neavo commited on
Commit
2b82e96
·
verified ·
1 Parent(s): d5e4ced
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "assets/modern_bert_cjk_stage_2",
3
+ "architectures": [
4
+ "ModernBertForMaskedLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 151644,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 151644,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 151645,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 1152,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 22,
37
+ "pad_token_id": 151646,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": false,
40
+ "repad_logits_with_grad": false,
41
+ "sep_token_id": 151645,
42
+ "sparse_pred_ignore_index": -100,
43
+ "sparse_prediction": false,
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.48.0",
46
+ "vocab_size": 151680
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3019c700d994365ad25e7fc0b6f1c0c7fbd4f3c70051ffd11579d4af4d672b5
3
+ size 910270752
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad6771f60dfa1770ddaad1fe84a7134b6258294bd5357e2998defb03f5233b4
3
+ size 11426146
tokenizer_config.json ADDED
@@ -0,0 +1,314 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151643": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151644": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151645": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151646": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151647": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151648": {
44
+ "content": "[UNUSED_1]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "151649": {
52
+ "content": "[UNUSED_2]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "151650": {
60
+ "content": "[UNUSED_3]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "151651": {
68
+ "content": "[UNUSED_4]",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "151652": {
76
+ "content": "[UNUSED_5]",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "151653": {
84
+ "content": "[UNUSED_6]",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "151654": {
92
+ "content": "[UNUSED_7]",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "151655": {
100
+ "content": "[UNUSED_8]",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "151656": {
108
+ "content": "[UNUSED_9]",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "151657": {
116
+ "content": "[UNUSED_10]",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "151658": {
124
+ "content": "[UNUSED_11]",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "151659": {
132
+ "content": "[UNUSED_12]",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "151660": {
140
+ "content": "[UNUSED_13]",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "151661": {
148
+ "content": "[UNUSED_14]",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "151662": {
156
+ "content": "[UNUSED_15]",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "151663": {
164
+ "content": "[UNUSED_16]",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "151664": {
172
+ "content": "[UNUSED_17]",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "151665": {
180
+ "content": "[UNUSED_18]",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "151666": {
188
+ "content": "[UNUSED_19]",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "151667": {
196
+ "content": "[UNUSED_20]",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "151668": {
204
+ "content": "[UNUSED_21]",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "151669": {
212
+ "content": "[UNUSED_22]",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "151670": {
220
+ "content": "[UNUSED_23]",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "151671": {
228
+ "content": "[UNUSED_24]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "151672": {
236
+ "content": "[UNUSED_25]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "151673": {
244
+ "content": "[UNUSED_26]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "151674": {
252
+ "content": "[UNUSED_27]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "151675": {
260
+ "content": "[UNUSED_28]",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "151676": {
268
+ "content": "[UNUSED_29]",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "151677": {
276
+ "content": "[UNUSED_30]",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "151678": {
284
+ "content": "[UNUSED_31]",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "151679": {
292
+ "content": "[UNUSED_32]",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ }
299
+ },
300
+ "clean_up_tokenization_spaces": false,
301
+ "cls_token": "[CLS]",
302
+ "do_lower_case": false,
303
+ "extra_special_tokens": {},
304
+ "mask_token": "[MASK]",
305
+ "model_input_names": [
306
+ "input_ids",
307
+ "attention_mask"
308
+ ],
309
