Hugging Face's logo

zanesmit29
/
founder-deberta-agnews-v1

Text Classification
Safetensors
English
deberta-v2
topic-classification
deberta
the-founder
Eval Results (legacy)
Model card Files
xet
 Community
zanesmit29 commited on
Commit
d56dc78
·
verified ·
1 Parent(s): 6e5bb2b

The Founder: deberta-v3-base fine-tuned on ag_news v1

Browse files
Files changed (20) hide show
  1. README.md +114 -0
  2. checkpoint-3375/config.json +51 -0
  3. checkpoint-3375/model.safetensors +3 -0
  4. checkpoint-3375/optimizer.pt +3 -0
  5. checkpoint-3375/rng_state.pth +3 -0
  6. checkpoint-3375/scheduler.pt +3 -0
  7. checkpoint-3375/trainer_state.json +521 -0
  8. checkpoint-3375/training_args.bin +3 -0
  9. checkpoint-6750/config.json +51 -0
  10. checkpoint-6750/model.safetensors +3 -0
  11. checkpoint-6750/optimizer.pt +3 -0
  12. checkpoint-6750/rng_state.pth +3 -0
  13. checkpoint-6750/scheduler.pt +3 -0
  14. checkpoint-6750/trainer_state.json +1006 -0
  15. checkpoint-6750/training_args.bin +3 -0
  16. config.json +51 -0
  17. model.safetensors +3 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +23 -0
  20. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - text-classification
7
+ - topic-classification
8
+ - deberta
9
+ - the-founder
10
+ datasets:
11
+ - fancyzhx/ag_news
12
+ metrics:
13
+ - accuracy
14
+ base_model: microsoft/deberta-v3-base
15
+ pipeline_tag: text-classification
16
+ model-index:
17
+ - name: founder-deberta-agnews-v1
18
+ results:
19
+ - task:
20
+ type: text-classification
21
+ name: Text Classification
22
+ dataset:
23
+ name: AG News
24
+ type: fancyzhx/ag_news
25
+ split: test
26
+ metrics:
27
+ - type: accuracy
28
+ value: 0.2500
29
+ name: Accuracy
30
+ - type: loss
31
+ value: nan
32
+ name: Eval Loss
33
+ ---
34
+
35
+ # founder-deberta-agnews-v1
36
+
37
+ Fine-tuned by **The Founder** — an autonomous ML orchestration superagent.
38
+
39
+ ## Model Description
40
+
41
+ Fine-tuned `microsoft/deberta-v3-base` on `fancyzhx/ag_news` for 4-class topic classification (World, Sports, Business, Sci/Tech). Orchestrated end-to-end by **The Founder** using Tesla T4 (Kaggle), Weights & Biases, and HuggingFace Hub.
42
+
43
+ ## Model Details
44
+
45
+ | Property | Value |
46
+ |---|---|
47
+ | Base model | microsoft/deberta-v3-base |
48
+ | Fine-tuned on | fancyzhx/ag_news |
49
+ | Task | 4-class topic classification |
50
+ | Labels | World, Sports, Business, Sci/Tech |
51
+ | Epochs | 3 |
52
+ | Batch size | 16 |
53
+ | Learning rate | 2e-05 |
54
+ | GPU | Tesla T4 (Kaggle) |
55
+ | Train loss | 0.6081 |
56
+ | Test loss | nan |
57
+ | Test accuracy | 0.2500 |
58
+ | Duration | 28.3 min |
59
+
60
+ ## How to Get Started
61
+
62
+ ```python
63
+ from transformers import pipeline
64
+ clf = pipeline("text-classification", model="zanesmit29/founder-deberta-agnews-v1")
65
+ clf("Apple announces new MacBook with M4 chip")
66
+ ```
67
+
68
+ ## Uses
69
+
70
+ ### Direct Use
71
+ Topic classification of English news articles across 4 categories: World, Sports, Business, and Science/Technology.
72
+
73
+ ### Out-of-Scope Use
74
+ Not suitable for non-English text, fine-grained news categorisation, or documents outside the news domain.
75
+
76
+ ## Training Details
77
+
78
+ ### Data
79
+ `fancyzhx/ag_news` — 120k train articles. 10% held out as validation (seed=42). 7.6k held-out test set used for final evaluation.
80
+
81
+ ### Hyperparameters
82
+
83
+ | Hyperparameter | Value |
84
+ |---|---|
85
+ | Learning rate | 2e-05 |
86
+ | Batch size | 16 |
87
+ | Epochs | 3 |
88
+ | Optimizer | AdamW |
89
+ | LR scheduler | Linear with warmup (10%) |
90
+ | Max sequence length | 128 |
91
+ | fp16 | true |
92
+
93
+ ## Results
94
+
95
+ | Metric | Value |
96
+ |---|---|
97
+ | Train loss | 0.6081 |
98
+ | Test loss | nan |
99
+ | Test accuracy | 0.2500 |
100
+ | Duration | 28.3 min |
101
+ | Hypothesis (>= 0.945) | REJECTED |
102
+
103
+ ## Experiment Tracking
104
+
105
+ [W&B Run](https://wandb.ai/zane-ml/the-founder/runs/gzr2uq6z)
106
+
107
+ ## Infrastructure
108
+
109
+ | Component | Tool |
110
+ |---|---|
111
+ | Compute | Tesla T4 (Kaggle) |
112
+ | Experiment tracking | Weights & Biases |
113
+ | Artifact storage | HuggingFace Hub |
114
+ | Orchestration | The Founder |
checkpoint-3375/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float16",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "World",
14
+ "1": "Sports",
15
+ "2": "Business",
16
+ "3": "Sci/Tech"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "Business": 2,
22
+ "Sci/Tech": 3,
23
+ "Sports": 1,
24
+ "World": 0
25
+ },
26
+ "layer_norm_eps": 1e-07,
27
+ "legacy": true,
28
+ "max_position_embeddings": 512,
29
+ "max_relative_positions": -1,
30
+ "model_type": "deberta-v2",
31
+ "norm_rel_ebd": "layer_norm",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 0,
35
+ "pooler_dropout": 0,
36
+ "pooler_hidden_act": "gelu",
37
+ "pooler_hidden_size": 768,
38
+ "pos_att_type": [
39
+ "p2c",
40
+ "c2p"
41
+ ],
42
+ "position_biased_input": false,
43
+ "position_buckets": 256,
44
+ "relative_attention": true,
45
+ "share_att_key": true,
46
+ "tie_word_embeddings": true,
47
+ "transformers_version": "5.0.0",
48
+ "type_vocab_size": 0,
49
+ "use_cache": false,
50
+ "vocab_size": 128100
51
+ }
checkpoint-3375/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f7597ca6965598c1655ac83d684e92d334eac2c878f2828809e0522e3cf8fc
3
+ size 368874960
checkpoint-3375/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6489899c6f74c5184114c3b66413051c75559c1657c25380f341b736fc1b6891
3
+ size 737873099
checkpoint-3375/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564eaddd27861d9a13d0013a39ac9940ca691eb4ac19cf19ec54d080117519bd
3
+ size 14645
