Hugging Face's logo

YagiASAFAS
/
PoliBERT-MY

Safetensors
bert
politics
Model card Files
xet
Community
YagiASAFAS commited on
Commit
4e78432
·
verified ·
1 Parent(s): 2e456f5

Training in progress, epoch 3

Browse files
Files changed (9) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-7197/config.json +125 -0
  3. run-1/checkpoint-7197/model.safetensors +3 -0
  4. run-1/checkpoint-7197/optimizer.pt +3 -0
  5. run-1/checkpoint-7197/rng_state.pth +3 -0
  6. run-1/checkpoint-7197/scaler.pt +3 -0
  7. run-1/checkpoint-7197/scheduler.pt +3 -0
  8. run-1/checkpoint-7197/trainer_state.json +646 -0
  9. run-1/checkpoint-7197/training_args.bin +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9999cc7240ed8263bf787b2aa642ae768be07d5dc6cb57accbab53463abfb27a
3
  size 438100144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb19d8f5f60ec559ca8b0f113d6118526dbcc7804bd492ae19376c21a4b3b51e
3
  size 438100144
run-1/checkpoint-7197/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41",
54
+ "42": "LABEL_42",
55
+ "43": "LABEL_43",
56
+ "44": "LABEL_44",
57
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47"
60
+ },
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 3072,
63
+ "label2id": {
64
+ "LABEL_0": 0,
65
+ "LABEL_1": 1,
66
+ "LABEL_10": 10,
67
+ "LABEL_11": 11,
68
+ "LABEL_12": 12,
69
+ "LABEL_13": 13,
70
+ "LABEL_14": 14,
71
+ "LABEL_15": 15,
72
+ "LABEL_16": 16,
73
+ "LABEL_17": 17,
74
+ "LABEL_18": 18,
75
+ "LABEL_19": 19,
76
+ "LABEL_2": 2,
77
+ "LABEL_20": 20,
78
+ "LABEL_21": 21,
79
+ "LABEL_22": 22,
80
+ "LABEL_23": 23,
81
+ "LABEL_24": 24,
82
+ "LABEL_25": 25,
83
+ "LABEL_26": 26,
84
+ "LABEL_27": 27,
85
+ "LABEL_28": 28,
86
+ "LABEL_29": 29,
87
+ "LABEL_3": 3,
88
+ "LABEL_30": 30,
89
+ "LABEL_31": 31,
90
+ "LABEL_32": 32,
91
+ "LABEL_33": 33,
92
+ "LABEL_34": 34,
93
+ "LABEL_35": 35,
94
+ "LABEL_36": 36,
95
+ "LABEL_37": 37,
96
+ "LABEL_38": 38,
97
+ "LABEL_39": 39,
98
+ "LABEL_4": 4,
99
+ "LABEL_40": 40,
100
+ "LABEL_41": 41,
101
+ "LABEL_42": 42,
102
+ "LABEL_43": 43,
103
+ "LABEL_44": 44,
104
+ "LABEL_45": 45,
105
+ "LABEL_46": 46,
106
+ "LABEL_47": 47,
107
+ "LABEL_5": 5,
108
+ "LABEL_6": 6,
109
+ "LABEL_7": 7,
110
+ "LABEL_8": 8,
111
+ "LABEL_9": 9
112
+ },
113
+ "layer_norm_eps": 1e-12,
114
+ "max_position_embeddings": 512,
115
+ "model_type": "bert",
116
+ "num_attention_heads": 12,
117
+ "num_hidden_layers": 12,
118
+ "pad_token_id": 0,
119
+ "position_embedding_type": "absolute",
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.50.3",
122
+ "type_vocab_size": 2,
123
+ "use_cache": true,
124
+ "vocab_size": 30522
125
+ }
run-1/checkpoint-7197/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb19d8f5f60ec559ca8b0f113d6118526dbcc7804bd492ae19376c21a4b3b51e
3
+ size 438100144
run-1/checkpoint-7197/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3024ea9ab720d435284c9cf4e9d572bfa3583d70c558d2f38944262fa65a78b3
3
+ size 876321402
run-1/checkpoint-7197/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:714a982d29c5cad10f1f61ff55536b945838337379aaedf05d2dafc18b602ef9
3
+ size 14244
run-1/checkpoint-7197/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ba24d8ea13580cb3e9ffd9df1030a15d15d73e1a76a486758f48659eb2546c
3
+ size 988
run-1/checkpoint-7197/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bb61cc45a97084c5970134256b1ee3e4a0fef5ea568365761abe8f943adc422
3
+ size 1064
run-1/checkpoint-7197/trainer_state.json ADDED
@@ -0,0 +1,646 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 7197,
3
+ "best_metric": 0.9372835834491008,
4
+ "best_model_checkpoint": "./results/run-1/checkpoint-7197",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 7197,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.041684035014589414,
14
+ "grad_norm": 2.362386465072632,
15
+ "learning_rate": 9.900000000000002e-06,
16
+ "loss": 1.3944,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.08336807002917883,
21
+ "grad_norm": 0.7483571767807007,
22
+ "learning_rate": 1.9900000000000003e-05,
23
+ "loss": 0.5576,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.12505210504376824,
28
+ "grad_norm": 0.8563070297241211,
29
+ "learning_rate": 2.9900000000000002e-05,
30
+ "loss": 0.4502,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.16673614005835766,
35
+ "grad_norm": 0.7200814485549927,
36
+ "learning_rate": 3.99e-05,
37
+ "loss": 0.388,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.20842017507294705,
42
+ "grad_norm": 1.4553083181381226,
43
+ "learning_rate": 4.99e-05,
44
+ "loss": 0.3508,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.25010421008753647,
49
+ "grad_norm": 0.9915399551391602,
50
+ "learning_rate": 4.978927203065135e-05,
51
+ "loss": 0.3186,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.29178824510212586,
56
+ "grad_norm": 0.9978141188621521,
57
+ "learning_rate": 4.957641549595573e-05,
58
+ "loss": 0.3087,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.3334722801167153,
63
+ "grad_norm": 1.3709461688995361,
64
+ "learning_rate": 4.936355896126011e-05,
65
+ "loss": 0.2976,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.3751563151313047,
70
+ "grad_norm": 1.82745361328125,
71
+ "learning_rate": 4.91507024265645e-05,
72
+ "loss": 0.28,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.4168403501458941,
77
+ "grad_norm": 1.2072925567626953,
78
+ "learning_rate": 4.893784589186888e-05,
79
+ "loss": 0.2751,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.45852438516048355,
84
+ "grad_norm": 1.0433937311172485,
85
+ "learning_rate": 4.872498935717327e-05,
86
+ "loss": 0.2712,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.5002084201750729,
91
+ "grad_norm": 1.1097549200057983,
92
+ "learning_rate": 4.851213282247765e-05,
93
+ "loss": 0.2909,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.5418924551896623,
98
+ "grad_norm": 1.2917771339416504,
99
+ "learning_rate": 4.8299276287782034e-05,
100
+ "loss": 0.2501,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.5835764902042517,
105
+ "grad_norm": 0.9812286496162415,
106
+ "learning_rate": 4.808641975308642e-05,
107
+ "loss": 0.2621,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.6252605252188412,
112
+ "grad_norm": 1.1786612272262573,
113
+ "learning_rate": 4.7873563218390804e-05,
114
+ "loss": 0.2435,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.6669445602334306,
119
+ "grad_norm": 1.4759145975112915,
120
+ "learning_rate": 4.766070668369519e-05,
121
+ "loss": 0.2398,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.70862859524802,
126
+ "grad_norm": 1.5548242330551147,
127
+ "learning_rate": 4.744785014899958e-05,
128
+ "loss": 0.2432,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.7503126302626094,
133
+ "grad_norm": 1.9005539417266846,
134
+ "learning_rate": 4.723499361430396e-05,
135
+ "loss": 0.2351,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.7919966652771988,
140
+ "grad_norm": 1.5831588506698608,
141
+ "learning_rate": 4.702213707960835e-05,
142
+ "loss": 0.2378,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.8336807002917882,
147
+ "grad_norm": 1.5482088327407837,
148
+ "learning_rate": 4.680928054491273e-05,
149
+ "loss": 0.2271,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 0.8753647353063777,
154
+ "grad_norm": 1.1437913179397583,
155
+ "learning_rate": 4.6596424010217114e-05,
156
+ "loss": 0.231,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 0.9170487703209671,
161
+ "grad_norm": 0.7985406517982483,
162
+ "learning_rate": 4.63835674755215e-05,
163
+ "loss": 0.228,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 0.9587328053355565,
168
+ "grad_norm": 1.9323142766952515,
169
+ "learning_rate": 4.6170710940825884e-05,
170
+ "loss": 0.2198,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 1.0,
175
+ "eval_administration_accuracy": 0.9322493224932249,
176
+ "eval_administration_f1": 0.9122911143651031,
177
+ "eval_corruption_accuracy": 0.9560141755263707,
178
+ "eval_corruption_f1": 0.9517304794081561,
179
+ "eval_democracy_accuracy": 0.9505941213258287,
180
+ "eval_democracy_f1": 0.9401838742047087,
181
+ "eval_development_accuracy": 0.9118198874296435,
182
+ "eval_development_f1": 0.9003553411809495,
183
+ "eval_economy_accuracy": 0.9264123410464874,
184
+ "eval_economy_f1": 0.9202465382357672,
185
+ "eval_education_accuracy": 0.9643527204502814,
186
+ "eval_education_f1": 0.9615509617901187,
187
+ "eval_environment_accuracy": 0.9799874921826142,
188
+ "eval_environment_f1": 0.9786142985651582,
189
+ "eval_instability_accuracy": 0.9417344173441734,
190
+ "eval_instability_f1": 0.9340921018628459,
191
+ "eval_leadership_accuracy": 0.8085261621846987,
192
+ "eval_leadership_f1": 0.7858417402549625,
193
+ "eval_loss": 0.21971678733825684,
194
+ "eval_overall_accuracy": 0.9324317281634354,
195
+ "eval_overall_f1": 0.9244250028140656,
196
+ "eval_race_accuracy": 0.9508025849489264,
197
+ "eval_race_f1": 0.9481714649378918,
198
+ "eval_religion_accuracy": 0.9530956848030019,
199
+ "eval_religion_f1": 0.9518106778632144,
200
+ "eval_runtime": 10.9084,
201
+ "eval_safety_accuracy": 0.9135918282259746,
202
+ "eval_safety_f1": 0.9082114410999095,
203
+ "eval_samples_per_second": 879.505,
204
+ "eval_steps_per_second": 55.003,
205
+ "step": 2399
206
+ },
207
+ {
208
+ "epoch": 1.0004168403501459,
209
+ "grad_norm": 1.2817295789718628,
210
+ "learning_rate": 4.5957854406130265e-05,
211
+ "loss": 0.2397,
212
+ "step": 2400
213
+ },
214
+ {
215
+ "epoch": 1.0421008753647354,
216
+ "grad_norm": 1.3623204231262207,
217
+ "learning_rate": 4.5744997871434654e-05,
218
+ "loss": 0.1885,
219
+ "step": 2500
220
+ },
221
+ {
222
+ "epoch": 1.0837849103793247,
223
+ "grad_norm": 1.2534806728363037,
224
+ "learning_rate": 4.553214133673904e-05,
225
+ "loss": 0.1843,
226
+ "step": 2600
227
+ },
228
+ {
229
+ "epoch": 1.1254689453939142,
230
+ "grad_norm": 1.2860488891601562,
231
+ "learning_rate": 4.5319284802043424e-05,
232
+ "loss": 0.1817,
233
+ "step": 2700
234
+ },
235
+ {
236
+ "epoch": 1.1671529804085035,
237
+ "grad_norm": 1.2887414693832397,
238
+ "learning_rate": 4.510642826734781e-05,
239
+ "loss": 0.1798,
240
+ "step": 2800
241
+ },
242
+ {
243
+ "epoch": 1.208837015423093,
244
+ "grad_norm": 1.973421335220337,
245
+ "learning_rate": 4.4893571732652194e-05,
246
+ "loss": 0.1878,
247
+ "step": 2900
248
+ },
249
+ {
250
+ "epoch": 1.2505210504376825,
251
+ "grad_norm": 0.7910940051078796,
252
+ "learning_rate": 4.468071519795658e-05,
253
+ "loss": 0.182,
254
+ "step": 3000
255
+ },
256
+ {
257
+ "epoch": 1.2922050854522718,
258
+ "grad_norm": 1.7422680854797363,
259
+ "learning_rate": 4.4467858663260964e-05,
260
+ "loss": 0.1833,
261
+ "step": 3100
262
+ },
263
+ {
264
+ "epoch": 1.3338891204668613,
265
+ "grad_norm": 1.1493451595306396,
266
+ "learning_rate": 4.4255002128565345e-05,
267
+ "loss": 0.1766,
268
+ "step": 3200
269
+ },
270
+ {
271
+ "epoch": 1.3755731554814505,
272
+ "grad_norm": 2.179731845855713,
273
+ "learning_rate": 4.4042145593869734e-05,
274
+ "loss": 0.1785,
275
+ "step": 3300
276
+ },
277
+ {
278
+ "epoch": 1.41725719049604,
279
+ "grad_norm": 1.5773117542266846,
280
+ "learning_rate": 4.3829289059174115e-05,
281
+ "loss": 0.1901,
282
+ "step": 3400
283
+ },
284
+ {
285
+ "epoch": 1.4589412255106295,
286
+ "grad_norm": 2.4681854248046875,
287
+ "learning_rate": 4.3616432524478504e-05,
288
+ "loss": 0.1833,
289
+ "step": 3500
290
+ },
291
+ {
292
+ "epoch": 1.5006252605252188,
293
+ "grad_norm": 2.391803503036499,
294
+ "learning_rate": 4.340357598978289e-05,
295
+ "loss": 0.1677,
296
+ "step": 3600
297
+ },
298
+ {
299
+ "epoch": 1.5423092955398081,
300
+ "grad_norm": 0.8182645440101624,
301
+ "learning_rate": 4.3190719455087274e-05,
302
+ "loss": 0.1666,
303
+ "step": 3700
304
+ },
305
+ {
306
+ "epoch": 1.5839933305543976,
307
+ "grad_norm": 1.2136952877044678,
308
+ "learning_rate": 4.297786292039166e-05,
309
+ "loss": 0.1787,
310
+ "step": 3800
311
+ },
312
+ {
313
+ "epoch": 1.6256773655689871,
314
+ "grad_norm": 2.435816764831543,
315
+ "learning_rate": 4.2765006385696044e-05,
316
+ "loss": 0.1678,
317
+ "step": 3900
318
+ },
319
+ {
320
+ "epoch": 1.6673614005835766,
321
+ "grad_norm": 1.5172932147979736,
322
+ "learning_rate": 4.2552149851000425e-05,
323
+ "loss": 0.1779,
324
+ "step": 4000
325
+ },
326
+ {
327
+ "epoch": 1.709045435598166,
328
+ "grad_norm": 1.4677119255065918,
329
+ "learning_rate": 4.2339293316304814e-05,
330
+ "loss": 0.1824,
331
+ "step": 4100
332
+ },
333
+ {
334
+ "epoch": 1.7507294706127552,
335
+ "grad_norm": 1.8327163457870483,
336
+ "learning_rate": 4.2126436781609195e-05,
337
+ "loss": 0.1719,
338
+ "step": 4200
339
+ },
340
+ {
341
+ "epoch": 1.7924135056273447,
342
+ "grad_norm": 1.2324726581573486,
343
+ "learning_rate": 4.1913580246913584e-05,
344
+ "loss": 0.1592,
345
+ "step": 4300
346
+ },
347
+ {
348
+ "epoch": 1.8340975406419342,
349
+ "grad_norm": 3.6276469230651855,
350
+ "learning_rate": 4.1700723712217965e-05,
351
+ "loss": 0.1636,
352
+ "step": 4400
353
+ },
354
+ {
355
+ "epoch": 1.8757815756565237,
356
+ "grad_norm": 0.940485417842865,
357
+ "learning_rate": 4.148786717752235e-05,
358
+ "loss": 0.1639,
359
+ "step": 4500
360
+ },
361
+ {
362
+ "epoch": 1.917465610671113,
363
+ "grad_norm": 2.002577781677246,
364
+ "learning_rate": 4.127501064282674e-05,
365
+ "loss": 0.1756,
366
+ "step": 4600
367
+ },
368
+ {
369
+ "epoch": 1.9591496456857023,
370
+ "grad_norm": 2.6062567234039307,
371
+ "learning_rate": 4.1062154108131124e-05,
372
+ "loss": 0.1729,
373
+ "step": 4700
374
+ },
375
+ {
376
+ "epoch": 2.0,
377
+ "eval_administration_accuracy": 0.9374609130706691,
378
+ "eval_administration_f1": 0.9302102302828306,
379
+ "eval_corruption_accuracy": 0.9603919116114238,
380
+ "eval_corruption_f1": 0.9585025895331236,
381
+ "eval_democracy_accuracy": 0.9562226391494684,
382
+ "eval_democracy_f1": 0.9505005443286667,
383
+ "eval_development_accuracy": 0.9199499687304565,
384
+ "eval_development_f1": 0.9145013995891959,
385
+ "eval_economy_accuracy": 0.9319366270585783,
386
+ "eval_economy_f1": 0.9302256375627648,
387
+ "eval_education_accuracy": 0.9651865749426725,
388
+ "eval_education_f1": 0.9641689686262792,
389
+ "eval_environment_accuracy": 0.9806128830519074,
390
+ "eval_environment_f1": 0.9798389855050841,
391
+ "eval_instability_accuracy": 0.9244319366270586,
392
+ "eval_instability_f1": 0.9301250908302109,
393
+ "eval_leadership_accuracy": 0.8395872420262664,
394
+ "eval_leadership_f1": 0.830858580138579,
395
+ "eval_loss": 0.20445191860198975,
396
+ "eval_overall_accuracy": 0.9366791744840525,
397
+ "eval_overall_f1": 0.9342598776015526,
398
+ "eval_race_accuracy": 0.9545549301646863,
399
+ "eval_race_f1": 0.9531323667533257,
400
+ "eval_religion_accuracy": 0.9575776526996039,
401
+ "eval_religion_f1": 0.9560680494194458,
402
+ "eval_runtime": 10.9745,
403
+ "eval_safety_accuracy": 0.9122368146758391,
404
+ "eval_safety_f1": 0.9129860886491253,
405
+ "eval_samples_per_second": 874.208,
406
+ "eval_steps_per_second": 54.672,
407
+ "step": 4798
408
+ },
409
+ {
410
+ "epoch": 2.0008336807002918,
411
+ "grad_norm": 1.0561970472335815,
412
+ "learning_rate": 4.085142613878246e-05,
413
+ "loss": 0.174,
414
+ "step": 4800
415
+ },
416
+ {
417
+ "epoch": 2.0425177157148813,
418
+ "grad_norm": 0.9414407014846802,
419
+ "learning_rate": 4.0638569604086845e-05,
420
+ "loss": 0.1259,
421
+ "step": 4900
422
+ },
423
+ {
424
+ "epoch": 2.084201750729471,
425
+ "grad_norm": 1.0318489074707031,
426
+ "learning_rate": 4.042571306939123e-05,
427
+ "loss": 0.1258,
428
+ "step": 5000
429
+ },
430
+ {
431
+ "epoch": 2.12588578574406,
432
+ "grad_norm": 2.4367470741271973,
433
+ "learning_rate": 4.0212856534695615e-05,
434
+ "loss": 0.1186,
435
+ "step": 5100
436
+ },
437
+ {
438
+ "epoch": 2.1675698207586493,
439
+ "grad_norm": 1.8129918575286865,
440
+ "learning_rate": 4e-05,
441
+ "loss": 0.1243,
442
+ "step": 5200
443
+ },
444
+ {
445
+ "epoch": 2.209253855773239,
446
+ "grad_norm": 2.235281467437744,
447
+ "learning_rate": 3.978714346530439e-05,
448
+ "loss": 0.1169,
449
+ "step": 5300
450
+ },
451
+ {
452
+ "epoch": 2.2509378907878284,
453
+ "grad_norm": 3.7830569744110107,
454
+ "learning_rate": 3.957428693060877e-05,
455
+ "loss": 0.1177,
456
+ "step": 5400
457
+ },
458
+ {
459
+ "epoch": 2.292621925802418,
460
+ "grad_norm": 1.2535426616668701,
461
+ "learning_rate": 3.9361430395913155e-05,
462
+ "loss": 0.1204,
463
+ "step": 5500
464
+ },
465
+ {
466
+ "epoch": 2.334305960817007,
467
+ "grad_norm": 1.443596601486206,
468
+ "learning_rate": 3.914857386121754e-05,
469
+ "loss": 0.1187,
470
+ "step": 5600
471
+ },
472
+ {
473
+ "epoch": 2.3759899958315964,
474
+ "grad_norm": 1.0241508483886719,
475
+ "learning_rate": 3.8935717326521925e-05,
476
+ "loss": 0.1222,
477
+ "step": 5700
478
+ },
479
+ {
480
+ "epoch": 2.417674030846186,
481
+ "grad_norm": 1.923004150390625,
482
+ "learning_rate": 3.8722860791826307e-05,
483
+ "loss": 0.1246,
484
+ "step": 5800
485
+ },
486
+ {
487
+ "epoch": 2.4593580658607754,
488
+ "grad_norm": 0.7686344385147095,
489
+ "learning_rate": 3.8510004257130695e-05,
490
+ "loss": 0.13,
491
+ "step": 5900
492
+ },
493
+ {
494
+ "epoch": 2.501042100875365,
495
+ "grad_norm": 1.762736439704895,
496
+ "learning_rate": 3.8297147722435077e-05,
497
+ "loss": 0.1263,
498
+ "step": 6000
499
+ },
500
+ {
501
+ "epoch": 2.542726135889954,
502
+ "grad_norm": 1.9006534814834595,
503
+ "learning_rate": 3.8084291187739465e-05,
504
+ "loss": 0.1152,
505
+ "step": 6100
506
+ },
507
+ {
508
+ "epoch": 2.5844101709045435,
509
+ "grad_norm": 2.003476858139038,
510
+ "learning_rate": 3.787143465304385e-05,
511
+ "loss": 0.1318,
512
+ "step": 6200
513
+ },
514
+ {
515
+ "epoch": 2.626094205919133,
516
+ "grad_norm": 1.8864182233810425,
517
+ "learning_rate": 3.7658578118348235e-05,
518
+ "loss": 0.1296,
519
+ "step": 6300
520
+ },
521
+ {
522
+ "epoch": 2.6677782409337225,
523
+ "grad_norm": 1.567968726158142,
524
+ "learning_rate": 3.744572158365262e-05,
525
+ "loss": 0.1292,
526
+ "step": 6400
527
+ },
528
+ {
529
+ "epoch": 2.7094622759483116,
530
+ "grad_norm": 1.7688707113265991,
531
+ "learning_rate": 3.7232865048957005e-05,
532
+ "loss": 0.1258,
533
+ "step": 6500
534
+ },
535
+ {
536
+ "epoch": 2.751146310962901,
537
+ "grad_norm": 2.138125419616699,
538
+ "learning_rate": 3.7020008514261387e-05,
539
+ "loss": 0.1208,
540
+ "step": 6600
541
+ },
542
+ {
543
+ "epoch": 2.7928303459774906,
544
+ "grad_norm": 3.3148305416107178,
545
+ "learning_rate": 3.6807151979565775e-05,
546
+ "loss": 0.1253,
547
+ "step": 6700
548
+ },
549
+ {
550
+ "epoch": 2.83451438099208,
551
+ "grad_norm": 1.8787152767181396,
552
+ "learning_rate": 3.6594295444870157e-05,
553
+ "loss": 0.1161,
554
+ "step": 6800
555
+ },
556
+ {
557
+ "epoch": 2.8761984160066696,
558
+ "grad_norm": 0.7995413541793823,
559
+ "learning_rate": 3.6381438910174545e-05,
560
+ "loss": 0.1196,
561
+ "step": 6900
562
+ },
563
+ {
564
+ "epoch": 2.917882451021259,
565
+ "grad_norm": 1.973639965057373,
566
+ "learning_rate": 3.6168582375478927e-05,
567
+ "loss": 0.1227,
568
+ "step": 7000
569
+ },
570
+ {
571
+ "epoch": 2.959566486035848,
572
+ "grad_norm": 1.0217853784561157,
573
+ "learning_rate": 3.5955725840783315e-05,
574
+ "loss": 0.125,
575
+ "step": 7100
576
+ },
577
+ {
578
+ "epoch": 3.0,
579
+ "eval_administration_accuracy": 0.9373566812591203,
580
+ "eval_administration_f1": 0.9333482432043958,
581
+ "eval_corruption_accuracy": 0.9609130706691682,
582
+ "eval_corruption_f1": 0.958848962871965,
583
+ "eval_democracy_accuracy": 0.9567437982072129,
584
+ "eval_democracy_f1": 0.9532298494465137,
585
+ "eval_development_accuracy": 0.9128622055451324,
586
+ "eval_development_f1": 0.9113351170841872,
587
+ "eval_economy_accuracy": 0.9317281634354805,
588
+ "eval_economy_f1": 0.9292396676492435,
589
+ "eval_education_accuracy": 0.965603502188868,
590
+ "eval_education_f1": 0.9637981071832747,
591
+ "eval_environment_accuracy": 0.9804044194288096,
592
+ "eval_environment_f1": 0.9788214035384287,
593
+ "eval_instability_accuracy": 0.9490306441525954,
594
+ "eval_instability_f1": 0.9469525951807101,
595
+ "eval_leadership_accuracy": 0.8446946007921617,
596
+ "eval_leadership_f1": 0.840338137042441,
597
+ "eval_loss": 0.20486579835414886,
598
+ "eval_overall_accuracy": 0.9398235007991106,
599
+ "eval_overall_f1": 0.9372835834491008,
600
+ "eval_race_accuracy": 0.9540337711069419,
601
+ "eval_race_f1": 0.9520143591935892,
602
+ "eval_religion_accuracy": 0.959349593495935,
603
+ "eval_religion_f1": 0.9575545048864775,
604
+ "eval_runtime": 10.9937,
605
+ "eval_safety_accuracy": 0.9251615593079008,
606
+ "eval_safety_f1": 0.9219220541079818,
607
+ "eval_samples_per_second": 872.682,
608
+ "eval_steps_per_second": 54.577,
609
+ "step": 7197
610
+ }
611
+ ],
612
+ "logging_steps": 100,
613
+ "max_steps": 23990,
614
+ "num_input_tokens_seen": 0,
615
+ "num_train_epochs": 10,
616
+ "save_steps": 500,
617
+ "stateful_callbacks": {
618
+ "EarlyStoppingCallback": {
619
+ "args": {
620
+ "early_stopping_patience": 2,
621
+ "early_stopping_threshold": 0.0
622
+ },
623
+ "attributes": {
624
+ "early_stopping_patience_counter": 0
625
+ }
626
+ },
627
+ "TrainerControl": {
628
+ "args": {
629
+ "should_epoch_stop": false,
630
+ "should_evaluate": false,
631
+ "should_log": false,
632
+ "should_save": true,
633
+ "should_training_stop": false
634
+ },
635
+ "attributes": {}
636
+ }
637
+ },
638
+ "total_flos": 2.989544340573389e+16,
639
+ "train_batch_size": 16,
640
+ "trial_name": null,
641
+ "trial_params": {
642
+ "gradient_accumulation_steps": 1,
643
+ "learning_rate": 5e-05,
644
+ "num_train_epochs": 10
645
+ }
646
+ }
run-1/checkpoint-7197/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4312a997194e916559618a59f3bbf4e1f98c127e89ae3b7fb5162b782863b12c
3
+ size 5368