+ "model_max_length": 8192,
310
+ "pad_token": "[PAD]",
311
+ "sep_token": "[SEP]",
312
+ "tokenizer_class": "PreTrainedTokenizerFast",
313
+ "unk_token": "[UNK]"
314
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ed8c3f2b88f6143a144457d2f43503e9495a8b2e6c898cc4108f9c6452c046
3
+ size 5368
training_args.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "output2/modern_bert_cjk_stage_2_pt_e3",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": true,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 32,
10
+ "per_device_eval_batch_size": 16,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 8,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 0.0005,
18
+ "weight_decay": 1e-05,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.999,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 1,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "warmup_stable_decay",
26
+ "lr_scheduler_kwargs": {
27
+ "num_decay_steps": 2232,
28
+ "num_stable_steps": 20082
29
+ },
30
+ "warmup_ratio": 0,
31
+ "warmup_steps": 0,
32
+ "log_level": "passive",
33
+ "log_level_replica": "warning",
34
+ "log_on_each_node": true,
35
+ "logging_dir": "output2/modern_bert_cjk_stage_2_pt_e3/runs/Jan27_00-07-38_bfa",
36
+ "logging_strategy": "steps",
37
+ "logging_first_step": false,
38
+ "logging_steps": 5,
39
+ "logging_nan_inf_filter": true,
40
+ "save_strategy": "steps",
41
+ "save_steps": 500,
42
+ "save_total_limit": null,
43
+ "save_safetensors": true,
44
+ "save_on_each_node": false,
45
+ "save_only_model": false,
46
+ "restore_callback_states_from_checkpoint": false,
47
+ "no_cuda": false,
48
+ "use_cpu": false,
49
+ "use_mps_device": false,
50
+ "seed": 42,
51
+ "data_seed": null,
52
+ "jit_mode_eval": false,
53
+ "use_ipex": false,
54
+ "bf16": true,
55
+ "fp16": false,
56
+ "fp16_opt_level": "O1",
57
+ "half_precision_backend": "auto",
58
+ "bf16_full_eval": false,
59
+ "fp16_full_eval": false,
60
+ "tf32": null,
61
+ "local_rank": 0,
62
+ "ddp_backend": null,
63
+ "tpu_num_cores": null,
64
+ "tpu_metrics_debug": false,
65
+ "debug": [],
66
+ "dataloader_drop_last": false,
67
+ "eval_steps": 500,
68
+ "dataloader_num_workers": 8,
69
+ "dataloader_prefetch_factor": null,
70
+ "past_index": -1,
71
+ "run_name": "output2/modern_bert_cjk_stage_2_pt_e3",
72
+ "disable_tqdm": false,
73
+ "remove_unused_columns": true,
74
+ "label_names": null,
75
+ "load_best_model_at_end": false,
76
+ "metric_for_best_model": null,
77
+ "greater_is_better": null,
78
+ "ignore_data_skip": false,
79
+ "fsdp": [],
80
+ "fsdp_min_num_params": 0,
81
+ "fsdp_config": {
82
+ "min_num_params": 0,
83
+ "xla": false,
84
+ "xla_fsdp_v2": false,
85
+ "xla_fsdp_grad_ckpt": false
86
+ },
87
+ "fsdp_transformer_layer_cls_to_wrap": null,
88
+ "accelerator_config": {
89
+ "split_batches": false,
90
+ "dispatch_batches": null,
91
+ "even_batches": true,
92
+ "use_seedable_sampler": true,
93
+ "non_blocking": false,
94
+ "gradient_accumulation_kwargs": null
95
+ },
96
+ "deepspeed": null,
97
+ "label_smoothing_factor": 0.0,
98
+ "optim": "adamw_torch",
99
+ "optim_args": null,
100
+ "adafactor": false,
101
+ "group_by_length": false,
102
+ "length_column_name": "length",
103
+ "report_to": [
104
+ "wandb"
105
+ ],
106
+ "ddp_find_unused_parameters": null,
107
+ "ddp_bucket_cap_mb": null,
108
+ "ddp_broadcast_buffers": null,
109
+ "dataloader_pin_memory": true,
110
+ "dataloader_persistent_workers": true,
111
+ "skip_memory_metrics": true,
112
+ "use_legacy_prediction_loop": false,
113
+ "push_to_hub": false,
114
+ "resume_from_checkpoint": null,
115
+ "hub_model_id": null,
116
+ "hub_strategy": "every_save",
117
+ "hub_token": "<HUB_TOKEN>",
118
+ "hub_private_repo": null,
119
+ "hub_always_push": false,
120
+ "gradient_checkpointing": true,
121
+ "gradient_checkpointing_kwargs": null,
122
+ "include_inputs_for_metrics": false,
123
+ "include_for_metrics": [],
124
+ "eval_do_concat_batches": true,
125
+ "fp16_backend": "auto",
126
+ "evaluation_strategy": null,
127
+ "push_to_hub_model_id": null,
128
+ "push_to_hub_organization": null,
129
+ "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
130
+ "mp_parameters": "",
131
+ "auto_find_batch_size": false,
132
+ "full_determinism": false,
133
+ "torchdynamo": null,
134
+ "ray_scope": "last",
135
+ "ddp_timeout": 1800,
136
+ "torch_compile": false,
137
+ "torch_compile_backend": null,
138
+ "torch_compile_mode": null,
139
+ "dispatch_batches": null,
140
+ "split_batches": null,
141
+ "include_tokens_per_second": false,
142
+ "include_num_input_tokens_seen": false,
143
+ "neftune_noise_alpha": null,
144
+ "optim_target_modules": null,
145
+ "batch_eval_metrics": false,
146
+ "eval_on_start": false,
147
+ "use_liger_kernel": false,
148
+ "eval_use_gather_object": false,
149
+ "average_tokens_across_devices": false
150
+ }