checkpoint-3375/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32269671c9abe6c1f19e5553d90bbb52199df554a78c94e31d8b692f3e97d755
3
+ size 1465
checkpoint-3375/trainer_state.json ADDED
@@ -0,0 +1,521 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 3375,
3
+ "best_metric": 0.25075,
4
+ "best_model_checkpoint": "./output/checkpoint-3375",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3375,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.014814814814814815,
14
+ "grad_norm": 14.703125,
15
+ "learning_rate": 4.839506172839507e-07,
16
+ "loss": 2.7555511474609373,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.02962962962962963,
21
+ "grad_norm": 6.84375,
22
+ "learning_rate": 9.77777777777778e-07,
23
+ "loss": 2.589150390625,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.044444444444444446,
28
+ "grad_norm": 13.71875,
29
+ "learning_rate": 1.4716049382716049e-06,
30
+ "loss": 2.321207733154297,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.05925925925925926,
35
+ "grad_norm": 11.1640625,
36
+ "learning_rate": 1.9654320987654324e-06,
37
+ "loss": 3.3190377807617186,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.07407407407407407,
42
+ "grad_norm": 1.9033203125,
43
+ "learning_rate": 2.4592592592592594e-06,
44
+ "loss": 2.7899411010742186,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.08888888888888889,
49
+ "grad_norm": 2.15234375,
50
+ "learning_rate": 2.953086419753087e-06,
51
+ "loss": 2.797424621582031,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.1037037037037037,
56
+ "grad_norm": 2.6875,
57
+ "learning_rate": 3.446913580246914e-06,
58
+ "loss": 2.79511474609375,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.11851851851851852,
63
+ "grad_norm": 2.25,
64
+ "learning_rate": 3.940740740740741e-06,
65
+ "loss": 2.7841900634765624,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.13333333333333333,
70
+ "grad_norm": 5.23828125,
71
+ "learning_rate": 4.434567901234568e-06,
72
+ "loss": 2.7853240966796875,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.14814814814814814,
77
+ "grad_norm": 1.57421875,
78
+ "learning_rate": 4.928395061728396e-06,
79
+ "loss": 2.783239440917969,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.16296296296296298,
84
+ "grad_norm": 2.755859375,
85
+ "learning_rate": 5.422222222222223e-06,
86
+ "loss": 2.794045104980469,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.17777777777777778,
91
+ "grad_norm": 2.765625,
92
+ "learning_rate": 5.916049382716051e-06,
93
+ "loss": 2.7928729248046875,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.1925925925925926,
98
+ "grad_norm": 1.4453125,
99
+ "learning_rate": 6.409876543209877e-06,
100
+ "loss": 2.7895327758789064,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.2074074074074074,
105
+ "grad_norm": 2.66796875,
106
+ "learning_rate": 6.903703703703705e-06,
107
+ "loss": 2.8108990478515623,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.2222222222222222,
112
+ "grad_norm": 1.375,
113
+ "learning_rate": 7.3975308641975315e-06,
114
+ "loss": 2.7918222045898435,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.23703703703703705,
119
+ "grad_norm": 1.8095703125,
120
+ "learning_rate": 7.89135802469136e-06,
121
+ "loss": 2.7923590087890626,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.2518518518518518,
126
+ "grad_norm": 3.416015625,
127
+ "learning_rate": 8.385185185185187e-06,
128
+ "loss": 2.7858929443359375,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.26666666666666666,
133
+ "grad_norm": 1.12890625,
134
+ "learning_rate": 8.879012345679013e-06,
135
+ "loss": 2.7902545166015624,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.2814814814814815,
140
+ "grad_norm": 1.3896484375,
141
+ "learning_rate": 9.37283950617284e-06,
142
+ "loss": 2.7882501220703126,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.2962962962962963,
147
+ "grad_norm": 1.427734375,
148
+ "learning_rate": 9.866666666666668e-06,
149
+ "loss": 2.787886962890625,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.3111111111111111,
154
+ "grad_norm": 2.126953125,
155
+ "learning_rate": 1.0360493827160493e-05,
156
+ "loss": 2.7724993896484373,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.32592592592592595,
161
+ "grad_norm": 2.55078125,
162
+ "learning_rate": 1.0854320987654322e-05,
163
+ "loss": 2.7831326293945313,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.34074074074074073,
168
+ "grad_norm": 1.505859375,
169
+ "learning_rate": 1.1348148148148148e-05,
170
+ "loss": 2.7880413818359373,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.35555555555555557,
175
+ "grad_norm": 2.021484375,
176
+ "learning_rate": 1.1841975308641975e-05,
177
+ "loss": 2.783760986328125,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.37037037037037035,
182
+ "grad_norm": 2.03515625,
183
+ "learning_rate": 1.2335802469135803e-05,
184
+ "loss": 2.7912301635742187,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.3851851851851852,
189
+ "grad_norm": 2.67578125,
190
+ "learning_rate": 1.282962962962963e-05,
191
+ "loss": 2.781982116699219,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.4,
196
+ "grad_norm": 1.6728515625,
197
+ "learning_rate": 1.3323456790123456e-05,
198
+ "loss": 2.7776669311523436,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.4148148148148148,
203
+ "grad_norm": 1.490234375,
204
+ "learning_rate": 1.3817283950617285e-05,
205
+ "loss": 2.77203857421875,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.42962962962962964,
210
+ "grad_norm": 1.0791015625,
211
+ "learning_rate": 1.4311111111111111e-05,
212
+ "loss": 2.794616394042969,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.4444444444444444,
217
