mianujmi commited on
Commit
b42e747
1 Parent(s): 5e72f4f

Training in progress, epoch 5

Browse files
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9592959295929593,
4
+ "eval_loss": 0.11152195930480957,
5
+ "eval_runtime": 6.4186,
6
+ "eval_samples_per_second": 141.62,
7
+ "eval_steps_per_second": 28.355,
8
+ "train_loss": 0.2716238140671255,
9
+ "train_runtime": 385.934,
10
+ "train_samples_per_second": 63.555,
11
+ "train_steps_per_second": 3.179
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9592959295929593,
4
+ "eval_loss": 0.11152195930480957,
5
+ "eval_runtime": 6.4186,
6
+ "eval_samples_per_second": 141.62,
7
+ "eval_steps_per_second": 28.355
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4cbae4dee8c63807b2f3f9bae5d8290cdf118551b919f7aa5d2791da52f73ff
3
  size 110345908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1077783091b43cbc9477d48115be981f061dfc0ccaac0a1dc0f64d71abfb0426
3
  size 110345908
runs/Sep19_18-39-02_BLR-GPU/events.out.tfevents.1726751753.BLR-GPU.43171.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e5acdddac6e611bbcb14707e0b06cb9f979b96ffd7136797d3805ed37d4036
3
+ size 411
runs/Sep19_18-58-58_BLR-GPU/events.out.tfevents.1726752539.BLR-GPU.43492.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a40608eb57436dee1118dfd137a12228da0005b1fc6bc21b4061220bb69dc7
3
+ size 5338
runs/Sep19_19-04-04_BLR-GPU/events.out.tfevents.1726752845.BLR-GPU.43640.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552c528d73f2604d0eaecdcfc7b81c762917451d13094244d38ab708f577d124
3
+ size 6373
runs/Sep19_19-06-28_BLR-GPU/events.out.tfevents.1726752988.BLR-GPU.43741.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8440d887743a15935bfb990f5453e15dc7fe5c8969cb587896d708d8a2d8dd7
3
+ size 49742
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.2716238140671255,
4
+ "train_runtime": 385.934,
5
+ "train_samples_per_second": 63.555,
6
+ "train_steps_per_second": 3.179
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,911 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9592959295929593,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1227",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1227,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "grad_norm": 8.624119758605957,
14
+ "learning_rate": 4.0650406504065046e-06,
15
+ "loss": 1.1456,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.05,
20
+ "grad_norm": 10.445067405700684,
21
+ "learning_rate": 8.130081300813009e-06,
22
+ "loss": 1.0943,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.07,
27
+ "grad_norm": 8.588050842285156,
28
+ "learning_rate": 1.2195121951219513e-05,
29
+ "loss": 1.0114,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.1,
34
+ "grad_norm": 13.745179176330566,
35
+ "learning_rate": 1.6260162601626018e-05,
36
+ "loss": 0.9088,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.12,
41
+ "grad_norm": 16.390989303588867,
42
+ "learning_rate": 2.032520325203252e-05,
43
+ "loss": 0.8678,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "grad_norm": 23.49904441833496,
49
+ "learning_rate": 2.4390243902439026e-05,
50
+ "loss": 0.6711,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.17,
55
+ "grad_norm": 15.184337615966797,
56
+ "learning_rate": 2.8455284552845528e-05,
57
+ "loss": 0.5926,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.2,
62
+ "grad_norm": 31.39984703063965,
