120000/rng_state.pth +3 -0
  37. checkpoint-120000/scheduler.pt +3 -0
  38. checkpoint-120000/special_tokens_map.json +5 -0
  39. checkpoint-120000/tokenizer.json +61 -0
  40. checkpoint-120000/tokenizer_config.json +8 -0
  41. checkpoint-120000/trainer_state.json +0 -0
  42. checkpoint-120000/training_args.bin +3 -0
  43. checkpoint-20000/config.json +42 -0
  44. checkpoint-20000/optimizer.pt +3 -0
  45. checkpoint-20000/pytorch_model.bin +3 -0
  46. checkpoint-20000/rng_state.pth +3 -0
  47. checkpoint-20000/scheduler.pt +3 -0
  48. checkpoint-20000/special_tokens_map.json +5 -0
  49. checkpoint-20000/tokenizer.json +61 -0
  50. checkpoint-20000/tokenizer_config.json +8 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - nberkowitz/gpn_grass_balanced_v1
6
+ model-index:
7
+ - name: model
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # model
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the nberkowitz/gpn_grass_balanced_v1 dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.0249
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 64
39
+ - eval_batch_size: 512
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 256
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - training_steps: 120000
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:------:|:---------------:|
52
+ | 1.0777 | 2.01 | 60000 | 1.0535 |
53
+ | 1.0495 | 4.03 | 120000 | 1.0253 |
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.30.0
59
+ - Pytorch 2.4.1
60
+ - Datasets 3.1.0
61
+ - Tokenizers 0.13.3
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.03,
3
+ "eval_loss": 1.0248529607287784,
4
+ "eval_runtime": 113.3652,
5
+ "eval_samples_per_second": 1017.023,
6
+ "eval_steps_per_second": 1.994,
7
+ "perplexity": 2.786685678208292,
8
+ "train_loss": 1.094069771003723,
9
+ "train_runtime": 112961.376,
10
+ "train_samples_per_second": 271.951,
11
+ "train_steps_per_second": 1.062
12
+ }
checkpoint-10000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPNForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "aux_features_vocab_size": 5,
7
+ "bias": false,
8
+ "classification_head": "standard",
9
+ "depthwise": false,
10
+ "dilation_base": 2,
11
+ "dilation_cycle": 8,
12
+ "dilation_double_every": 1,
13
+ "dilation_max": 9999,
14
+ "embedding": "one_hot",
15
+ "embedding_size": 768,
16
+ "encoder": "convnet",
17
+ "first_kernel_size": 9,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.0,
20
+ "hidden_size": 512,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 2048,
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 1536,
25
+ "mlm_head_transform": true,
26
+ "model_type": "GPN",
27
+ "n_aux_features": 0,
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 25,
30
+ "pad_token_id": 0,
31
+ "pos_weight": null,
32
+ "regression_softplus": false,
33
+ "rest_kernel_size": 5,
34
+ "rotary_value": false,
35
+ "slim": false,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.30.0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 7
42
+ }
checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69854b299fd59a6793b04cd481948372cc988b44f30fd1ae0b9bd135648033fe
3
+ size 189424250
checkpoint-10000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a95707adba75f7fbca2c2ac934f7053b5d5f519a6e1b7881b199cff9adb0a98
3
+ size 372416818
checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e63cf4e3c6261a653e114a9f78519531b5c2715637fab95a0cb286fea0cf3e3c
3
+ size 14942
checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cce94495de89581303768c5b9c334387da671b02f371388046da6da2775fa58
3
+ size 1064