+ "grad_norm": NaN,
218
+ "learning_rate": 1.480493827160494e-05,
219
+ "loss": 1.4020367431640626,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.45925925925925926,
224
+ "grad_norm": NaN,
225
+ "learning_rate": 1.5298765432098768e-05,
226
+ "loss": 0.0,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.4740740740740741,
231
+ "grad_norm": NaN,
232
+ "learning_rate": 1.5792592592592595e-05,
233
+ "loss": 0.0,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.4888888888888889,
238
+ "grad_norm": NaN,
239
+ "learning_rate": 1.628641975308642e-05,
240
+ "loss": 0.0,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.5037037037037037,
245
+ "grad_norm": NaN,
246
+ "learning_rate": 1.6780246913580248e-05,
247
+ "loss": 0.0,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.5185185185185185,
252
+ "grad_norm": NaN,
253
+ "learning_rate": 1.7274074074074075e-05,
254
+ "loss": 0.0,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.5333333333333333,
259
+ "grad_norm": NaN,
260
+ "learning_rate": 1.7767901234567905e-05,
261
+ "loss": 0.0,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.5481481481481482,
266
+ "grad_norm": NaN,
267
+ "learning_rate": 1.826172839506173e-05,
268
+ "loss": 0.0,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.562962962962963,
273
+ "grad_norm": NaN,
274
+ "learning_rate": 1.8755555555555558e-05,
275
+ "loss": 0.0,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.5777777777777777,
280
+ "grad_norm": NaN,
281
+ "learning_rate": 1.9249382716049385e-05,
282
+ "loss": 0.0,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.5925925925925926,
287
+ "grad_norm": NaN,
288
+ "learning_rate": 1.974320987654321e-05,
289
+ "loss": 0.0,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.6074074074074074,
294
+ "grad_norm": NaN,
295
+ "learning_rate": 1.9940740740740744e-05,
296
+ "loss": 0.0,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.6222222222222222,
301
+ "grad_norm": NaN,
302
+ "learning_rate": 1.9817283950617285e-05,
303
+ "loss": 0.0,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.6370370370370371,
308
+ "grad_norm": NaN,
309
+ "learning_rate": 1.969382716049383e-05,
310
+ "loss": 0.0,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.6518518518518519,
315
+ "grad_norm": NaN,
316
+ "learning_rate": 1.9570370370370373e-05,
317
+ "loss": 0.0,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.6666666666666666,
322
+ "grad_norm": NaN,
323
+ "learning_rate": 1.9446913580246914e-05,
324
+ "loss": 0.0,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.6814814814814815,
329
+ "grad_norm": NaN,
330
+ "learning_rate": 1.932345679012346e-05,
331
+ "loss": 0.0,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.6962962962962963,
336
+ "grad_norm": NaN,
337
+ "learning_rate": 1.9200000000000003e-05,
338
+ "loss": 0.0,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.7111111111111111,
343
+ "grad_norm": NaN,
344
+ "learning_rate": 1.9076543209876547e-05,
345
+ "loss": 0.0,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.725925925925926,
350
+ "grad_norm": NaN,
351
+ "learning_rate": 1.8953086419753087e-05,
352
+ "loss": 0.0,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.7407407407407407,
357
+ "grad_norm": NaN,
358
+ "learning_rate": 1.882962962962963e-05,
359
+ "loss": 0.0,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.7555555555555555,
364
+ "grad_norm": NaN,
365
+ "learning_rate": 1.8706172839506172e-05,
366
+ "loss": 0.0,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.7703703703703704,
371
+ "grad_norm": NaN,
372
+ "learning_rate": 1.858271604938272e-05,
373
+ "loss": 0.0,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.7851851851851852,
378
+ "grad_norm": NaN,
379
+ "learning_rate": 1.845925925925926e-05,
380
+ "loss": 0.0,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.8,
385
+ "grad_norm": NaN,
386
+ "learning_rate": 1.8335802469135805e-05,
387
+ "loss": 0.0,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.8148148148148148,
392
+ "grad_norm": NaN,
393
+ "learning_rate": 1.8212345679012346e-05,
394
+ "loss": 0.0,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.8296296296296296,
399
+ "grad_norm": NaN,
400
+ "learning_rate": 1.808888888888889e-05,
401
+ "loss": 0.0,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.8444444444444444,
406
+ "grad_norm": NaN,
407
+ "learning_rate": 1.7965432098765434e-05,
408
+ "loss": 0.0,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.8592592592592593,
413
+ "grad_norm": NaN,
414
+ "learning_rate": 1.784197530864198e-05,
415
+ "loss": 0.0,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.8740740740740741,
420
+ "grad_norm": NaN,
421
+ "learning_rate": 1.771851851851852e-05,
422
+ "loss": 0.0,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.8888888888888888,
427
+ "grad_norm": NaN,
428
+ "learning_rate": 1.7595061728395063e-05,
429
+ "loss": 0.0,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.9037037037037037,
434
+ "grad_norm": NaN,
435
+ "learning_rate": 1.7471604938271608e-05,
436
+ "loss": 0.0,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.9185185185185185,
441
+ "grad_norm": NaN,
442
+ "learning_rate": 1.734814814814815e-05,
443
+ "loss": 0.0,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.9333333333333333,
448
+ "grad_norm": NaN,
449
+ "learning_rate": 1.7224691358024693e-05,
450
+ "loss": 0.0,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.9481481481481482,
455
+ "grad_norm": NaN,
456
+ "learning_rate": 1.7101234567901237e-05,
457
+ "loss": 0.0,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.9629629629629629,
462
+ "grad_norm": NaN,
463
+ "learning_rate": 1.697777777777778e-05,
464
