samtuckervegan commited on
Commit
967740c
·
verified ·
1 Parent(s): db68344

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text-regression
6
+ base_model: allenai/longformer-base-4096
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ datasets:
10
+ - open-paws/animal_alignment_feedback
11
+ ---
12
+
13
+ # Model Trained Using AutoTrain
14
+
15
+ - Problem type: Text Regression
16
+
17
+ ## Validation Metrics
18
+ loss: 0.01995982974767685
19
+
20
+ mse: 0.019954577088356018
21
+
22
+ mae: 0.11011234670877457
23
+
24
+ r2: 0.4796050786972046
25
+
26
+ rmse: 0.14126067070616655
27
+
28
+ explained_variance: 0.4826643466949463
checkpoint-1995/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
+ "_num_labels": 1,
4
+ "architectures": [
5
+ "LongformerForSequenceClassification"
6
+ ],
7
+ "attention_mode": "longformer",
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "attention_window": [
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "bos_token_id": 0,
24
+ "eos_token_id": 2,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "target"
31
+ },
32
+ "ignore_attention_mask": false,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "target": 0
37
+ },
38
+ "layer_norm_eps": 1e-05,
39
+ "max_position_embeddings": 4098,
40
+ "model_type": "longformer",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "onnx_export": false,
44
+ "pad_token_id": 1,
45
+ "problem_type": "regression",
46
+ "sep_token_id": 2,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.48.0",
49
+ "type_vocab_size": 1,
50
+ "vocab_size": 50265
51
+ }
checkpoint-1995/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e880ca0c633fd989d7175045a7e2d62478202d24f2d85f71464dd0439c653a4
3
+ size 594675108
checkpoint-1995/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc611980ddc9547cf203c8a42b2e2a434dde670d760e5db25b1f42fb2523f54b
3
+ size 1189510202
checkpoint-1995/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a675567c784cb2560b40c5bad7898ff90c9d2173d06f68f26cd950d4f2fa4c
3
+ size 15024
checkpoint-1995/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12fbcf5dca92f6871fd9a0bf78e3f345e735991a511954cd1c6cbc9766aada38
3
+ size 15024
checkpoint-1995/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f571d0323ff470a2531b0e399342fd4d3b4f7612bd26d23801973a53076730e
3
+ size 15024
checkpoint-1995/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e906a29529fd0c99c5c46ac7d137dae5271a4cf50cc1efb56b2f3deeca7b4e55
3
+ size 15024
checkpoint-1995/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faad063d0b5c31daa74d718392911eca50dbfa84a12e587603d8c5dece6b9c73
3
+ size 1064
checkpoint-1995/trainer_state.json ADDED
@@ -0,0 +1,634 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.01995982974767685,
3
+ "best_model_checkpoint": "trustworthiness-longformer/checkpoint-1995",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1995,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03759398496240601,
13
+ "grad_norm": 9.034588813781738,
14
+ "learning_rate": 4.229323308270677e-06,
15
+ "loss": 0.5584,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.07518796992481203,
20
+ "grad_norm": 1.967883586883545,
21
+ "learning_rate": 8.1203007518797e-06,
22
+ "loss": 0.1203,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.11278195488721804,
27
+ "grad_norm": 1.5318199396133423,
28
+ "learning_rate": 1.2349624060150378e-05,
29
+ "loss": 0.0532,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.15037593984962405,
34
+ "grad_norm": 0.6738603115081787,
35
+ "learning_rate": 1.6578947368421053e-05,
36
+ "loss": 0.0438,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.18796992481203006,