checkpoint-10000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "[PAD]",
4
+ "unk_token": "[UNK]"
5
+ }
checkpoint-10000/tokenizer.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[MASK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[UNK]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Lowercase"
36
+ },
37
+ "pre_tokenizer": {
38
+ "type": "Whitespace"
39
+ },
40
+ "post_processor": null,
41
+ "decoder": null,
42
+ "model": {
43
+ "type": "BPE",
44
+ "dropout": null,
45
+ "unk_token": "[UNK]",
46
+ "continuing_subword_prefix": null,
47
+ "end_of_word_suffix": null,
48
+ "fuse_unk": false,
49
+ "byte_fallback": false,
50
+ "vocab": {
51
+ "[PAD]": 0,
52
+ "[MASK]": 1,
53
+ "[UNK]": 2,
54
+ "a": 3,
55
+ "c": 4,
56
+ "g": 5,
57
+ "t": 6
58
+ },
59
+ "merges": []
60
+ }
61
+ }
checkpoint-10000/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "mask_token": "[MASK]",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "[PAD]",
6
+ "tokenizer_class": "PreTrainedTokenizerFast",
7
+ "unk_token": "[UNK]"
8
+ }
checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.08333333333333333,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 4.995833333333333e-05,
13
+ "loss": 1.3001,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 4.991666666666667e-05,
19
+ "loss": 1.2479,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 4.9875000000000006e-05,
25
+ "loss": 1.2428,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 4.9833333333333336e-05,
31
+ "loss": 1.2412,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 4.979166666666667e-05,
37
+ "loss": 1.2395,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 4.975e-05,
43
+ "loss": 1.2386,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "learning_rate": 4.970833333333333e-05,
49
+ "loss": 1.2377,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 4.966666666666667e-05,
55
+ "loss": 1.2365,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 0.01,
60
+ "learning_rate": 4.962500000000001e-05,
61
+ "loss": 1.2345,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 0.01,
66
+ "learning_rate": 4.958333333333334e-05,
67
+ "loss": 1.2322,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 0.01,
72
+ "learning_rate": 4.954166666666667e-05,
73
+ "loss": 1.2306,
74
+ "step": 1100
75
+ },
76
+ {
77
+ "epoch": 0.01,
78
+ "learning_rate": 4.9500000000000004e-05,
79
+ "loss": 1.2312,
80
+ "step": 1200
81
+ },
82
+ {
83
+ "epoch": 0.01,
84
+ "learning_rate": 4.9458333333333334e-05,
85
+ "loss": 1.2291,
86
+ "step": 1300
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "learning_rate": 4.9416666666666664e-05,
91
+ "loss": 1.2279,
92
+ "step": 1400
93
+ },
94
+ {
95
+ "epoch": 0.01,
96
+ "learning_rate": 4.937500000000001e-05,
97
+ "loss": 1.226,
98
+ "step": 1500
99
+ },
100
+ {
101
+ "epoch": 0.01,
102
+ "learning_rate": 4.933333333333334e-05,
103
+ "loss": 1.2268,
104
+ "step": 1600
105
+ },
106
+ {
107
+ "epoch": 0.01,
108
+ "learning_rate": 4.929166666666667e-05,
109
+ "loss": 1.2258,
110
+ "step": 1700
111
+ },
112
+ {
113
+ "epoch": 0.01,
114
+ "learning_rate": 4.9250000000000004e-05,
115
+ "loss": 1.2241,
116
+ "step": 1800
117
+ },
118
+ {
119
+ "epoch": 0.02,
120
+ "learning_rate": 4.9208333333333335e-05,
121
+ "loss": 1.2248,
122
+ "step": 1900
123
+ },
124
+ {
125
+ "epoch": 0.02,
126
+ "learning_rate": 4.9166666666666665e-05,
127
+ "loss": 1.2242,
128
+ "step": 2000
129
+ },
130
+ {
131
+ "epoch": 0.02,
132
+ "learning_rate": 4.9125e-05,
133
+ "loss": 1.2227,
134
+ "step": 2100
135
+ },
136
+ {
137
+ "epoch": 0.02,
138