+ "loss": 0.0,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.9777777777777777,
469
+ "grad_norm": NaN,
470
+ "learning_rate": 1.685432098765432e-05,
471
+ "loss": 0.0,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.9925925925925926,
476
+ "grad_norm": NaN,
477
+ "learning_rate": 1.6730864197530866e-05,
478
+ "loss": 0.0,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 1.0,
483
+ "eval_accuracy": 0.25075,
484
+ "eval_loss": NaN,
485
+ "eval_runtime": 17.2707,
486
+ "eval_samples_per_second": 694.818,
487
+ "eval_steps_per_second": 5.443,
488
+ "step": 3375
489
+ }
490
+ ],
491
+ "logging_steps": 50,
492
+ "max_steps": 10125,
493
+ "num_input_tokens_seen": 0,
494
+ "num_train_epochs": 3,
495
+ "save_steps": 500,
496
+ "stateful_callbacks": {
497
+ "EarlyStoppingCallback": {
498
+ "args": {
499
+ "early_stopping_patience": 1,
500
+ "early_stopping_threshold": 0.0
501
+ },
502
+ "attributes": {
503
+ "early_stopping_patience_counter": 0
504
+ }
505
+ },
506
+ "TrainerControl": {
507
+ "args": {
508
+ "should_epoch_stop": false,
509
+ "should_evaluate": false,
510
+ "should_log": false,
511
+ "should_save": true,
512
+ "should_training_stop": false
513
+ },
514
+ "attributes": {}
515
+ }
516
+ },
517
+ "total_flos": 7104253464576000.0,
518
+ "train_batch_size": 32,
519
+ "trial_name": null,
520
+ "trial_params": null
521
+ }
checkpoint-3375/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c254fc621281085336573f9bac919fbf732b0f6220b544a5ec62f99aaa22512
3
+ size 5201
checkpoint-6750/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float16",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "World",
14
+ "1": "Sports",
15
+ "2": "Business",
16
+ "3": "Sci/Tech"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "Business": 2,
22
+ "Sci/Tech": 3,
23
+ "Sports": 1,
24
+ "World": 0
25
+ },
26
+ "layer_norm_eps": 1e-07,
27
+ "legacy": true,
28
+ "max_position_embeddings": 512,
29
+ "max_relative_positions": -1,
30
+ "model_type": "deberta-v2",
31
+ "norm_rel_ebd": "layer_norm",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 0,
35
+ "pooler_dropout": 0,
36
+ "pooler_hidden_act": "gelu",
37
+ "pooler_hidden_size": 768,
38
+ "pos_att_type": [
39
+ "p2c",
40
+ "c2p"
41
+ ],
42
+ "position_biased_input": false,
43
+ "position_buckets": 256,
44
+ "relative_attention": true,
45
+ "share_att_key": true,
46
+ "tie_word_embeddings": true,
47
+ "transformers_version": "5.0.0",
48
+ "type_vocab_size": 0,
49
+ "use_cache": false,
50
+ "vocab_size": 128100
51
+ }
checkpoint-6750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f7597ca6965598c1655ac83d684e92d334eac2c878f2828809e0522e3cf8fc
3
+ size 368874960
checkpoint-6750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f5ab17b4801f3777d3a0b3f0c0be612b471d9f1dd5784fe7a8b5897c90c1f61
3
+ size 737873099
checkpoint-6750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e63ad524afe4b24b2659fb48b3c02bebb2308485b93b0b62c3636c0583902eff
3
+ size 14645
checkpoint-6750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81dabad12ac102b2ee834773ff1aee7945c1d985ea247c2e71f4e881e83d31d9
3
+ size 1465
checkpoint-6750/trainer_state.json ADDED
@@ -0,0 +1,1006 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 3375,
3
+ "best_metric": 0.25075,
4
+ "best_model_checkpoint": "./output/checkpoint-3375",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 6750,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.014814814814814815,
14
+ "grad_norm": 14.703125,
15
+ "learning_rate": 4.839506172839507e-07,
16
+ "loss": 2.7555511474609373,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.02962962962962963,
21
+ "grad_norm": 6.84375,
22
+ "learning_rate": 9.77777777777778e-07,
23
+ "loss": 2.589150390625,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.044444444444444446,
28
+ "grad_norm": 13.71875,
29
+ "learning_rate": 1.4716049382716049e-06,
30
+ "loss": 2.321207733154297,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.05925925925925926,
35
+ "grad_norm": 11.1640625,
36
+ "learning_rate": 1.9654320987654324e-06,
37
+ "loss": 3.3190377807617186,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.07407407407407407,
42
+ "grad_norm": 1.9033203125,
43
+ "learning_rate": 2.4592592592592594e-06,
44
+ "loss": 2.7899411010742186,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.08888888888888889,
49
+ "grad_norm": 2.15234375,
50
+ "learning_rate": 2.953086419753087e-06,
51
+ "loss": 2.797424621582031,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.1037037037037037,
56
+ "grad_norm": 2.6875,
57
+ "learning_rate": 3.446913580246914e-06,
58
+ "loss": 2.79511474609375,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.11851851851851852,
63
+ "grad_norm": 2.25,
64
+ "learning_rate": 3.940740740740741e-06,
65
+ "loss": 2.7841900634765624,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.13333333333333333,
70
+ "grad_norm": 5.23828125,
71
+ "learning_rate": 4.434567901234568e-06,
72
+ "loss": 2.7853240966796875,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.14814814814814814,
77
+ "grad_norm": 1.57421875,
78
+ "learning_rate": 4.928395061728396e-06,
79
+ "loss": 2.783239440917969,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.16296296296296298,
84
+ "grad_norm": 2.755859375,
85
+ "learning_rate": 5.422222222222223e-06,
86
+ "loss": 2.794045104980469,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.17777777777777778,
91
+ "grad_norm": 2.765625,
92
+ "learning_rate": 5.916049382716051e-06,
93
+ "loss": 2.7928729248046875,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.1925925925925926,
98
+ "grad_norm": 1.4453125,
99
+ "learning_rate": 6.409876543209877e-06,
100
+ "loss": 2.7895327758789064,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.2074074074074074,