41
+ "grad_norm": 2.247737169265747,
42
+ "learning_rate": 2.080827067669173e-05,
43
+ "loss": 0.0443,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.22556390977443608,
48
+ "grad_norm": 1.5706892013549805,
49
+ "learning_rate": 2.5037593984962406e-05,
50
+ "loss": 0.0422,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.2631578947368421,
55
+ "grad_norm": 1.9436813592910767,
56
+ "learning_rate": 2.9266917293233085e-05,
57
+ "loss": 0.0403,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.3007518796992481,
62
+ "grad_norm": 1.7137566804885864,
63
+ "learning_rate": 3.349624060150376e-05,
64
+ "loss": 0.0389,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.3383458646616541,
69
+ "grad_norm": 1.5335218906402588,
70
+ "learning_rate": 3.772556390977444e-05,
71
+ "loss": 0.0369,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.37593984962406013,
76
+ "grad_norm": 2.1619019508361816,
77
+ "learning_rate": 4.195488721804511e-05,
78
+ "loss": 0.0357,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.41353383458646614,
83
+ "grad_norm": 0.8143567442893982,
84
+ "learning_rate": 4.486842105263158e-05,
85
+ "loss": 0.034,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.45112781954887216,
90
+ "grad_norm": 0.34969833493232727,
91
+ "learning_rate": 4.4398496240601505e-05,
92
+ "loss": 0.0309,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.48872180451127817,
97
+ "grad_norm": 0.6551300883293152,
98
+ "learning_rate": 4.392857142857143e-05,
99
+ "loss": 0.0315,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.5263157894736842,
104
+ "grad_norm": 1.1032406091690063,
105
+ "learning_rate": 4.3458646616541354e-05,
106
+ "loss": 0.0309,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.5639097744360902,
111
+ "grad_norm": 0.3101660907268524,
112
+ "learning_rate": 4.2988721804511285e-05,
113
+ "loss": 0.03,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.6015037593984962,
118
+ "grad_norm": 0.9715960621833801,
119
+ "learning_rate": 4.251879699248121e-05,
120
+ "loss": 0.029,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.6390977443609023,
125
+ "grad_norm": 1.2566590309143066,
126
+ "learning_rate": 4.2048872180451127e-05,
127
+ "loss": 0.0311,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.6766917293233082,
132
+ "grad_norm": 0.9328742027282715,
133
+ "learning_rate": 4.157894736842105e-05,
134
+ "loss": 0.0283,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.7142857142857143,
139
+ "grad_norm": 1.1680524349212646,
140
+ "learning_rate": 4.110902255639098e-05,
141
+ "loss": 0.0279,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.7518796992481203,
146
+ "grad_norm": 0.6984049081802368,
147
+ "learning_rate": 4.0639097744360906e-05,
148
+ "loss": 0.0276,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.7894736842105263,
153
+ "grad_norm": 0.7427186965942383,
154
+ "learning_rate": 4.016917293233083e-05,
155
+ "loss": 0.0284,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.8270676691729323,
160
+ "grad_norm": 0.9322423338890076,
161
+ "learning_rate": 3.9699248120300755e-05,
162
+ "loss": 0.0267,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.8646616541353384,
167
+ "grad_norm": 0.5467056035995483,
168
+ "learning_rate": 3.922932330827068e-05,
169
+ "loss": 0.0274,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.9022556390977443,
174
+ "grad_norm": 0.7492877840995789,
175
+ "learning_rate": 3.87593984962406e-05,
176
+ "loss": 0.0266,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.9398496240601504,
181
+ "grad_norm": 1.0156948566436768,
182
+ "learning_rate": 3.828947368421053e-05,