+ "learning_rate": 4.908333333333334e-05,
139
+ "loss": 1.2216,
140
+ "step": 2200
141
+ },
142
+ {
143
+ "epoch": 0.02,
144
+ "learning_rate": 4.904166666666667e-05,
145
+ "loss": 1.2217,
146
+ "step": 2300
147
+ },
148
+ {
149
+ "epoch": 0.02,
150
+ "learning_rate": 4.9e-05,
151
+ "loss": 1.2208,
152
+ "step": 2400
153
+ },
154
+ {
155
+ "epoch": 0.02,
156
+ "learning_rate": 4.8958333333333335e-05,
157
+ "loss": 1.2203,
158
+ "step": 2500
159
+ },
160
+ {
161
+ "epoch": 0.02,
162
+ "learning_rate": 4.891666666666667e-05,
163
+ "loss": 1.2192,
164
+ "step": 2600
165
+ },
166
+ {
167
+ "epoch": 0.02,
168
+ "learning_rate": 4.8875e-05,
169
+ "loss": 1.2187,
170
+ "step": 2700
171
+ },
172
+ {
173
+ "epoch": 0.02,
174
+ "learning_rate": 4.883333333333334e-05,
175
+ "loss": 1.2189,
176
+ "step": 2800
177
+ },
178
+ {
179
+ "epoch": 0.02,
180
+ "learning_rate": 4.879166666666667e-05,
181
+ "loss": 1.2177,
182
+ "step": 2900
183
+ },
184
+ {
185
+ "epoch": 0.03,
186
+ "learning_rate": 4.875e-05,
187
+ "loss": 1.2168,
188
+ "step": 3000
189
+ },
190
+ {
191
+ "epoch": 0.03,
192
+ "learning_rate": 4.8708333333333336e-05,
193
+ "loss": 1.2163,
194
+ "step": 3100
195
+ },
196
+ {
197
+ "epoch": 0.03,
198
+ "learning_rate": 4.866666666666667e-05,
199
+ "loss": 1.2151,
200
+ "step": 3200
201
+ },
202
+ {
203
+ "epoch": 0.03,
204
+ "learning_rate": 4.8625e-05,
205
+ "loss": 1.2156,
206
+ "step": 3300
207
+ },
208
+ {
209
+ "epoch": 0.03,
210
+ "learning_rate": 4.858333333333333e-05,
211
+ "loss": 1.2146,
212
+ "step": 3400
213
+ },
214
+ {
215
+ "epoch": 0.03,
216
+ "learning_rate": 4.854166666666667e-05,
217
+ "loss": 1.2124,
218
+ "step": 3500
219
+ },
220
+ {
221
+ "epoch": 0.03,
222
+ "learning_rate": 4.85e-05,
223
+ "loss": 1.2124,
224
+ "step": 3600
225
+ },
226
+ {
227
+ "epoch": 0.03,
228
+ "learning_rate": 4.845833333333334e-05,
229
+ "loss": 1.2129,
230
+ "step": 3700
231
+ },
232
+ {
233
+ "epoch": 0.03,
234
+ "learning_rate": 4.8416666666666673e-05,
235
+ "loss": 1.2109,
236
+ "step": 3800
237
+ },
238
+ {
239
+ "epoch": 0.03,
240
+ "learning_rate": 4.8375000000000004e-05,
241
+ "loss": 1.2104,
242
+ "step": 3900
243
+ },
244
+ {
245
+ "epoch": 0.03,
246
+ "learning_rate": 4.8333333333333334e-05,
247
+ "loss": 1.211,
248
+ "step": 4000
249
+ },
250
+ {
251
+ "epoch": 0.03,
252
+ "learning_rate": 4.829166666666667e-05,
253
+ "loss": 1.2081,
254
+ "step": 4100
255
+ },
256
+ {
257
+ "epoch": 0.04,
258
+ "learning_rate": 4.825e-05,
259
+ "loss": 1.2089,
260
+ "step": 4200
261
+ },
262
+ {
263
+ "epoch": 0.04,
264
+ "learning_rate": 4.820833333333333e-05,
265
+ "loss": 1.2077,
266
+ "step": 4300
267
+ },
268
+ {
269
+ "epoch": 0.04,
270
+ "learning_rate": 4.8166666666666674e-05,
271
+ "loss": 1.208,
272
+ "step": 4400
273
+ },
274
+ {
275
+ "epoch": 0.04,
276
+ "learning_rate": 4.8125000000000004e-05,
277
+ "loss": 1.2069,
278
+ "step": 4500
279
+ },
280
+ {
281
+ "epoch": 0.04,
282
+ "learning_rate": 4.8083333333333334e-05,
283
+ "loss": 1.206,
284
+ "step": 4600
285
+ },
286
+ {
287
+ "epoch": 0.04,
288
+ "learning_rate": 4.804166666666667e-05,
289
+ "loss": 1.2058,
290
+ "step": 4700
291
+ },
292
+ {
293
+ "epoch": 0.04,
294
+ "learning_rate": 4.8e-05,
295
+ "loss": 1.2038,
296
+ "step": 4800
297
+ },
298
+ {
299
+ "epoch": 0.04,
300
+ "learning_rate": 4.795833333333333e-05,
301
+ "loss": 1.2044,
302
+ "step": 4900
303
+ },
304
+ {
305
+ "epoch": 0.04,
306
+ "learning_rate": 4.791666666666667e-05,
307
+ "loss": 1.2044,
308
+ "step": 5000
309
+ },
310
+ {
311
+ "epoch": 0.04,
312
+ "learning_rate": 4.7875000000000005e-05,
313
+ "loss": 1.2035,
314
+ "step": 5100
315
+ },
316
+ {
317
+ "epoch": 0.04,
318
+ "learning_rate": 4.7833333333333335e-05,
319
+ "loss": 1.202,
320
+ "step": 5200
321
+ },
322
+ {
323
+ "epoch": 0.04,
324
+ "learning_rate": 4.7791666666666665e-05,
325
+ "loss": 1.2018,
326
+ "step": 5300
327
+ },
328
+ {
329
+ "epoch": 0.04,
330
+ "learning_rate": 4.775e-05,
331
+ "loss": 1.2015,
332
+ "step": 5400
333
+ },
334
+ {
335
+ "epoch": 0.05,
336
+ "learning_rate": 4.770833333333334e-05,
337
+ "loss": 1.1997,
338
+ "step": 5500
339
+ },
340
+ {
341
+ "epoch": 0.05,
342
+ "learning_rate": 4.766666666666667e-05,
343
+ "loss": 1.2016,
344
+ "step": 5600
345
+ },
346
+ {
347
+ "epoch": 0.05,
348
+ "learning_rate": 4.7625000000000006e-05,
349
+ "loss": 1.1986,
350
+ "step": 5700
351
+ },
352
+ {
353
+ "epoch": 0.05,
354
+ "learning_rate": 4.7583333333333336e-05,
355
+ "loss": 1.1994,
356
+ "step": 5800
357
+ },
358
+ {
359
+ "epoch": 0.05,
360
+ "learning_rate": 4.7541666666666666e-05,
361
+ "loss": 1.1996,
362
+ "step": 5900
363
+ },
364
+ {
365
+ "epoch": 0.05,
366
+ "learning_rate": 4.75e-05,
367
+ "loss": 1.198,
368
+ "step": 6000
369
+ },
370
+ {
371
+ "epoch": 0.05,
372
+ "learning_rate": 4.745833333333334e-05,
373
+ "loss": 1.1969,
374
+ "step": 6100
375
+ },
376
+ {
377
+ "epoch": 0.05,
378
+ "learning_rate": 4.741666666666667e-05,
379
+ "loss": 1.197,
380
+ "step": 6200
381
+ },
382
+ {
383
+ "epoch": 0.05,
384
+ "learning_rate": 4.7375e-05,
385
+ "loss": 1.1972,
386
+ "step": 6300
387
+ },
388
+ {
389
+ "epoch": 0.05,
390
+ "learning_rate": 4.7333333333333336e-05,
391
+ "loss": 1.1949,
392
+ "step": 6400
393
+ },
394
+ {
395
+ "epoch": 0.05,
396
+ "learning_rate": 4.7291666666666666e-05,
397
+ "loss": 1.1964,
398
+ "step": 6500
399
+ },
400
+ {
401
+ "epoch": 0.06,
402
+ "learning_rate": 4.7249999999999997e-05,
403
+ "loss": 1.1949,
404
+ "step": 6600
405
+ },
406
+ {
407
+ "epoch": 0.06,
408
+ "learning_rate": 4.720833333333334e-05,
409
+ "loss": 1.195,
410
+ "step": 6700
411
+ },
412
+ {
413
+ "epoch": 0.06,
414
+ "learning_rate": 4.716666666666667e-05,
415
+ "loss": 1.194,
416
+ "step": 6800
417
+ },
418
+ {
419
+ "epoch": 0.06,
420
+ "learning_rate": 4.7125e-05,
421
+ "loss": 1.1923,
422
+ "step": 6900
423
+ },
424
+ {
425
+ "epoch": 0.06,
426
+ "learning_rate": 4.708333333333334e-05,
427
+ "loss": 1.1943,
428
+ "step": 7000
429
+ },
430
+ {
431
+ "epoch": 0.06,
432
+ "learning_rate": 4.704166666666667e-05,
433
+ "loss": 1.1935,
434
+ "step": 7100
435
+ },
436
+ {
437
+ "epoch": 0.06,
438
+ "learning_rate": 4.7e-05,
439
+ "loss": 1.1916,
440
+ "step": 7200
441
+ },
442
+ {
443
+ "epoch": 0.06,
444
+ "learning_rate": 4.695833333333334e-05,
445
+ "loss": 1.1924,
446
+ "step": 7300
447
+ },
448
+ {
449
+ "epoch": 0.06,
450
+ "learning_rate": 4.691666666666667e-05,
451
+ "loss": 1.1912,
452
+ "step": 7400
453
+ },
454
+ {
455
+ "epoch": 0.06,
456
+ "learning_rate": 4.6875e-05,
457
+ "loss": 1.1906,
458
+ "step": 7500
459
+ },
460
+ {
461
+ "epoch": 0.06,
462
+ "learning_rate": 4.683333333333334e-05,
463
+ "loss": 1.1896,
464
+ "step": 7600
465
+ },
466
+ {
467
+ "epoch": 0.06,
468
+ "learning_rate": 4.679166666666667e-05,
469
+ "loss": 1.1893,
470
+ "step": 7700
471
+ },
472
+ {
473
+ "epoch": 0.07,
474
+ "learning_rate": 4.6750000000000005e-05,
475
+ "loss": 1.19,
476
+ "step": 7800
477
+ },
478
+ {
479
+ "epoch": 0.07,
480
+ "learning_rate": 4.6708333333333335e-05,
481
+ "loss": 1.1894,
482
+ "step": 7900
483
+ },
484
+ {
485
+ "epoch": 0.07,
486
+ "learning_rate": 4.666666666666667e-05,
487
+ "loss": 1.188,
488
+ "step": 8000
489
+ },
490
+ {
491
+ "epoch": 0.07,
492
+ "learning_rate": 4.6625e-05,
493
+ "loss": 1.1865,
494
+ "step": 8100
495
+ },
496
+ {
497
+ "epoch": 0.07,
498
+ "learning_rate": 4.658333333333333e-05,
499
+ "loss": 1.1872,
500
+ "step": 8200
501
+ },
502
+ {
503
+ "epoch": 0.07,
504
+ "learning_rate": 4.654166666666667e-05,
505
+ "loss": 1.1855,
506
+ "step": 8300
507
+ },
508
+ {
509
+ "epoch": 0.07,
510
+ "learning_rate": 4.6500000000000005e-05,
511
+ "loss": 1.1848,
512
+ "step": 8400
513
+ },
514
+ {
515
+ "epoch": 0.07,
516
+ "learning_rate": 4.6458333333333335e-05,
517
+ "loss": 1.1865,
518
+ "step": 8500
519
+ },
520
+ {
521
+ "epoch": 0.07,
522
+ "learning_rate": 4.641666666666667e-05,
523
+ "loss": 1.1846,
524
+ "step": 8600
525
+ },
526
+ {
527
+ "epoch": 0.07,
528
+ "learning_rate": 4.6375e-05,
529
+ "loss": 1.1851,
530
+ "step": 8700
531
+ },
532
+ {
533
+ "epoch": 0.07,
534
+ "learning_rate": 4.633333333333333e-05,
535
+ "loss": 1.1848,
536
+ "step": 8800
537
+ },
538
+ {
539
+ "epoch": 0.07,
540
+ "learning_rate": 4.629166666666667e-05,
541
+ "loss": 1.185,
542
+ "step": 8900
543
+ },
544
+ {
545
+ "epoch": 0.07,
546
+ "learning_rate": 4.6250000000000006e-05,
547
+ "loss": 1.1829,
548
+ "step": 9000
549
+ },
550
+ {
551
+ "epoch": 0.08,
552
+ "learning_rate": 4.6208333333333336e-05,
553
+ "loss": 1.1821,
554
+ "step": 9100
555
+ },
556
+ {
557
+ "epoch": 0.08,
558
+ "learning_rate": 4.6166666666666666e-05,
559
+ "loss": 1.1822,
560
+ "step": 9200
561
+ },
562
+ {
563
+ "epoch": 0.08,
564
+ "learning_rate": 4.6125e-05,
565
+ "loss": 1.1818,
566
+ "step": 9300
567
+ },
568
+ {
569
+ "epoch": 0.08,
570
+ "learning_rate": 4.608333333333333e-05,
571
+ "loss": 1.1812,
572
+ "step": 9400
573
+ },
574
+ {
575
+ "epoch": 0.08,
576
+ "learning_rate": 4.604166666666666e-05,
577
+ "loss": 1.1804,
578
+ "step": 9500
579
+ },
580
+ {
581
+ "epoch": 0.08,
582
+ "learning_rate": 4.600000000000001e-05,
583
+ "loss": 1.1795,
584
+ "step": 9600
585
+ },
586
+ {
587
+ "epoch": 0.08,
588
+ "learning_rate": 4.595833333333334e-05,
589
+ "loss": 1.1794,
590
+ "step": 9700
591
+ },
592
+ {
593
+ "epoch": 0.08,
594
+ "learning_rate": 4.591666666666667e-05,
595
+ "loss": 1.1783,
596
+ "step": 9800
597
+ },
598
+ {
599
+ "epoch": 0.08,
600
+ "learning_rate": 4.5875000000000004e-05,
601
+ "loss": 1.1775,
602
+ "step": 9900
603
+ },
604
+ {
605
+ "epoch": 0.08,
606
+ "learning_rate": 4.5833333333333334e-05,
607
+ "loss": 1.1781,
608
+ "step": 10000
609
+ }
610
+ ],
611
+ "max_steps": 120000,
612
+ "num_train_epochs": 9223372036854775807,
613
+ "total_flos": 7.3209999261696e+17,
614
+ "trial_name": null,
615
+ "trial_params": null
616
+ }
checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0efb37155af09406bda4f4fc9d4ab7d3d67fab3954723032e5e79e169d869e
3
+ size 4408
checkpoint-100000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPNForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "aux_features_vocab_size": 5,
7
+ "bias": false,
8
+ "classification_head": "standard",
9
+ "depthwise": false,
10
+ "dilation_base": 2,
11
+ "dilation_cycle": 8,
12
+ "dilation_double_every": 1,
13
+ "dilation_max": 9999,
14
+ "embedding": "one_hot",
15
+ "embedding_size": 768,
16
+ "encoder": "convnet",
17
+ "first_kernel_size": 9,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.0,
20
+ "hidden_size": 512,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 2048,
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 1536,
25
+ "mlm_head_transform": true,
26
+ "model_type": "GPN",
27
+ "n_aux_features": 0,
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 25,
30
+ "pad_token_id": 0,
31
+ "pos_weight": null,
32
+ "regression_softplus": false,
33
+ "rest_kernel_size": 5,
34
+ "rotary_value": false,
35
+ "slim": false,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.30.0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 7
42
+ }
checkpoint-100000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ac69ab97cd54d6340839243e5ffd21f830eb4ffb10e705d9b22a21e50b7a47
3
+ size 189424570
checkpoint-100000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ff6056655b680c6961b945f8ccee5287240321eee6c643bbbd68dfd422f4b86
3
+ size 372416818
checkpoint-100000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b82f8e7e21f4444fd61c6d7941e8c4a3f64c30f26a1094c913a4fe30488760
3
+ size 14942
checkpoint-100000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51b77956d90021bc73786bb1429149c03cf518fa4d26433a0a1f3df8a0ad5cef
3
+ size 1064
checkpoint-100000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "[PAD]",
4
+ "unk_token": "[UNK]"
5
+ }
checkpoint-100000/tokenizer.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[MASK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[UNK]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Lowercase"
36
+ },
37
+ "pre_tokenizer": {
38
+ "type": "Whitespace"
39
+ },
40
+ "post_processor": null,
41
+ "decoder": null,
42
+ "model": {
43
+ "type": "BPE",
44
+ "dropout": null,
45
+ "unk_token": "[UNK]",
46
+ "continuing_subword_prefix": null,
47
+ "end_of_word_suffix": null,
48
+ "fuse_unk": false,
49
+ "byte_fallback": false,
50
+ "vocab": {
51
+ "[PAD]": 0,
52
+ "[MASK]": 1,
53
+ "[UNK]": 2,
54
+ "a": 3,
55
+ "c": 4,
56
+ "g": 5,
57
+ "t": 6
58
+ },
59
+ "merges": []
60
+ }
61
+ }
checkpoint-100000/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "mask_token": "[MASK]",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "[PAD]",
6
+ "tokenizer_class": "PreTrainedTokenizerFast",
7
+ "unk_token": "[UNK]"
8
+ }
checkpoint-100000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0efb37155af09406bda4f4fc9d4ab7d3d67fab3954723032e5e79e169d869e
3
+ size 4408
checkpoint-110000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPNForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "aux_features_vocab_size": 5,
7
+ "bias": false,
8
+ "classification_head": "standard",
9
+ "depthwise": false,
10
+ "dilation_base": 2,
11
+ "dilation_cycle": 8,
12
+ "dilation_double_every": 1,
13
+ "dilation_max": 9999,
14
+ "embedding": "one_hot",
15
+ "embedding_size": 768,
16
+ "encoder": "convnet",
17
+ "first_kernel_size": 9,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.0,
20
+ "hidden_size": 512,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 2048,
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 1536,
25
+ "mlm_head_transform": true,
26
+ "model_type": "GPN",
27
+ "n_aux_features": 0,
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 25,
30
+ "pad_token_id": 0,
31
+ "pos_weight": null,
32
+ "regression_softplus": false,
33
+ "rest_kernel_size": 5,
34
+ "rotary_value": false,
35
+ "slim": false,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.30.0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 7
42
+ }
checkpoint-110000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:825bee343cd45e5ec9ead855836886c9066ca03ffe0003fc778acc9076f40af4
3
+ size 189424570
checkpoint-110000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1411d874ae9551e2daf0d82e2490cc878a62540705601cc8d9346ef101264464
3
+ size 372416818