105
+ "grad_norm": 2.66796875,
106
+ "learning_rate": 6.903703703703705e-06,
107
+ "loss": 2.8108990478515623,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.2222222222222222,
112
+ "grad_norm": 1.375,
113
+ "learning_rate": 7.3975308641975315e-06,
114
+ "loss": 2.7918222045898435,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.23703703703703705,
119
+ "grad_norm": 1.8095703125,
120
+ "learning_rate": 7.89135802469136e-06,
121
+ "loss": 2.7923590087890626,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.2518518518518518,
126
+ "grad_norm": 3.416015625,
127
+ "learning_rate": 8.385185185185187e-06,
128
+ "loss": 2.7858929443359375,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.26666666666666666,
133
+ "grad_norm": 1.12890625,
134
+ "learning_rate": 8.879012345679013e-06,
135
+ "loss": 2.7902545166015624,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.2814814814814815,
140
+ "grad_norm": 1.3896484375,
141
+ "learning_rate": 9.37283950617284e-06,
142
+ "loss": 2.7882501220703126,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.2962962962962963,
147
+ "grad_norm": 1.427734375,
148
+ "learning_rate": 9.866666666666668e-06,
149
+ "loss": 2.787886962890625,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.3111111111111111,
154
+ "grad_norm": 2.126953125,
155
+ "learning_rate": 1.0360493827160493e-05,
156
+ "loss": 2.7724993896484373,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.32592592592592595,
161
+ "grad_norm": 2.55078125,
162
+ "learning_rate": 1.0854320987654322e-05,
163
+ "loss": 2.7831326293945313,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.34074074074074073,
168
+ "grad_norm": 1.505859375,
169
+ "learning_rate": 1.1348148148148148e-05,
170
+ "loss": 2.7880413818359373,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.35555555555555557,
175
+ "grad_norm": 2.021484375,
176
+ "learning_rate": 1.1841975308641975e-05,
177
+ "loss": 2.783760986328125,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.37037037037037035,
182
+ "grad_norm": 2.03515625,
183
+ "learning_rate": 1.2335802469135803e-05,
184
+ "loss": 2.7912301635742187,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.3851851851851852,
189
+ "grad_norm": 2.67578125,
190
+ "learning_rate": 1.282962962962963e-05,
191
+ "loss": 2.781982116699219,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.4,
196
+ "grad_norm": 1.6728515625,
197
+ "learning_rate": 1.3323456790123456e-05,
198
+ "loss": 2.7776669311523436,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.4148148148148148,
203
+ "grad_norm": 1.490234375,
204
+ "learning_rate": 1.3817283950617285e-05,
205
+ "loss": 2.77203857421875,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.42962962962962964,
210
+ "grad_norm": 1.0791015625,
211
+ "learning_rate": 1.4311111111111111e-05,
212
+ "loss": 2.794616394042969,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.4444444444444444,
217
+ "grad_norm": NaN,
218
+ "learning_rate": 1.480493827160494e-05,
219
+ "loss": 1.4020367431640626,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.45925925925925926,
224
+ "grad_norm": NaN,
225
+ "learning_rate": 1.5298765432098768e-05,
226
+ "loss": 0.0,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.4740740740740741,
231
+ "grad_norm": NaN,
232
+ "learning_rate": 1.5792592592592595e-05,
233
+ "loss": 0.0,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.4888888888888889,
238
+ "grad_norm": NaN,
239
+ "learning_rate": 1.628641975308642e-05,
240
+ "loss": 0.0,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.5037037037037037,
245
+ "grad_norm": NaN,
246
+ "learning_rate": 1.6780246913580248e-05,
247
+ "loss": 0.0,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.5185185185185185,
252
+ "grad_norm": NaN,
253
+ "learning_rate": 1.7274074074074075e-05,
254
+ "loss": 0.0,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.5333333333333333,
259
+ "grad_norm": NaN,
260
+ "learning_rate": 1.7767901234567905e-05,
261
+ "loss": 0.0,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.5481481481481482,
266
+ "grad_norm": NaN,
267
+ "learning_rate": 1.826172839506173e-05,
268
+ "loss": 0.0,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.562962962962963,
273
+ "grad_norm": NaN,
274
+ "learning_rate": 1.8755555555555558e-05,
275
+ "loss": 0.0,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.5777777777777777,
280
+ "grad_norm": NaN,
281
+ "learning_rate": 1.9249382716049385e-05,
282
+ "loss": 0.0,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.5925925925925926,
287
+ "grad_norm": NaN,
288
+ "learning_rate": 1.974320987654321e-05,
289
+ "loss": 0.0,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.6074074074074074,
294
+ "grad_norm": NaN,
295
+ "learning_rate": 1.9940740740740744e-05,
296
+ "loss": 0.0,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.6222222222222222,
301
+ "grad_norm": NaN,
302
+ "learning_rate": 1.9817283950617285e-05,
303
+ "loss": 0.0,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.6370370370370371,
308
+ "grad_norm": NaN,
309
+ "learning_rate": 1.969382716049383e-05,
310
+ "loss": 0.0,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.6518518518518519,
315
+ "grad_norm": NaN,
316
+ "learning_rate": 1.9570370370370373e-05,
317
+ "loss": 0.0,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.6666666666666666,
322
+ "grad_norm": NaN,
323
+ "learning_rate": 1.9446913580246914e-05,
324
+ "loss": 0.0,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.6814814814814815,
329
+ "grad_norm": NaN,
330
+ "learning_rate": 1.932345679012346e-05,
331
+ "loss": 0.0,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.6962962962962963,
336
+ "grad_norm": NaN,
337
+ "learning_rate": 1.9200000000000003e-05,