183
+ "loss": 0.0257,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.9774436090225563,
188
+ "grad_norm": 2.6121363639831543,
189
+ "learning_rate": 3.781954887218045e-05,
190
+ "loss": 0.0255,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 1.0,
195
+ "eval_explained_variance": 0.43071454763412476,
196
+ "eval_loss": 0.021834315732121468,
197
+ "eval_mae": 0.11838787794113159,
198
+ "eval_mse": 0.021832076832652092,
199
+ "eval_r2": 0.4306418299674988,
200
+ "eval_rmse": 0.14775681653531958,
201
+ "eval_runtime": 333.3711,
202
+ "eval_samples_per_second": 63.818,
203
+ "eval_steps_per_second": 0.999,
204
+ "step": 665
205
+ },
206
+ {
207
+ "epoch": 1.0150375939849625,
208
+ "grad_norm": 1.001768708229065,
209
+ "learning_rate": 3.734962406015038e-05,
210
+ "loss": 0.0248,
211
+ "step": 675
212
+ },
213
+ {
214
+ "epoch": 1.0526315789473684,
215
+ "grad_norm": 0.44310006499290466,
216
+ "learning_rate": 3.687969924812031e-05,
217
+ "loss": 0.0248,
218
+ "step": 700
219
+ },
220
+ {
221
+ "epoch": 1.0902255639097744,
222
+ "grad_norm": 0.7214398384094238,
223
+ "learning_rate": 3.6409774436090224e-05,
224
+ "loss": 0.0241,
225
+ "step": 725
226
+ },
227
+ {
228
+ "epoch": 1.1278195488721805,
229
+ "grad_norm": 0.6446682810783386,
230
+ "learning_rate": 3.593984962406015e-05,
231
+ "loss": 0.0238,
232
+ "step": 750
233
+ },
234
+ {
235
+ "epoch": 1.1654135338345863,
236
+ "grad_norm": 0.539253830909729,
237
+ "learning_rate": 3.546992481203008e-05,
238
+ "loss": 0.0261,
239
+ "step": 775
240
+ },
241
+ {
242
+ "epoch": 1.2030075187969924,
243
+ "grad_norm": 0.4309803247451782,
244
+ "learning_rate": 3.5000000000000004e-05,
245
+ "loss": 0.0243,
246
+ "step": 800
247
+ },
248
+ {
249
+ "epoch": 1.2406015037593985,
250
+ "grad_norm": 0.2850622534751892,
251
+ "learning_rate": 3.453007518796993e-05,
252
+ "loss": 0.0239,
253
+ "step": 825
254
+ },
255
+ {
256
+ "epoch": 1.2781954887218046,
257
+ "grad_norm": 0.4944869577884674,
258
+ "learning_rate": 3.406015037593985e-05,
259
+ "loss": 0.0248,
260
+ "step": 850
261
+ },
262
+ {
263
+ "epoch": 1.3157894736842106,
264
+ "grad_norm": 0.26742395758628845,
265
+ "learning_rate": 3.3590225563909776e-05,
266
+ "loss": 0.0234,
267
+ "step": 875
268
+ },
269
+ {
270
+ "epoch": 1.3533834586466165,
271
+ "grad_norm": 1.0373315811157227,
272
+ "learning_rate": 3.31203007518797e-05,
273
+ "loss": 0.0243,
274
+ "step": 900
275
+ },
276
+ {
277
+ "epoch": 1.3909774436090225,
278
+ "grad_norm": 0.6992561221122742,
279
+ "learning_rate": 3.2650375939849625e-05,
280
+ "loss": 0.0234,
281
+ "step": 925
282
+ },
283
+ {
284
+ "epoch": 1.4285714285714286,
285
+ "grad_norm": 0.6922001242637634,
286
+ "learning_rate": 3.218045112781955e-05,
287
+ "loss": 0.024,
288
+ "step": 950
289
+ },
290
+ {
291
+ "epoch": 1.4661654135338344,
292
+ "grad_norm": 0.7946988940238953,
293
+ "learning_rate": 3.171052631578948e-05,
294
+ "loss": 0.0261,
295
+ "step": 975
296
+ },
297
+ {
298
+ "epoch": 1.5037593984962405,
299
+ "grad_norm": 0.24744807183742523,
300
+ "learning_rate": 3.1240601503759404e-05,
301
+ "loss": 0.0234,
302
+ "step": 1000
303
+ },
304
+ {
305
+ "epoch": 1.5413533834586466,
306
+ "grad_norm": 0.6126484870910645,
307
+ "learning_rate": 3.077067669172932e-05,
308
+ "loss": 0.0237,
309
+ "step": 1025
310
+ },
311
+ {
312
+ "epoch": 1.5789473684210527,
313
+ "grad_norm": 0.9163932800292969,
314
+ "learning_rate": 3.030075187969925e-05,
315
+ "loss": 0.0251,
316
+ "step": 1050
317
+ },
318
+ {
319
+ "epoch": 1.6165413533834587,
320
+ "grad_norm": 0.42940250039100647,
321
+ "learning_rate": 2.9830827067669177e-05,