checkpoint-110000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b82f8e7e21f4444fd61c6d7941e8c4a3f64c30f26a1094c913a4fe30488760
3
+ size 14942
checkpoint-110000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3f9db5cf2ae4aad45ed733e0c3908bbe6b8cb480d2f0fdfe9adc9e761ce4e6
3
+ size 1064
checkpoint-110000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "[PAD]",
4
+ "unk_token": "[UNK]"
5
+ }
checkpoint-110000/tokenizer.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[MASK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[UNK]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Lowercase"
36
+ },
37
+ "pre_tokenizer": {
38
+ "type": "Whitespace"
39
+ },
40
+ "post_processor": null,
41
+ "decoder": null,
42
+ "model": {
43
+ "type": "BPE",
44
+ "dropout": null,
45
+ "unk_token": "[UNK]",
46
+ "continuing_subword_prefix": null,
47
+ "end_of_word_suffix": null,
48
+ "fuse_unk": false,
49
+ "byte_fallback": false,
50
+ "vocab": {
51
+ "[PAD]": 0,
52
+ "[MASK]": 1,
53
+ "[UNK]": 2,
54
+ "a": 3,
55
+ "c": 4,
56
+ "g": 5,
57
+ "t": 6
58
+ },
59
+ "merges": []
60
+ }
61
+ }
checkpoint-110000/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "mask_token": "[MASK]",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "[PAD]",
6
+ "tokenizer_class": "PreTrainedTokenizerFast",
7
+ "unk_token": "[UNK]"
8
+ }
checkpoint-110000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-110000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0efb37155af09406bda4f4fc9d4ab7d3d67fab3954723032e5e79e169d869e
3
+ size 4408
checkpoint-120000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPNForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "aux_features_vocab_size": 5,
7
+ "bias": false,
8
+ "classification_head": "standard",
9
+ "depthwise": false,
10
+ "dilation_base": 2,
11
+ "dilation_cycle": 8,
12
+ "dilation_double_every": 1,
13
+ "dilation_max": 9999,
14
+ "embedding": "one_hot",
15
+ "embedding_size": 768,
16
+ "encoder": "convnet",
17
+ "first_kernel_size": 9,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.0,
20
+ "hidden_size": 512,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 2048,
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 1536,
25
+ "mlm_head_transform": true,
26
+ "model_type": "GPN",
27
+ "n_aux_features": 0,
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 25,
30
+ "pad_token_id": 0,
31
+ "pos_weight": null,
32
+ "regression_softplus": false,
33
+ "rest_kernel_size": 5,
34
+ "rotary_value": false,
35
+ "slim": false,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.30.0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 7
42
+ }
checkpoint-120000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6e9d7e5a4524657bfc271fd2fb3ab193fce4759ff20f54099083a5125b62138
3
+ size 189424570
checkpoint-120000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c51c8c8b8fc7b0708d03d439c176aa05cb7cc6431d84e85b1399ccc80ade821
3
+ size 372416818
checkpoint-120000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ddab582c0c3a0ce21fbd54ce9ed10b11a116e8b6fdbd816eda2b29c4c33640
3
+ size 14942
checkpoint-120000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288acaa8d2583597c3cad4280f81b3142e63a3b9315c0282478f97ba168919c8
3
+ size 1064
checkpoint-120000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "[PAD]",
4
+ "unk_token": "[UNK]"
5
+ }
checkpoint-120000/tokenizer.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[MASK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[UNK]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Lowercase"
36
+ },
37
+ "pre_tokenizer": {
38
+ "type": "Whitespace"
39
+ },
40
+ "post_processor": null,
41
+ "decoder": null,
42
+ "model": {
43
+ "type": "BPE",
44
+ "dropout": null,
45
+ "unk_token": "[UNK]",
46
+ "continuing_subword_prefix": null,
47
+ "end_of_word_suffix": null,
48
+ "fuse_unk": false,
49
+ "byte_fallback": false,
50
+ "vocab": {
51
+ "[PAD]": 0,
52
+ "[MASK]": 1,
53
+ "[UNK]": 2,
54
+ "a": 3,
55
+ "c": 4,
56
+ "g": 5,
57
+ "t": 6
58
+ },
59
+ "merges": []
60
+ }
61
+ }
checkpoint-120000/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "mask_token": "[MASK]",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "[PAD]",
6
+ "tokenizer_class": "PreTrainedTokenizerFast",
7
+ "unk_token": "[UNK]"
8
+ }
checkpoint-120000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-120000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0efb37155af09406bda4f4fc9d4ab7d3d67fab3954723032e5e79e169d869e
3
+ size 4408
checkpoint-20000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPNForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "aux_features_vocab_size": 5,
7
+ "bias": false,
8
+ "classification_head": "standard",
9
+ "depthwise": false,
10
+ "dilation_base": 2,
11
+ "dilation_cycle": 8,
12
+ "dilation_double_every": 1,
13
+ "dilation_max": 9999,
14
+ "embedding": "one_hot",
15
+ "embedding_size": 768,
16
+ "encoder": "convnet",
17
+ "first_kernel_size": 9,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.0,
20
+ "hidden_size": 512,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 2048,
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 1536,
25
+ "mlm_head_transform": true,
26
+ "model_type": "GPN",
27
+ "n_aux_features": 0,
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 25,
30
+ "pad_token_id": 0,
31
+ "pos_weight": null,
32
+ "regression_softplus": false,
33
+ "rest_kernel_size": 5,
34
+ "rotary_value": false,
35
+ "slim": false,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.30.0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 7
42
+ }
checkpoint-20000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc73cc26de3fe4df3887a75c42ec66fb1065899872cb619af82435a871851c8
3
+ size 189424250
checkpoint-20000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53d8cccd302f450e5c38100baf79b4d706d049a2f970717891ca877e392f745
3
+ size 372416818
checkpoint-20000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e63cf4e3c6261a653e114a9f78519531b5c2715637fab95a0cb286fea0cf3e3c
3
+ size 14942
checkpoint-20000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e4fe7c8bb62830100b9c1471bbeb02c95460e651fc4c0fbb279ffc9c6f42de
3
+ size 1064
checkpoint-20000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "[PAD]",
4
+ "unk_token": "[UNK]"
5
+ }
checkpoint-20000/tokenizer.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[MASK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[UNK]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Lowercase"
36
+ },
37
+ "pre_tokenizer": {
38
+ "type": "Whitespace"
39
+ },
40
+ "post_processor": null,
41
+ "decoder": null,
42
+ "model": {
43
+ "type": "BPE",
44
+ "dropout": null,
45
+ "unk_token": "[UNK]",
46
+ "continuing_subword_prefix": null,
47
+ "end_of_word_suffix": null,
48
+ "fuse_unk": false,
49
+ "byte_fallback": false,
50
+ "vocab": {
51
+ "[PAD]": 0,
52
+ "[MASK]": 1,
53
+ "[UNK]": 2,
54
+ "a": 3,
55
+ "c": 4,
56
+ "g": 5,
57
+ "t": 6
58
+ },
59
+ "merges": []
60
+ }
61
+ }
checkpoint-20000/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "mask_token": "[MASK]",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "[PAD]",
6
+ "tokenizer_class": "PreTrainedTokenizerFast",
7
+ "unk_token": "[UNK]"
8
+ }