338
+ "loss": 0.0,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.7111111111111111,
343
+ "grad_norm": NaN,
344
+ "learning_rate": 1.9076543209876547e-05,
345
+ "loss": 0.0,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.725925925925926,
350
+ "grad_norm": NaN,
351
+ "learning_rate": 1.8953086419753087e-05,
352
+ "loss": 0.0,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.7407407407407407,
357
+ "grad_norm": NaN,
358
+ "learning_rate": 1.882962962962963e-05,
359
+ "loss": 0.0,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.7555555555555555,
364
+ "grad_norm": NaN,
365
+ "learning_rate": 1.8706172839506172e-05,
366
+ "loss": 0.0,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.7703703703703704,
371
+ "grad_norm": NaN,
372
+ "learning_rate": 1.858271604938272e-05,
373
+ "loss": 0.0,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.7851851851851852,
378
+ "grad_norm": NaN,
379
+ "learning_rate": 1.845925925925926e-05,
380
+ "loss": 0.0,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.8,
385
+ "grad_norm": NaN,
386
+ "learning_rate": 1.8335802469135805e-05,
387
+ "loss": 0.0,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.8148148148148148,
392
+ "grad_norm": NaN,
393
+ "learning_rate": 1.8212345679012346e-05,
394
+ "loss": 0.0,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.8296296296296296,
399
+ "grad_norm": NaN,
400
+ "learning_rate": 1.808888888888889e-05,
401
+ "loss": 0.0,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.8444444444444444,
406
+ "grad_norm": NaN,
407
+ "learning_rate": 1.7965432098765434e-05,
408
+ "loss": 0.0,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.8592592592592593,
413
+ "grad_norm": NaN,
414
+ "learning_rate": 1.784197530864198e-05,
415
+ "loss": 0.0,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.8740740740740741,
420
+ "grad_norm": NaN,
421
+ "learning_rate": 1.771851851851852e-05,
422
+ "loss": 0.0,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.8888888888888888,
427
+ "grad_norm": NaN,
428
+ "learning_rate": 1.7595061728395063e-05,
429
+ "loss": 0.0,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.9037037037037037,
434
+ "grad_norm": NaN,
435
+ "learning_rate": 1.7471604938271608e-05,
436
+ "loss": 0.0,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.9185185185185185,
441
+ "grad_norm": NaN,
442
+ "learning_rate": 1.734814814814815e-05,
443
+ "loss": 0.0,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.9333333333333333,
448
+ "grad_norm": NaN,
449
+ "learning_rate": 1.7224691358024693e-05,
450
+ "loss": 0.0,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.9481481481481482,
455
+ "grad_norm": NaN,
456
+ "learning_rate": 1.7101234567901237e-05,
457
+ "loss": 0.0,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.9629629629629629,
462
+ "grad_norm": NaN,
463
+ "learning_rate": 1.697777777777778e-05,
464
+ "loss": 0.0,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.9777777777777777,
469
+ "grad_norm": NaN,
470
+ "learning_rate": 1.685432098765432e-05,
471
+ "loss": 0.0,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.9925925925925926,
476
+ "grad_norm": NaN,
477
+ "learning_rate": 1.6730864197530866e-05,
478
+ "loss": 0.0,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 1.0,
483
+ "eval_accuracy": 0.25075,
484
+ "eval_loss": NaN,
485
+ "eval_runtime": 17.2707,
486
+ "eval_samples_per_second": 694.818,
487
+ "eval_steps_per_second": 5.443,
488
+ "step": 3375
489
+ },
490
+ {
491
+ "epoch": 1.0074074074074073,
492
+ "grad_norm": NaN,
493
+ "learning_rate": 1.660740740740741e-05,
494
+ "loss": 0.0,
495
+ "step": 3400
496
+ },
497
+ {
498
+ "epoch": 1.0222222222222221,
499
+ "grad_norm": NaN,
500
+ "learning_rate": 1.648395061728395e-05,
501
+ "loss": 0.0,
502
+ "step": 3450
503
+ },
504
+ {
505
+ "epoch": 1.037037037037037,
506
+ "grad_norm": NaN,
507
+ "learning_rate": 1.6360493827160495e-05,
508
+ "loss": 0.0,
509
+ "step": 3500
510
+ },
511
+ {
512
+ "epoch": 1.0518518518518518,
513
+ "grad_norm": NaN,
514
+ "learning_rate": 1.623703703703704e-05,
515
+ "loss": 0.0,
516
+ "step": 3550
517
+ },
518
+ {
519
+ "epoch": 1.0666666666666667,
520
+ "grad_norm": NaN,
521
+ "learning_rate": 1.611358024691358e-05,
522
+ "loss": 0.0,
523
+ "step": 3600
524
+ },
525
+ {
526
+ "epoch": 1.0814814814814815,
527
+ "grad_norm": NaN,
528
+ "learning_rate": 1.5990123456790124e-05,
529
+ "loss": 0.0,
530
+ "step": 3650
531
+ },
532
+ {
533
+ "epoch": 1.0962962962962963,
534
+ "grad_norm": NaN,
535
+ "learning_rate": 1.586666666666667e-05,
536
+ "loss": 0.0,
537
+ "step": 3700
538
+ },
539
+ {
540
+ "epoch": 1.1111111111111112,
541
+ "grad_norm": NaN,
542
+ "learning_rate": 1.574320987654321e-05,
543
+ "loss": 0.0,
544
+ "step": 3750
545
+ },
546
+ {
547
+ "epoch": 1.125925925925926,
548
+ "grad_norm": NaN,
549
+ "learning_rate": 1.5619753086419753e-05,
550
+ "loss": 0.0,
551
+ "step": 3800
552
+ },
553
+ {
554
+ "epoch": 1.1407407407407408,
555
+ "grad_norm": NaN,
556
+ "learning_rate": 1.5496296296296298e-05,
557
+ "loss": 0.0,
558
+ "step": 3850
559
+ },
560
+ {
561
+ "epoch": 1.1555555555555554,
562
+ "grad_norm": NaN,
563
+ "learning_rate": 1.537283950617284e-05,
564
+ "loss": 0.0,
565
+ "step": 3900
566
+ },
567
+ {
568
+ "epoch": 1.1703703703703703,
569
+ "grad_norm": NaN,
570
+ "learning_rate": 1.5249382716049384e-05,
571
+ "loss": 0.0,
572
+ "step": 3950
573
+ },
574
+ {
575
+ "epoch": 1.1851851851851851,
576
+ "grad_norm": NaN,
577
+ "learning_rate": 1.5125925925925927e-05,
578
+ "loss": 0.0,
579
+ "step": 4000
580
+ },
581
+ {
582
+ "epoch": 1.2,
583
+ "grad_norm": NaN,
584
+ "learning_rate": 1.5002469135802471e-05,
585
+ "loss": 0.0,
586
+ "step": 4050
587
+ },
588
+ {
589
+ "epoch": 1.2148148148148148,
590
+ "grad_norm": NaN,
591
+ "learning_rate": 1.4879012345679013e-05,
592
+ "loss": 0.0,
593
+ "step": 4100
594
+ },
595
+ {
596
+ "epoch": 1.2296296296296296,
597
+ "grad_norm": NaN,
598
+ "learning_rate": 1.4755555555555556e-05,
599
+ "loss": 0.0,
600
+ "step": 4150
601
+ },
602
+ {
603
+ "epoch": 1.2444444444444445,
604
+ "grad_norm": NaN,
605
+ "learning_rate": 1.4632098765432098e-05,
606
+ "loss": 0.0,
607
+ "step": 4200
608
+ },
609
+ {
610
+ "epoch": 1.2592592592592593,
611
+ "grad_norm": NaN,
612
+ "learning_rate": 1.4508641975308644e-05,
613
+ "loss": 0.0,
614
+ "step": 4250
615
+ },
616
+ {
617
+ "epoch": 1.2740740740740741,
618
+ "grad_norm": NaN,
619
+ "learning_rate": 1.4385185185185187e-05,
620
+ "loss": 0.0,
621
+ "step": 4300
622
+ },
623
+ {
624
+ "epoch": 1.2888888888888888,
625
+ "grad_norm": NaN,
626
+ "learning_rate": 1.426172839506173e-05,
627
+ "loss": 0.0,
628
+ "step": 4350
629
+ },
630
+ {
631
+ "epoch": 1.3037037037037038,
632
+ "grad_norm": NaN,
633
+ "learning_rate": 1.4138271604938272e-05,
634
+ "loss": 0.0,
635
+ "step": 4400
636
+ },
637
+ {
638
+ "epoch": 1.3185185185185184,
639
+ "grad_norm": NaN,
640
+ "learning_rate": 1.4014814814814816e-05,
641
+ "loss": 0.0,
642
+ "step": 4450
643
+ },
644
+ {
645
+ "epoch": 1.3333333333333333,
646
+ "grad_norm": NaN,
647
+ "learning_rate": 1.389135802469136e-05,
648
+ "loss": 0.0,
649
+ "step": 4500
650
+ },
651
+ {
652
+ "epoch": 1.348148148148148,
653
+ "grad_norm": NaN,
654
+ "learning_rate": 1.3767901234567903e-05,
655
+ "loss": 0.0,
656
+ "step": 4550
657
+ },
658
+ {
659
+ "epoch": 1.362962962962963,
660
+ "grad_norm": NaN,
661
+ "learning_rate": 1.3644444444444445e-05,
662
+ "loss": 0.0,
663
+ "step": 4600
664
+ },
665
+ {
666
+ "epoch": 1.3777777777777778,
667
+ "grad_norm": NaN,
668
+ "learning_rate": 1.352098765432099e-05,
669
+ "loss": 0.0,
670
+ "step": 4650
671
+ },
672
+ {
673
+ "epoch": 1.3925925925925926,
674
+ "grad_norm": NaN,
675
+ "learning_rate": 1.3397530864197532e-05,
676
+ "loss": 0.0,
677
+ "step": 4700
678
+ },
679
+ {
680
+ "epoch": 1.4074074074074074,
681
+ "grad_norm": NaN,
682
+ "learning_rate": 1.3274074074074074e-05,
683
+ "loss": 0.0,
684
+ "step": 4750
685
+ },
686
+ {
687
+ "epoch": 1.4222222222222223,
688
+ "grad_norm": NaN,
689
+ "learning_rate": 1.3150617283950617e-05,
690
+ "loss": 0.0,
691
+ "step": 4800
692
+ },
693
+ {
694
+ "epoch": 1.4370370370370371,
695
+ "grad_norm": NaN,
696
+ "learning_rate": 1.3027160493827163e-05,
697
+ "loss": 0.0,
698
+ "step": 4850
699
+ },
700
+ {
701
+ "epoch": 1.4518518518518517,
702
+ "grad_norm": NaN,
703
+ "learning_rate": 1.2903703703703705e-05,
704
+ "loss": 0.0,
705
+ "step": 4900
706
+ },
707
+ {
708
+ "epoch": 1.4666666666666668,
709
+ "grad_norm": NaN,
710
+ "learning_rate": 1.2780246913580248e-05,
711
+ "loss": 0.0,
712
+ "step": 4950
713
+ },
714
+ {
715
+ "epoch": 1.4814814814814814,
716
+ "grad_norm": NaN,
717
+ "learning_rate": 1.265679012345679e-05,
718
+ "loss": 0.0,
719
+ "step": 5000
720
+ },
721
+ {
722
+ "epoch": 1.4962962962962962,
723
+ "grad_norm": NaN,
724
+ "learning_rate": 1.2533333333333336e-05,
725
+ "loss": 0.0,
726
+ "step": 5050
727
+ },
728
+ {
729
+ "epoch": 1.511111111111111,
730
+ "grad_norm": NaN,
731
+ "learning_rate": 1.2409876543209878e-05,
732
+ "loss": 0.0,
733
+ "step": 5100
734
+ },
735
+ {
736
+ "epoch": 1.525925925925926,
737
+ "grad_norm": NaN,
738
+ "learning_rate": 1.2286419753086421e-05,
739
+ "loss": 0.0,
740
+ "step": 5150
741
+ },
742
+ {
743
+ "epoch": 1.5407407407407407,
744
+ "grad_norm": NaN,
745
+ "learning_rate": 1.2162962962962963e-05,
746
+ "loss": 0.0,
747
+ "step": 5200
748
+ },
749
+ {
750
+ "epoch": 1.5555555555555556,
751
+ "grad_norm": NaN,
752
+ "learning_rate": 1.2039506172839508e-05,
753
+ "loss": 0.0,
754
+ "step": 5250
755
+ },
756
+ {
757
+ "epoch": 1.5703703703703704,
758
+ "grad_norm": NaN,
759
+ "learning_rate": 1.191604938271605e-05,
760
+ "loss": 0.0,
761
+ "step": 5300
762
+ },
763
+ {
764
+ "epoch": 1.585185185185185,
765
+ "grad_norm": NaN,
766
+ "learning_rate": 1.1792592592592592e-05,
767
+ "loss": 0.0,
768
+ "step": 5350
769
+ },
770
+ {
771
+ "epoch": 1.6,
772
+ "grad_norm": NaN,
773
+ "learning_rate": 1.1669135802469137e-05,
774
+ "loss": 0.0,
775
+ "step": 5400
776
+ },
777
+ {
778
+ "epoch": 1.6148148148148147,
779
+ "grad_norm": NaN,
780
+ "learning_rate": 1.1545679012345681e-05,
781
+ "loss": 0.0,
782
+ "step": 5450
783
+ },
784
+ {
785
+ "epoch": 1.6296296296296298,
786
+ "grad_norm": NaN,
787
+ "learning_rate": 1.1422222222222223e-05,
788
+ "loss": 0.0,
789
+ "step": 5500
790
+ },
791
+ {
792
+ "epoch": 1.6444444444444444,
793
+ "grad_norm": NaN,
794
+ "learning_rate": 1.1298765432098766e-05,
795
+ "loss": 0.0,
796
+ "step": 5550
797
+ },
798
+ {
799
+ "epoch": 1.6592592592592592,
800
+ "grad_norm": NaN,
801
+ "learning_rate": 1.1175308641975308e-05,
802
+ "loss": 0.0,
803
+ "step": 5600
804
+ },
805
+ {
806
+ "epoch": 1.674074074074074,
807
+ "grad_norm": NaN,
808
+ "learning_rate": 1.1051851851851854e-05,
809
+ "loss": 0.0,
810
+ "step": 5650
811
+ },
812
+ {
813
+ "epoch": 1.6888888888888889,
814
+ "grad_norm": NaN,
815
+ "learning_rate": 1.0928395061728397e-05,
816
+ "loss": 0.0,
817
+ "step": 5700
818
+ },
819
+ {
820
+ "epoch": 1.7037037037037037,
821
+ "grad_norm": NaN,
822
+ "learning_rate": 1.080493827160494e-05,
823
+ "loss": 0.0,
824
+ "step": 5750
825
+ },
826
+ {
827
+ "epoch": 1.7185185185185186,
828
+ "grad_norm": NaN,
829
+ "learning_rate": 1.0681481481481482e-05,
830
+ "loss": 0.0,
831
+ "step": 5800
832
+ },
833
+ {
834
+ "epoch": 1.7333333333333334,
835
+ "grad_norm": NaN,
836
+ "learning_rate": 1.0558024691358026e-05,
837
+ "loss": 0.0,
838
+ "step": 5850
839
+ },
840
+ {
841
+ "epoch": 1.748148148148148,
842
+ "grad_norm": NaN,
843
+ "learning_rate": 1.0434567901234568e-05,
844
+ "loss": 0.0,
845
+ "step": 5900
846
+ },
847
+ {
848
+ "epoch": 1.762962962962963,
849
+ "grad_norm": NaN,
850
+ "learning_rate": 1.0311111111111113e-05,
851
+ "loss": 0.0,
852
+ "step": 5950
853
+ },
854
+ {
855
+ "epoch": 1.7777777777777777,
856
+ "grad_norm": NaN,
857
+ "learning_rate": 1.0187654320987655e-05,
858
+ "loss": 0.0,
859
+ "step": 6000
860
+ },
861
+ {
862
+ "epoch": 1.7925925925925927,
863
+ "grad_norm": NaN,
864
+ "learning_rate": 1.00641975308642e-05,
865
+ "loss": 0.0,
866
+ "step": 6050
867
+ },
868
+ {
869
+ "epoch": 1.8074074074074074,
870
+ "grad_norm": NaN,
871
+ "learning_rate": 9.940740740740742e-06,
872
+ "loss": 0.0,
873
+ "step": 6100
874
+ },
875
+ {
876
+ "epoch": 1.8222222222222222,
877
+ "grad_norm": NaN,
878
+ "learning_rate": 9.817283950617284e-06,
879
+ "loss": 0.0,
880
+ "step": 6150
881
+ },
882
+ {
883
+ "epoch": 1.837037037037037,
884
+ "grad_norm": NaN,
885
+ "learning_rate": 9.693827160493828e-06,
886
+ "loss": 0.0,
887
+ "step": 6200
888
+ },
889
+ {
890
+ "epoch": 1.8518518518518519,
891
+ "grad_norm": NaN,
892
+ "learning_rate": 9.570370370370371e-06,
893
+ "loss": 0.0,
894
+ "step": 6250
895
+ },
896
+ {
897
+ "epoch": 1.8666666666666667,
898
+ "grad_norm": NaN,
899
+ "learning_rate": 9.446913580246915e-06,
900
+ "loss": 0.0,
901
+ "step": 6300
902
+ },
903
+ {
904
+ "epoch": 1.8814814814814815,
905
+ "grad_norm": NaN,
906
+ "learning_rate": 9.323456790123458e-06,
907
+ "loss": 0.0,
908
+ "step": 6350
909
+ },
910
+ {
911
+ "epoch": 1.8962962962962964,
912
+ "grad_norm": NaN,
913
+ "learning_rate": 9.200000000000002e-06,
914
+ "loss": 0.0,
915
+ "step": 6400
916
+ },
917
+ {
918
+ "epoch": 1.911111111111111,
919
+ "grad_norm": NaN,
920
+ "learning_rate": 9.076543209876544e-06,
921
+ "loss": 0.0,
922
+ "step": 6450
923
+ },
924
+ {
925
+ "epoch": 1.925925925925926,
926
+ "grad_norm": NaN,
927
+ "learning_rate": 8.953086419753088e-06,
928
+ "loss": 0.0,
929
+ "step": 6500
930
+ },
931
+ {
932
+ "epoch": 1.9407407407407407,
933
+ "grad_norm": NaN,
934
+ "learning_rate": 8.829629629629631e-06,
935
+ "loss": 0.0,
936
+ "step": 6550
937
+ },
938
+ {
939
+ "epoch": 1.9555555555555557,
940
+ "grad_norm": NaN,
941
+ "learning_rate": 8.706172839506173e-06,
942
+ "loss": 0.0,
943
+ "step": 6600
944
+ },
945
+ {
946
+ "epoch": 1.9703703703703703,
947
+ "grad_norm": NaN,
948
+ "learning_rate": 8.582716049382716e-06,
949
+ "loss": 0.0,
950
+ "step": 6650
951
+ },
952
+ {
953
+ "epoch": 1.9851851851851852,
954
+ "grad_norm": NaN,
955
+ "learning_rate": 8.45925925925926e-06,
956
+ "loss": 0.0,
957
+ "step": 6700
958
+ },
959
+ {
960
+ "epoch": 2.0,
961
+ "grad_norm": NaN,
962
+ "learning_rate": 8.335802469135803e-06,
963
+ "loss": 0.0,
964
+ "step": 6750
965
+ },
966
+ {
967
+ "epoch": 2.0,
968
+ "eval_accuracy": 0.25075,
969
+ "eval_loss": NaN,
970
+ "eval_runtime": 17.4556,
971
+ "eval_samples_per_second": 687.46,
972
+ "eval_steps_per_second": 5.385,
973
+ "step": 6750
974
+ }
975
+ ],
976
+ "logging_steps": 50,
977
+ "max_steps": 10125,
978
+ "num_input_tokens_seen": 0,
979
+ "num_train_epochs": 3,
980
+ "save_steps": 500,
981
+ "stateful_callbacks": {
982
+ "EarlyStoppingCallback": {
983
+ "args": {
984
+ "early_stopping_patience": 1,
985
+ "early_stopping_threshold": 0.0
986
+ },
987
+ "attributes": {
988
+ "early_stopping_patience_counter": 1
989
+ }
990
+ },
991
+ "TrainerControl": {
992
+ "args": {
993
+ "should_epoch_stop": false,
994
+ "should_evaluate": false,
995
+ "should_log": false,
996
+ "should_save": true,
997
+ "should_training_stop": true
998
+ },
999
+ "attributes": {}
1000
+ }
1001
+ },
1002
+ "total_flos": 1.4208506929152e+16,
1003
+ "train_batch_size": 32,
1004
+ "trial_name": null,
1005
+ "trial_params": null
1006
+ }
checkpoint-6750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c254fc621281085336573f9bac919fbf732b0f6220b544a5ec62f99aaa22512
3
+ size 5201
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float16",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "World",
14
+ "1": "Sports",
15
+ "2": "Business",
16
+ "3": "Sci/Tech"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "Business": 2,
22
+ "Sci/Tech": 3,
23
+ "Sports": 1,
24
+ "World": 0
25
+ },
26
+ "layer_norm_eps": 1e-07,
27
+ "legacy": true,
28
+ "max_position_embeddings": 512,
29
+ "max_relative_positions": -1,
30
+ "model_type": "deberta-v2",
31
+ "norm_rel_ebd": "layer_norm",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 0,
35
+ "pooler_dropout": 0,
36
+ "pooler_hidden_act": "gelu",
37
+ "pooler_hidden_size": 768,
38
+ "pos_att_type": [
39
+ "p2c",
40
+ "c2p"
41
+ ],
42
+ "position_biased_input": false,
43
+ "position_buckets": 256,
44
+ "relative_attention": true,
45
+ "share_att_key": true,
46
+ "tie_word_embeddings": true,
47
+ "transformers_version": "5.0.0",
48
+ "type_vocab_size": 0,
49
+ "use_cache": false,
50
+ "vocab_size": 128100
51
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f7597ca6965598c1655ac83d684e92d334eac2c878f2828809e0522e3cf8fc
3
+ size 368874960
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "extra_special_tokens": [
9
+ "[PAD]",
10
+ "[CLS]",
11
+ "[SEP]"
12
+ ],
13
+ "is_local": false,
14
+ "mask_token": "[MASK]",
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "pad_token": "[PAD]",
17
+ "sep_token": "[SEP]",
18
+ "split_by_punct": false,
19
+ "tokenizer_class": "DebertaV2Tokenizer",
20
+ "unk_id": 3,
21
+ "unk_token": "[UNK]",
22
+ "vocab_type": "spm"
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c254fc621281085336573f9bac919fbf732b0f6220b544a5ec62f99aaa22512
3
+ size 5201