322
+ "loss": 0.025,
323
+ "step": 1075
324
+ },
325
+ {
326
+ "epoch": 1.6541353383458648,
327
+ "grad_norm": 0.21495333313941956,
328
+ "learning_rate": 2.93609022556391e-05,
329
+ "loss": 0.0229,
330
+ "step": 1100
331
+ },
332
+ {
333
+ "epoch": 1.6917293233082706,
334
+ "grad_norm": 0.20642122626304626,
335
+ "learning_rate": 2.8890977443609026e-05,
336
+ "loss": 0.0223,
337
+ "step": 1125
338
+ },
339
+ {
340
+ "epoch": 1.7293233082706767,
341
+ "grad_norm": 0.2935808002948761,
342
+ "learning_rate": 2.8421052631578946e-05,
343
+ "loss": 0.0228,
344
+ "step": 1150
345
+ },
346
+ {
347
+ "epoch": 1.7669172932330826,
348
+ "grad_norm": 0.6718006730079651,
349
+ "learning_rate": 2.7951127819548878e-05,
350
+ "loss": 0.0228,
351
+ "step": 1175
352
+ },
353
+ {
354
+ "epoch": 1.8045112781954886,
355
+ "grad_norm": 0.2039840817451477,
356
+ "learning_rate": 2.74812030075188e-05,
357
+ "loss": 0.0235,
358
+ "step": 1200
359
+ },
360
+ {
361
+ "epoch": 1.8421052631578947,
362
+ "grad_norm": 0.6539952754974365,
363
+ "learning_rate": 2.7011278195488723e-05,
364
+ "loss": 0.0232,
365
+ "step": 1225
366
+ },
367
+ {
368
+ "epoch": 1.8796992481203008,
369
+ "grad_norm": 0.20303431153297424,
370
+ "learning_rate": 2.6541353383458647e-05,
371
+ "loss": 0.0243,
372
+ "step": 1250
373
+ },
374
+ {
375
+ "epoch": 1.9172932330827068,
376
+ "grad_norm": 1.0404738187789917,
377
+ "learning_rate": 2.6071428571428574e-05,
378
+ "loss": 0.0235,
379
+ "step": 1275
380
+ },
381
+ {
382
+ "epoch": 1.954887218045113,
383
+ "grad_norm": 0.4455120861530304,
384
+ "learning_rate": 2.56015037593985e-05,
385
+ "loss": 0.0234,
386
+ "step": 1300
387
+ },
388
+ {
389
+ "epoch": 1.9924812030075187,
390
+ "grad_norm": 0.29621434211730957,
391
+ "learning_rate": 2.5131578947368423e-05,
392
+ "loss": 0.0233,
393
+ "step": 1325
394
+ },
395
+ {
396
+ "epoch": 2.0,
397
+ "eval_explained_variance": 0.4605059027671814,
398
+ "eval_loss": 0.020697500556707382,
399
+ "eval_mae": 0.11327706277370453,
400
+ "eval_mse": 0.020693965256214142,
401
+ "eval_r2": 0.4603225588798523,
402
+ "eval_rmse": 0.14385397198622685,
403
+ "eval_runtime": 332.1992,
404
+ "eval_samples_per_second": 64.043,
405
+ "eval_steps_per_second": 1.002,
406
+ "step": 1330
407
+ },
408
+ {
409
+ "epoch": 2.030075187969925,
410
+ "grad_norm": 0.17958290874958038,
411
+ "learning_rate": 2.4661654135338347e-05,
412
+ "loss": 0.0235,
413
+ "step": 1350
414
+ },
415
+ {
416
+ "epoch": 2.0676691729323307,
417
+ "grad_norm": 0.27772992849349976,
418
+ "learning_rate": 2.4191729323308275e-05,
419
+ "loss": 0.0223,
420
+ "step": 1375
421
+ },
422
+ {
423
+ "epoch": 2.1052631578947367,
424
+ "grad_norm": 0.1573406457901001,
425
+ "learning_rate": 2.37218045112782e-05,
426
+ "loss": 0.0214,
427
+ "step": 1400
428
+ },
429
+ {
430
+ "epoch": 2.142857142857143,
431
+ "grad_norm": 0.704254686832428,
432
+ "learning_rate": 2.3251879699248123e-05,
433
+ "loss": 0.0224,
434
+ "step": 1425
435
+ },
436
+ {
437
+ "epoch": 2.180451127819549,
438
+ "grad_norm": 0.3219689726829529,
439
+ "learning_rate": 2.2781954887218044e-05,
440
+ "loss": 0.0219,
441
+ "step": 1450
442
+ },
443
+ {
444
+ "epoch": 2.218045112781955,
445
+ "grad_norm": 1.3933064937591553,
446
+ "learning_rate": 2.2312030075187972e-05,
447
+ "loss": 0.022,
448
+ "step": 1475
449
+ },
450
+ {
451
+ "epoch": 2.255639097744361,
452
+ "grad_norm": 0.4605341851711273,
453
+ "learning_rate": 2.1842105263157896e-05,
454
+ "loss": 0.0221,
455
+ "step": 1500
456
+ },
457
+ {
458
+ "epoch": 2.293233082706767,
459
+ "grad_norm": 0.23276148736476898,
460
+ "learning_rate": 2.137218045112782e-05,