63
+ "learning_rate": 3.2520325203252037e-05,
64
+ "loss": 0.5689,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.22,
69
+ "grad_norm": 11.041800498962402,
70
+ "learning_rate": 3.6585365853658535e-05,
71
+ "loss": 0.5543,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.24,
76
+ "grad_norm": 23.220727920532227,
77
+ "learning_rate": 4.065040650406504e-05,
78
+ "loss": 0.4727,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.27,
83
+ "grad_norm": 7.919190406799316,
84
+ "learning_rate": 4.4715447154471546e-05,
85
+ "loss": 0.4859,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.29,
90
+ "grad_norm": 17.01369285583496,
91
+ "learning_rate": 4.878048780487805e-05,
92
+ "loss": 0.4051,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.32,
97
+ "grad_norm": 7.333168983459473,
98
+ "learning_rate": 4.968297101449276e-05,
99
+ "loss": 0.4138,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.34,
104
+ "grad_norm": 11.308248519897461,
105
+ "learning_rate": 4.9230072463768114e-05,
106
+ "loss": 0.4285,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.37,
111
+ "grad_norm": 15.314751625061035,
112
+ "learning_rate": 4.8777173913043476e-05,
113
+ "loss": 0.3061,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.39,
118
+ "grad_norm": 30.280778884887695,
119
+ "learning_rate": 4.8324275362318844e-05,
120
+ "loss": 0.4037,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.42,
125
+ "grad_norm": 9.863381385803223,
126
+ "learning_rate": 4.7871376811594205e-05,
127
+ "loss": 0.2954,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.44,
132
+ "grad_norm": 25.285860061645508,
133
+ "learning_rate": 4.741847826086957e-05,
134
+ "loss": 0.3745,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.46,
139
+ "grad_norm": 9.545634269714355,
140
+ "learning_rate": 4.696557971014493e-05,
141
+ "loss": 0.4062,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.49,
146
+ "grad_norm": 20.92987060546875,
147
+ "learning_rate": 4.651268115942029e-05,
148
+ "loss": 0.365,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.51,
153
+ "grad_norm": 9.27026081085205,
154
+ "learning_rate": 4.6059782608695657e-05,
155
+ "loss": 0.2602,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.54,
160
+ "grad_norm": 12.594367980957031,
161
+ "learning_rate": 4.560688405797102e-05,
162
+ "loss": 0.3196,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.56,
167
+ "grad_norm": 18.245967864990234,
168
+ "learning_rate": 4.515398550724638e-05,
169
+ "loss": 0.3375,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.59,
174
+ "grad_norm": 22.912260055541992,
175
+ "learning_rate": 4.470108695652174e-05,
176
+ "loss": 0.2464,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.61,
181
+ "grad_norm": 18.069555282592773,
182
+ "learning_rate": 4.42481884057971e-05,
183
+ "loss": 0.5225,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.64,
188
+ "grad_norm": 4.701681613922119,
189
+ "learning_rate": 4.379528985507246e-05,
190
+ "loss": 0.4517,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.66,
195
+ "grad_norm": 8.533316612243652,
196
+ "learning_rate": 4.334239130434783e-05,
197
+ "loss": 0.3102,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.68,
202
+ "grad_norm": 13.00133991241455,
203
+ "learning_rate": 4.288949275362319e-05,
204
+ "loss": 0.2733,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.71,
209
+ "grad_norm": 11.808174133300781,
210
+ "learning_rate": 4.243659420289855e-05,
211
+ "loss": 0.3279,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.73,
216
+ "grad_norm": 3.255472183227539,
217
+ "learning_rate": 4.1983695652173914e-05,
218
+ "loss": 0.2222,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.76,
223
+ "grad_norm": 18.238956451416016,
224
+ "learning_rate": 4.1530797101449276e-05,
225
+ "loss": 0.2738,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.78,
230
+ "grad_norm": 6.426773548126221,
231
+ "learning_rate": 4.1077898550724644e-05,
232
+ "loss": 0.2553,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.81,
237
+ "grad_norm": 11.917569160461426,
238
+ "learning_rate": 4.0625000000000005e-05,
239
+ "loss": 0.3049,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.83,
244
+ "grad_norm": 8.527942657470703,
245
+ "learning_rate": 4.017210144927536e-05,
246
+ "loss": 0.3218,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.86,
251
+ "grad_norm": 12.122479438781738,
252
+ "learning_rate": 3.971920289855073e-05,
253
+ "loss": 0.2399,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.88,
258
+ "grad_norm": 9.603090286254883,
259
+ "learning_rate": 3.926630434782609e-05,
260
+ "loss": 0.2811,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.9,
265
+ "grad_norm": 5.066426753997803,
266
+ "learning_rate": 3.881340579710145e-05,
267
+ "loss": 0.2594,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.93,
272
+ "grad_norm": 18.739673614501953,
273
+ "learning_rate": 3.836050724637682e-05,
274
+ "loss": 0.244,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.95,
279
+ "grad_norm": 17.591327667236328,
280
+ "learning_rate": 3.790760869565217e-05,
281
+ "loss": 0.3675,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.98,
286
+ "grad_norm": 12.923001289367676,
287
+ "learning_rate": 3.745471014492754e-05,
288
+ "loss": 0.3065,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 1.0,
293
+ "eval_accuracy": 0.9471947194719472,
294
+ "eval_loss": 0.15252229571342468,
295
+ "eval_runtime": 6.4388,
296
+ "eval_samples_per_second": 141.175,
297
+ "eval_steps_per_second": 28.266,
298
+ "step": 409
299
+ },
300
+ {
301
+ "epoch": 1.0,
302
+ "grad_norm": 7.585595607757568,
303
+ "learning_rate": 3.70018115942029e-05,
304
+ "loss": 0.2302,
305
+ "step": 410
306
+ },
307
+ {
308
+ "epoch": 1.03,
309
+ "grad_norm": 9.591753005981445,
310
+ "learning_rate": 3.654891304347826e-05,
311
+ "loss": 0.2185,
312
+ "step": 420
313
+ },
314
+ {
315
+ "epoch": 1.05,
316
+ "grad_norm": 18.43389320373535,
317
+ "learning_rate": 3.6096014492753624e-05,
318
+ "loss": 0.1938,
319
+ "step": 430
320
+ },
321
+ {
322
+ "epoch": 1.08,
323
+ "grad_norm": 13.575929641723633,
324
+ "learning_rate": 3.5643115942028985e-05,
325
+ "loss": 0.2622,
326
+ "step": 440
327
+ },
328
+ {
329
+ "epoch": 1.1,
330
+ "grad_norm": 18.06717300415039,
331
+ "learning_rate": 3.5190217391304346e-05,
332
+ "loss": 0.4565,
333
+ "step": 450
334
+ },
335
+ {
336
+ "epoch": 1.12,
337
+ "grad_norm": 8.216936111450195,
338
+ "learning_rate": 3.4737318840579714e-05,
339
+ "loss": 0.2695,
340
+ "step": 460
341
+ },
342
+ {
343
+ "epoch": 1.15,
344
+ "grad_norm": 9.777605056762695,
345
+ "learning_rate": 3.4284420289855076e-05,
346
+ "loss": 0.2196,
347
+ "step": 470
348
+ },
349
+ {
350
+ "epoch": 1.17,
351
+ "grad_norm": 14.722864151000977,
352
+ "learning_rate": 3.383152173913044e-05,
353
+ "loss": 0.3281,
354
+ "step": 480
355
+ },
356
+ {
357
+ "epoch": 1.2,
358
+ "grad_norm": 6.793803691864014,
359
+ "learning_rate": 3.33786231884058e-05,
360
+ "loss": 0.2514,
361
+ "step": 490
362
+ },
363
+ {
364
+ "epoch": 1.22,
365
+ "grad_norm": 12.138315200805664,
366
+ "learning_rate": 3.292572463768116e-05,
367
+ "loss": 0.2029,
368
+ "step": 500
369
+ },
370
+ {
371
+ "epoch": 1.25,
372
+ "grad_norm": 9.416603088378906,
373
+ "learning_rate": 3.247282608695653e-05,
374
+ "loss": 0.2635,
375
+ "step": 510
376
+ },
377
+ {
378
+ "epoch": 1.27,
379
+ "grad_norm": 9.601762771606445,
380
+ "learning_rate": 3.201992753623189e-05,
381
+ "loss": 0.1661,
382
+ "step": 520
383
+ },
384
+ {
385
+ "epoch": 1.3,
386
+ "grad_norm": 5.231688022613525,
387
+ "learning_rate": 3.156702898550725e-05,
388
+ "loss": 0.2205,
389
+ "step": 530
390
+ },
391
+ {
392
+ "epoch": 1.32,
393
+ "grad_norm": 6.3703532218933105,
394
+ "learning_rate": 3.111413043478261e-05,
395
+ "loss": 0.2531,
396
+ "step": 540
397
+ },
398
+ {
399
+ "epoch": 1.34,
400
+ "grad_norm": 14.850451469421387,
401
+ "learning_rate": 3.066123188405797e-05,
402
+ "loss": 0.1995,
403
+ "step": 550
404
+ },
405
+ {
406
+ "epoch": 1.37,
407
+ "grad_norm": 14.940292358398438,
408
+ "learning_rate": 3.0208333333333334e-05,
409
+ "loss": 0.2991,
410
+ "step": 560
411
+ },
412
+ {
413
+ "epoch": 1.39,
414
+ "grad_norm": 18.384620666503906,
415
+ "learning_rate": 2.9755434782608698e-05,
416
+ "loss": 0.1576,
417
+ "step": 570
418
+ },
419
+ {
420
+ "epoch": 1.42,
421
+ "grad_norm": 8.814579963684082,
422
+ "learning_rate": 2.930253623188406e-05,
423
+ "loss": 0.2447,
424
+ "step": 580
425
+ },
426
+ {
427
+ "epoch": 1.44,
428
+ "grad_norm": 9.285147666931152,
429
+ "learning_rate": 2.884963768115942e-05,
430
+ "loss": 0.1615,
431
+ "step": 590
432
+ },
433
+ {
434
+ "epoch": 1.47,
435
+ "grad_norm": 7.262125015258789,
436
+ "learning_rate": 2.8396739130434785e-05,
437
+ "loss": 0.1979,
438
+ "step": 600
439
+ },
440
+ {
441
+ "epoch": 1.49,
442
+ "grad_norm": 1.0271364450454712,
443
+ "learning_rate": 2.7943840579710146e-05,
444
+ "loss": 0.18,
445
+ "step": 610
446
+ },
447
+ {
448
+ "epoch": 1.52,
449
+ "grad_norm": 15.003844261169434,
450
+ "learning_rate": 2.749094202898551e-05,
451
+ "loss": 0.1752,
452
+ "step": 620
453
+ },
454
+ {
455
+ "epoch": 1.54,
456
+ "grad_norm": 25.77374267578125,
457
+ "learning_rate": 2.7038043478260872e-05,
458
+ "loss": 0.1326,
459
+ "step": 630
460
+ },
461
+ {
462
+ "epoch": 1.56,
463
+ "grad_norm": 33.20709228515625,
464
+ "learning_rate": 2.6585144927536234e-05,
465
+ "loss": 0.3093,
466
+ "step": 640
467
+ },
468
+ {
469
+ "epoch": 1.59,
470
+ "grad_norm": 11.408818244934082,
471
+ "learning_rate": 2.6132246376811598e-05,
472
+ "loss": 0.2182,
473
+ "step": 650
474
+ },
475
+ {
476
+ "epoch": 1.61,
477
+ "grad_norm": 2.7263596057891846,
478
+ "learning_rate": 2.567934782608696e-05,
479
+ "loss": 0.1294,
480
+ "step": 660
481
+ },
482
+ {
483
+ "epoch": 1.64,
484
+ "grad_norm": 3.28471302986145,
485
+ "learning_rate": 2.5226449275362317e-05,
486
+ "loss": 0.2335,
487
+ "step": 670
488
+ },
489
+ {
490
+ "epoch": 1.66,
491
+ "grad_norm": 9.495030403137207,
492
+ "learning_rate": 2.4773550724637682e-05,
493
+ "loss": 0.191,
494
+ "step": 680
495
+ },
496
+ {
497
+ "epoch": 1.69,
498
+ "grad_norm": 15.677921295166016,
499
+ "learning_rate": 2.4320652173913043e-05,
500
+ "loss": 0.201,
501
+ "step": 690
502
+ },
503
+ {
504
+ "epoch": 1.71,
505
+ "grad_norm": 10.669686317443848,
506
+ "learning_rate": 2.3867753623188408e-05,
507
+ "loss": 0.2334,
508
+ "step": 700
509
+ },
510
+ {
511
+ "epoch": 1.74,
512
+ "grad_norm": 22.738924026489258,
513
+ "learning_rate": 2.341485507246377e-05,
514
+ "loss": 0.2054,
515
+ "step": 710
516
+ },
517
+ {
518
+ "epoch": 1.76,
519
+ "grad_norm": 13.700279235839844,
520
+ "learning_rate": 2.296195652173913e-05,
521
+ "loss": 0.2358,
522
+ "step": 720
523
+ },
524
+ {
525
+ "epoch": 1.78,
526
+ "grad_norm": 8.795063018798828,
527
+ "learning_rate": 2.2509057971014495e-05,
528
+ "loss": 0.2259,
529
+ "step": 730
530
+ },
531
+ {
532
+ "epoch": 1.81,
533
+ "grad_norm": 13.257553100585938,
534
+ "learning_rate": 2.2056159420289856e-05,
535
+ "loss": 0.2174,
536
+ "step": 740
537
+ },
538
+ {
539
+ "epoch": 1.83,
540
+ "grad_norm": 16.352462768554688,
541
+ "learning_rate": 2.1603260869565217e-05,
542
+ "loss": 0.1939,
543
+ "step": 750
544
+ },
545
+ {
546
+ "epoch": 1.86,
547
+ "grad_norm": 9.414634704589844,
548
+ "learning_rate": 2.1150362318840582e-05,
549
+ "loss": 0.1856,
550
+ "step": 760
551
+ },
552
+ {
553
+ "epoch": 1.88,
554
+ "grad_norm": 12.655200958251953,
555
+ "learning_rate": 2.0697463768115943e-05,
556
+ "loss": 0.2237,
557
+ "step": 770
558
+ },
559
+ {
560
+ "epoch": 1.91,
561
+ "grad_norm": 8.855188369750977,
562
+ "learning_rate": 2.0244565217391308e-05,
563
+ "loss": 0.2063,
564
+ "step": 780
565
+ },
566
+ {
567
+ "epoch": 1.93,
568
+ "grad_norm": 0.29552894830703735,
569
+ "learning_rate": 1.9791666666666665e-05,
570
+ "loss": 0.1005,
571
+ "step": 790
572
+ },
573
+ {
574
+ "epoch": 1.96,
575
+ "grad_norm": 2.12908935546875,
576
+ "learning_rate": 1.933876811594203e-05,
577
+ "loss": 0.1538,
578
+ "step": 800
579
+ },
580
+ {
581
+ "epoch": 1.98,
582
+ "grad_norm": 8.586709022521973,
583
+ "learning_rate": 1.888586956521739e-05,
584
+ "loss": 0.1745,
585
+ "step": 810
586
+ },
587
+ {
588
+ "epoch": 2.0,
589
+ "eval_accuracy": 0.9570957095709571,
590
+ "eval_loss": 0.12920857965946198,
591
+ "eval_runtime": 6.4383,
592
+ "eval_samples_per_second": 141.187,
593
+ "eval_steps_per_second": 28.268,
594
+ "step": 818
595
+ },
596
+ {
597
+ "epoch": 2.0,
598
+ "grad_norm": 20.99432373046875,
599
+ "learning_rate": 1.8432971014492756e-05,
600
+ "loss": 0.2031,
601
+ "step": 820
602
+ },
603
+ {
604
+ "epoch": 2.03,
605
+ "grad_norm": 11.791101455688477,
606
+ "learning_rate": 1.7980072463768117e-05,
607
+ "loss": 0.1351,
608
+ "step": 830
609
+ },
610
+ {
611
+ "epoch": 2.05,
612
+ "grad_norm": 4.006465435028076,
613
+ "learning_rate": 1.752717391304348e-05,
614
+ "loss": 0.1164,
615
+ "step": 840
616
+ },
617
+ {
618
+ "epoch": 2.08,
619
+ "grad_norm": 5.286161422729492,
620
+ "learning_rate": 1.7074275362318843e-05,
621
+ "loss": 0.1593,
622
+ "step": 850
623
+ },
624
+ {
625
+ "epoch": 2.1,
626
+ "grad_norm": 5.119263648986816,
627
+ "learning_rate": 1.66213768115942e-05,
628
+ "loss": 0.0819,
629
+ "step": 860
630
+ },
631
+ {
632
+ "epoch": 2.13,
633
+ "grad_norm": 7.2655253410339355,
634
+ "learning_rate": 1.6168478260869565e-05,
635
+ "loss": 0.0936,
636
+ "step": 870
637
+ },
638
+ {
639
+ "epoch": 2.15,
640
+ "grad_norm": 21.422300338745117,
641
+ "learning_rate": 1.571557971014493e-05,
642
+ "loss": 0.1586,
643
+ "step": 880
644
+ },
645
+ {
646
+ "epoch": 2.18,
647
+ "grad_norm": 20.841064453125,
648
+ "learning_rate": 1.526268115942029e-05,
649
+ "loss": 0.2057,
650
+ "step": 890
651
+ },
652
+ {
653
+ "epoch": 2.2,
654
+ "grad_norm": 5.252929210662842,
655
+ "learning_rate": 1.4809782608695653e-05,
656
+ "loss": 0.1781,
657
+ "step": 900
658
+ },
659
+ {
660
+ "epoch": 2.22,
661
+ "grad_norm": 23.310047149658203,
662
+ "learning_rate": 1.4356884057971015e-05,
663
+ "loss": 0.1749,
664
+ "step": 910
665
+ },
666
+ {
667
+ "epoch": 2.25,
668
+ "grad_norm": 2.4795796871185303,
669
+ "learning_rate": 1.3903985507246378e-05,
670
+ "loss": 0.2178,
671
+ "step": 920
672
+ },
673
+ {
674
+ "epoch": 2.27,
675
+ "grad_norm": 8.616735458374023,
676
+ "learning_rate": 1.3451086956521738e-05,
677
+ "loss": 0.2184,
678
+ "step": 930
679
+ },
680
+ {
681
+ "epoch": 2.3,
682
+ "grad_norm": 11.104738235473633,
683
+ "learning_rate": 1.2998188405797101e-05,
684
+ "loss": 0.088,
685
+ "step": 940
686
+ },
687
+ {
688
+ "epoch": 2.32,
689
+ "grad_norm": 11.91581916809082,
690
+ "learning_rate": 1.2545289855072464e-05,
691
+ "loss": 0.2445,
692
+ "step": 950
693
+ },
694
+ {
695
+ "epoch": 2.35,
696
+ "grad_norm": 1.7576195001602173,
697
+ "learning_rate": 1.2092391304347827e-05,
698
+ "loss": 0.1298,
699
+ "step": 960
700
+ },
701
+ {
702
+ "epoch": 2.37,
703
+ "grad_norm": 9.120392799377441,
704
+ "learning_rate": 1.163949275362319e-05,
705
+ "loss": 0.1935,
706
+ "step": 970
707
+ },
708
+ {
709
+ "epoch": 2.4,
710
+ "grad_norm": 13.665518760681152,
711
+ "learning_rate": 1.1186594202898551e-05,
712
+ "loss": 0.1689,
713
+ "step": 980
714
+ },
715
+ {
716
+ "epoch": 2.42,
717
+ "grad_norm": 19.75223731994629,
718
+ "learning_rate": 1.0733695652173914e-05,
719
+ "loss": 0.142,
720
+ "step": 990
721
+ },
722
+ {
723
+ "epoch": 2.44,
724
+ "grad_norm": 8.352010726928711,
725
+ "learning_rate": 1.0280797101449275e-05,
726
+ "loss": 0.2239,
727
+ "step": 1000
728
+ },
729
+ {
730
+ "epoch": 2.47,
731
+ "grad_norm": 21.5345516204834,
732
+ "learning_rate": 9.827898550724638e-06,
733
+ "loss": 0.2238,
734
+ "step": 1010
735
+ },
736
+ {
737
+ "epoch": 2.49,
738
+ "grad_norm": 8.045764923095703,
739
+ "learning_rate": 9.375000000000001e-06,
740
+ "loss": 0.1246,
741
+ "step": 1020
742
+ },
743
+ {
744
+ "epoch": 2.52,
745
+ "grad_norm": 8.87646770477295,
746
+ "learning_rate": 8.922101449275362e-06,
747
+ "loss": 0.0863,
748
+ "step": 1030
749
+ },
750
+ {
751
+ "epoch": 2.54,
752
+ "grad_norm": 11.654149055480957,
753
+ "learning_rate": 8.469202898550725e-06,
754
+ "loss": 0.0846,
755
+ "step": 1040
756
+ },
757
+ {
758
+ "epoch": 2.57,
759
+ "grad_norm": 0.8430119156837463,
760
+ "learning_rate": 8.016304347826086e-06,
761
+ "loss": 0.1514,
762
+ "step": 1050
763
+ },
764
+ {
765
+ "epoch": 2.59,
766
+ "grad_norm": 1.686838984489441,
767
+ "learning_rate": 7.56340579710145e-06,
768
+ "loss": 0.0937,
769
+ "step": 1060
770
+ },
771
+ {
772
+ "epoch": 2.62,
773
+ "grad_norm": 31.7119140625,
774
+ "learning_rate": 7.110507246376811e-06,
775
+ "loss": 0.1698,
776
+ "step": 1070
777
+ },
778
+ {
779
+ "epoch": 2.64,
780
+ "grad_norm": 12.519082069396973,
781
+ "learning_rate": 6.657608695652175e-06,
782
+ "loss": 0.1635,
783
+ "step": 1080
784
+ },
785
+ {
786
+ "epoch": 2.67,
787
+ "grad_norm": 0.5338079333305359,
788
+ "learning_rate": 6.204710144927536e-06,
789
+ "loss": 0.0695,
790
+ "step": 1090
791
+ },
792
+ {
793
+ "epoch": 2.69,
794
+ "grad_norm": 22.285619735717773,
795
+ "learning_rate": 5.751811594202898e-06,
796
+ "loss": 0.1957,
797
+ "step": 1100
798
+ },
799
+ {
800
+ "epoch": 2.71,
801
+ "grad_norm": 9.996444702148438,
802
+ "learning_rate": 5.298913043478261e-06,
803
+ "loss": 0.2182,
804
+ "step": 1110
805
+ },
806
+ {
807
+ "epoch": 2.74,
808
+ "grad_norm": 5.337853908538818,
809
+ "learning_rate": 4.846014492753623e-06,
810
+ "loss": 0.089,
811
+ "step": 1120
812
+ },
813
+ {
814
+ "epoch": 2.76,
815
+ "grad_norm": 6.16534948348999,
816
+ "learning_rate": 4.393115942028985e-06,
817
+ "loss": 0.1833,
818
+ "step": 1130
819
+ },
820
+ {
821
+ "epoch": 2.79,
822
+ "grad_norm": 0.6340013742446899,
823
+ "learning_rate": 3.940217391304348e-06,
824
+ "loss": 0.1684,
825
+ "step": 1140
826
+ },
827
+ {
828
+ "epoch": 2.81,
829
+ "grad_norm": 17.78191375732422,
830
+ "learning_rate": 3.4873188405797104e-06,
831
+ "loss": 0.211,
832
+ "step": 1150
833
+ },
834
+ {
835
+ "epoch": 2.84,
836
+ "grad_norm": 6.65162992477417,
837
+ "learning_rate": 3.0344202898550725e-06,
838
+ "loss": 0.1569,
839
+ "step": 1160
840
+ },
841
+ {
842
+ "epoch": 2.86,
843
+ "grad_norm": 14.574379920959473,
844
+ "learning_rate": 2.581521739130435e-06,
845
+ "loss": 0.1173,
846
+ "step": 1170
847
+ },
848
+ {
849
+ "epoch": 2.89,
850
+ "grad_norm": 6.665879249572754,
851
+ "learning_rate": 2.1286231884057975e-06,
852
+ "loss": 0.1795,
853
+ "step": 1180
854
+ },
855
+ {
856
+ "epoch": 2.91,
857
+ "grad_norm": 2.035705327987671,
858
+ "learning_rate": 1.6757246376811596e-06,
859
+ "loss": 0.201,
860
+ "step": 1190
861
+ },
862
+ {
863
+ "epoch": 2.93,
864
+ "grad_norm": 5.481184482574463,
865
+ "learning_rate": 1.2228260869565218e-06,
866
+ "loss": 0.127,
867
+ "step": 1200
868
+ },
869
+ {
870
+ "epoch": 2.96,
871
+ "grad_norm": 19.509849548339844,
872
+ "learning_rate": 7.699275362318841e-07,
873
+ "loss": 0.1226,
874
+ "step": 1210
875
+ },
876
+ {
877
+ "epoch": 2.98,
878
+ "grad_norm": 9.846253395080566,
879
+ "learning_rate": 3.170289855072464e-07,
880
+ "loss": 0.1562,
881
+ "step": 1220
882
+ },
883
+ {
884
+ "epoch": 3.0,
885
+ "eval_accuracy": 0.9592959295929593,
886
+ "eval_loss": 0.11152195930480957,
887
+ "eval_runtime": 6.4385,
888
+ "eval_samples_per_second": 141.182,
889
+ "eval_steps_per_second": 28.267,
890
+ "step": 1227
891
+ },
892
+ {
893
+ "epoch": 3.0,
894
+ "step": 1227,
895
+ "total_flos": 6.096847334287933e+17,
896
+ "train_loss": 0.2716238140671255,
897
+ "train_runtime": 385.934,
898
+ "train_samples_per_second": 63.555,
899
+ "train_steps_per_second": 3.179
900
+ }
901
+ ],
902
+ "logging_steps": 10,
903
+ "max_steps": 1227,
904
+ "num_input_tokens_seen": 0,
905
+ "num_train_epochs": 3,
906
+ "save_steps": 500,
907
+ "total_flos": 6.096847334287933e+17,
908
+ "train_batch_size": 5,
909
+ "trial_name": null,
910
+ "trial_params": null
911
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfedc8f5ed47ec359ef9e00ae52792e6c6472082ab69f9bf790bd0429c2fee18
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afda2eb9d4d2d007a3282d1dffa34b80db794ffda2c85b7e64b7d0b9abe623cc
3
  size 4984