461
+ "loss": 0.0216,
462
+ "step": 1525
463
+ },
464
+ {
465
+ "epoch": 2.3308270676691727,
466
+ "grad_norm": 0.602206289768219,
467
+ "learning_rate": 2.0902255639097745e-05,
468
+ "loss": 0.0211,
469
+ "step": 1550
470
+ },
471
+ {
472
+ "epoch": 2.3684210526315788,
473
+ "grad_norm": 0.3370234966278076,
474
+ "learning_rate": 2.0432330827067672e-05,
475
+ "loss": 0.0208,
476
+ "step": 1575
477
+ },
478
+ {
479
+ "epoch": 2.406015037593985,
480
+ "grad_norm": 0.3906821310520172,
481
+ "learning_rate": 1.9962406015037593e-05,
482
+ "loss": 0.0202,
483
+ "step": 1600
484
+ },
485
+ {
486
+ "epoch": 2.443609022556391,
487
+ "grad_norm": 0.26114577054977417,
488
+ "learning_rate": 1.949248120300752e-05,
489
+ "loss": 0.0221,
490
+ "step": 1625
491
+ },
492
+ {
493
+ "epoch": 2.481203007518797,
494
+ "grad_norm": 0.215437650680542,
495
+ "learning_rate": 1.9022556390977445e-05,
496
+ "loss": 0.023,
497
+ "step": 1650
498
+ },
499
+ {
500
+ "epoch": 2.518796992481203,
501
+ "grad_norm": 0.7732388377189636,
502
+ "learning_rate": 1.855263157894737e-05,
503
+ "loss": 0.0217,
504
+ "step": 1675
505
+ },
506
+ {
507
+ "epoch": 2.556390977443609,
508
+ "grad_norm": 0.2342628836631775,
509
+ "learning_rate": 1.8082706766917293e-05,
510
+ "loss": 0.0219,
511
+ "step": 1700
512
+ },
513
+ {
514
+ "epoch": 2.593984962406015,
515
+ "grad_norm": 0.49042457342147827,
516
+ "learning_rate": 1.761278195488722e-05,
517
+ "loss": 0.0213,
518
+ "step": 1725
519
+ },
520
+ {
521
+ "epoch": 2.6315789473684212,
522
+ "grad_norm": 0.6491354703903198,
523
+ "learning_rate": 1.7142857142857142e-05,
524
+ "loss": 0.0215,
525
+ "step": 1750
526
+ },
527
+ {
528
+ "epoch": 2.6691729323308273,
529
+ "grad_norm": 0.4228556454181671,
530
+ "learning_rate": 1.667293233082707e-05,
531
+ "loss": 0.0211,
532
+ "step": 1775
533
+ },
534
+ {
535
+ "epoch": 2.706766917293233,
536
+ "grad_norm": 0.25106143951416016,
537
+ "learning_rate": 1.6203007518796994e-05,
538
+ "loss": 0.0209,
539
+ "step": 1800
540
+ },
541
+ {
542
+ "epoch": 2.744360902255639,
543
+ "grad_norm": 0.3744986355304718,
544
+ "learning_rate": 1.5733082706766918e-05,
545
+ "loss": 0.0214,
546
+ "step": 1825
547
+ },
548
+ {
549
+ "epoch": 2.781954887218045,
550
+ "grad_norm": 1.0658032894134521,
551
+ "learning_rate": 1.5263157894736842e-05,
552
+ "loss": 0.022,
553
+ "step": 1850
554
+ },
555
+ {
556
+ "epoch": 2.819548872180451,
557
+ "grad_norm": 0.6378421187400818,
558
+ "learning_rate": 1.4793233082706768e-05,
559
+ "loss": 0.0212,
560
+ "step": 1875
561
+ },
562
+ {
563
+ "epoch": 2.857142857142857,
564
+ "grad_norm": 0.972565770149231,
565
+ "learning_rate": 1.4323308270676692e-05,
566
+ "loss": 0.0219,
567
+ "step": 1900
568
+ },
569
+ {
570
+ "epoch": 2.8947368421052633,
571
+ "grad_norm": 0.43301036953926086,
572
+ "learning_rate": 1.3853383458646618e-05,
573
+ "loss": 0.0213,
574
+ "step": 1925
575
+ },
576
+ {
577
+ "epoch": 2.932330827067669,
578
+ "grad_norm": 0.6031925082206726,
579
+ "learning_rate": 1.3383458646616541e-05,
580
+ "loss": 0.0217,
581
+ "step": 1950
582
+ },
583
+ {
584
+ "epoch": 2.969924812030075,
585
+ "grad_norm": 0.20304885506629944,
586
+ "learning_rate": 1.2913533834586467e-05,
587
+ "loss": 0.0209,
588
+ "step": 1975
589
+ },
590
+ {
591
+ "epoch": 3.0,
592
+ "eval_explained_variance": 0.4826643466949463,
593
+ "eval_loss": 0.01995982974767685,
594
+ "eval_mae": 0.11011234670877457,
595
+ "eval_mse": 0.019954577088356018,
596
+ "eval_r2": 0.4796050786972046,
597
+ "eval_rmse": 0.14126067070616655,
598
+ "eval_runtime": 332.8065,
599
+ "eval_samples_per_second": 63.926,
600
+ "eval_steps_per_second": 1.001,
601
+ "step": 1995
602
+ }
603
+ ],
604
+ "logging_steps": 25,
605
+ "max_steps": 2660,
606
+ "num_input_tokens_seen": 0,
607
+ "num_train_epochs": 4,
608
+ "save_steps": 500,
609
+ "stateful_callbacks": {
610
+ "EarlyStoppingCallback": {
611
+ "args": {
612
+ "early_stopping_patience": 5,
613
+ "early_stopping_threshold": 0.01
614
+ },
615
+ "attributes": {
616
+ "early_stopping_patience_counter": 2
617
+ }
618
+ },
619
+ "TrainerControl": {
620
+ "args": {
621
+ "should_epoch_stop": false,
622
+ "should_evaluate": false,
623
+ "should_log": false,
624
+ "should_save": true,
625
+ "should_training_stop": false
626
+ },
627
+ "attributes": {}
628
+ }
629
+ },
630
+ "total_flos": 6.709296778916659e+17,
631
+ "train_batch_size": 8,
632
+ "trial_name": null,
633
+ "trial_params": null
634
+ }
checkpoint-1995/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71aeb218e0762ccac67c95db4e13d54a6cf196371d480110a4c133356492c6f4
3
+ size 5368
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
+ "_num_labels": 1,
4
+ "architectures": [
5
+ "LongformerForSequenceClassification"
6
+ ],
7
+ "attention_mode": "longformer",
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "attention_window": [
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "bos_token_id": 0,
24
+ "eos_token_id": 2,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "target"
31
+ },
32
+ "ignore_attention_mask": false,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "target": 0
37
+ },
38
+ "layer_norm_eps": 1e-05,
39
+ "max_position_embeddings": 4098,
40
+ "model_type": "longformer",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "onnx_export": false,
44
+ "pad_token_id": 1,
45
+ "problem_type": "regression",
46
+ "sep_token_id": 2,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.48.0",
49
+ "type_vocab_size": 1,
50
+ "vocab_size": 50265
51
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e880ca0c633fd989d7175045a7e2d62478202d24f2d85f71464dd0439c653a4
3
+ size 594675108
runs/Apr05_21-33-19_r-samtuckervegan-autotrain-advanced-os00zc35-ce32e-t60ab/events.out.tfevents.1743888809.r-samtuckervegan-autotrain-advanced-os00zc35-ce32e-t60ab.216.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccb501a907a4ee5cd03bd21d67ba0899e23e8b49030e266f9b9b7c76246308a0
3
- size 28647
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d1f4fa339defe802f79a4d99895edd20c7ff42ee6158b08acf6165c1e748f18
3
+ size 30155
runs/Apr05_21-33-19_r-samtuckervegan-autotrain-advanced-os00zc35-ce32e-t60ab/events.out.tfevents.1743913966.r-samtuckervegan-autotrain-advanced-os00zc35-ce32e-t60ab.216.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a4e359f133e73902735b0f8c84918e78cac6d91449fb0968bb0ff01f94eeb36
3
+ size 609
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "LongformerTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71aeb218e0762ccac67c95db4e13d54a6cf196371d480110a4c133356492c6f4
3
+ size 5368
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "open-paws/animal_alignment_feedback",
3
+ "model": "allenai/longformer-base-4096",
4
+ "lr": 4.5e-05,
5
+ "epochs": 4,
6
+ "max_seq_length": 4096,
7
+ "batch_size": 8,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 4,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "test",
17
+ "text_column": "text",
18
+ "target_column": "rating_trustworthiness",
19
+ "logging_steps": -1,
20
+ "project_name": "trustworthiness-longformer",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "eval_strategy": "epoch",
26
+ "username": "samtuckervegan",
27
+ "log": "tensorboard",
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff