emilykang commited on
Commit
1679ae1
1 Parent(s): 9e078fc

Training in progress, epoch 1

Browse files
adapter_config.json CHANGED
@@ -20,10 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
  "v_proj",
 
25
  "q_proj",
26
- "o_proj"
 
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "v_proj",
24
+ "fc1",
25
  "q_proj",
26
+ "k_proj",
27
+ "fc2",
28
+ "dense"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b9b993b0ee3752155962ca4efbf07cd1ce83fed06e9a3544709007de4b04eb3
3
- size 15754264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbee633b10670664767a216f2288e30da987541ca15433314557f0c673dc8742
3
+ size 47236352
trainer_state.json ADDED
@@ -0,0 +1,408 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 540,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.18518518518518517,
13
+ "grad_norm": 9.9296875,
14
+ "learning_rate": 0.00019983081582712685,
15
+ "loss": 0.8329,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.37037037037037035,
20
+ "grad_norm": 15.890625,
21
+ "learning_rate": 0.00019932383577419432,
22
+ "loss": 0.8473,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.5555555555555556,
27
+ "grad_norm": 15.71875,
28
+ "learning_rate": 0.00019848077530122083,
29
+ "loss": 0.8181,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.7407407407407407,
34
+ "grad_norm": 17.453125,
35
+ "learning_rate": 0.00019730448705798239,
36
+ "loss": 0.8512,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.9259259259259259,
41
+ "grad_norm": 18.234375,
42
+ "learning_rate": 0.0001957989512315489,
43
+ "loss": 0.8302,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 1.1111111111111112,
48
+ "grad_norm": 25.78125,
49
+ "learning_rate": 0.00019396926207859084,
50
+ "loss": 0.8281,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.2962962962962963,
55
+ "grad_norm": 24.984375,
56
+ "learning_rate": 0.00019182161068802741,
57
+ "loss": 0.8343,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.4814814814814814,
62
+ "grad_norm": 24.296875,
63
+ "learning_rate": 0.00018936326403234125,
64
+ "loss": 0.7968,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.6666666666666665,
69
+ "grad_norm": 16.3125,
70
+ "learning_rate": 0.00018660254037844388,
71
+ "loss": 0.7891,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.8518518518518519,
76
+ "grad_norm": 13.578125,
77
+ "learning_rate": 0.00018354878114129367,
78
+ "loss": 0.7864,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 2.037037037037037,
83
+ "grad_norm": 14.25,
84
+ "learning_rate": 0.0001802123192755044,
85
+ "loss": 0.7815,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 2.2222222222222223,
90
+ "grad_norm": 14.7734375,
91
+ "learning_rate": 0.0001766044443118978,
92
+ "loss": 0.7697,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 2.4074074074074074,
97
+ "grad_norm": 11.3125,
98
+ "learning_rate": 0.00017273736415730488,
99
+ "loss": 0.7728,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 2.5925925925925926,
104
+ "grad_norm": 11.203125,
105
+ "learning_rate": 0.0001686241637868734,
106
+ "loss": 0.7413,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 2.7777777777777777,
111
+ "grad_norm": 14.8125,
112
+ "learning_rate": 0.00016427876096865394,
113
+ "loss": 0.749,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 2.962962962962963,
118
+ "grad_norm": 11.5,
119
+ "learning_rate": 0.00015971585917027862,
120
+ "loss": 0.7216,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 3.148148148148148,
125
+ "grad_norm": 13.109375,
126
+ "learning_rate": 0.0001549508978070806,
127
+ "loss": 0.7739,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 3.3333333333333335,
132
+ "grad_norm": 13.453125,
133
+ "learning_rate": 0.00015000000000000001,
134
+ "loss": 0.733,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 3.5185185185185186,
139
+ "grad_norm": 17.84375,
140
+ "learning_rate": 0.00014487991802004623,
141
+ "loss": 0.7267,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 3.7037037037037037,
146
+ "grad_norm": 16.765625,
147
+ "learning_rate": 0.0001396079766039157,
148
+ "loss": 0.7191,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 3.888888888888889,
153
+ "grad_norm": 17.515625,
154
+ "learning_rate": 0.00013420201433256689,
155
+ "loss": 0.7207,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 4.074074074074074,
160
+ "grad_norm": 21.578125,
161
+ "learning_rate": 0.00012868032327110904,
162
+ "loss": 0.7718,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 4.2592592592592595,
167
+ "grad_norm": 15.7890625,
168
+ "learning_rate": 0.00012306158707424403,
169
+ "loss": 0.7487,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 4.444444444444445,
174
+ "grad_norm": 15.9140625,
175
+ "learning_rate": 0.00011736481776669306,
176
+ "loss": 0.7416,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 4.62962962962963,
181
+ "grad_norm": 19.1875,
182
+ "learning_rate": 0.00011160929141252303,
183
+ "loss": 0.7517,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 4.814814814814815,
188
+ "grad_norm": 20.03125,
189
+ "learning_rate": 0.00010581448289104758,
190
+ "loss": 0.7521,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 5.0,
195
+ "grad_norm": 20.421875,
196
+ "learning_rate": 0.0001,
197
+ "loss": 0.753,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 5.185185185185185,
202
+ "grad_norm": 21.109375,
203
+ "learning_rate": 9.418551710895243e-05,
204
+ "loss": 0.7609,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 5.37037037037037,
209
+ "grad_norm": 17.53125,
210
+ "learning_rate": 8.839070858747697e-05,
211
+ "loss": 0.7744,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 5.555555555555555,
216
+ "grad_norm": 16.90625,
217
+ "learning_rate": 8.263518223330697e-05,
218
+ "loss": 0.7907,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 5.7407407407407405,
223
+ "grad_norm": 20.46875,
224
+ "learning_rate": 7.693841292575598e-05,
225
+ "loss": 0.8155,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 5.925925925925926,
230
+ "grad_norm": 19.984375,
231
+ "learning_rate": 7.131967672889101e-05,
232
+ "loss": 0.7919,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 6.111111111111111,
237
+ "grad_norm": 20.0625,
238
+ "learning_rate": 6.579798566743314e-05,
239
+ "loss": 0.7648,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 6.296296296296296,
244
+ "grad_norm": 18.140625,
245
+ "learning_rate": 6.039202339608432e-05,
246
+ "loss": 0.7645,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 6.481481481481482,
251
+ "grad_norm": 17.40625,
252
+ "learning_rate": 5.5120081979953785e-05,
253
+ "loss": 0.7765,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 6.666666666666667,
258
+ "grad_norm": 18.484375,
259
+ "learning_rate": 5.000000000000002e-05,
260
+ "loss": 0.8114,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 6.851851851851852,
265
+ "grad_norm": 21.609375,
266
+ "learning_rate": 4.50491021929194e-05,
267
+ "loss": 0.7967,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 7.037037037037037,
272
+ "grad_norm": 26.5625,
273
+ "learning_rate": 4.028414082972141e-05,
274
+ "loss": 0.8445,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 7.222222222222222,
279
+ "grad_norm": 21.703125,
280
+ "learning_rate": 3.5721239031346066e-05,
281
+ "loss": 0.8495,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 7.407407407407407,
286
+ "grad_norm": 20.984375,
287
+ "learning_rate": 3.137583621312665e-05,
288
+ "loss": 0.8274,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 7.592592592592593,
293
+ "grad_norm": 19.296875,
294
+ "learning_rate": 2.7262635842695127e-05,
295
+ "loss": 0.8176,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 7.777777777777778,
300
+ "grad_norm": 21.984375,
301
+ "learning_rate": 2.339555568810221e-05,
302
+ "loss": 0.8328,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 7.962962962962963,
307
+ "grad_norm": 20.515625,
308
+ "learning_rate": 1.9787680724495617e-05,
309
+ "loss": 0.8183,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 8.148148148148149,
314
+ "grad_norm": 25.671875,
315
+ "learning_rate": 1.6451218858706374e-05,
316
+ "loss": 0.7987,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 8.333333333333334,
321
+ "grad_norm": 20.28125,
322
+ "learning_rate": 1.339745962155613e-05,
323
+ "loss": 0.7994,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 8.518518518518519,
328
+ "grad_norm": 22.828125,
329
+ "learning_rate": 1.0636735967658784e-05,
330
+ "loss": 0.7928,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 8.703703703703704,
335
+ "grad_norm": 22.375,
336
+ "learning_rate": 8.178389311972612e-06,
337
+ "loss": 0.7978,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 8.88888888888889,
342
+ "grad_norm": 22.171875,
343
+ "learning_rate": 6.030737921409169e-06,
344
+ "loss": 0.8077,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 9.074074074074074,
349
+ "grad_norm": 21.28125,
350
+ "learning_rate": 4.20104876845111e-06,
351
+ "loss": 0.8003,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 9.25925925925926,
356
+ "grad_norm": 18.765625,
357
+ "learning_rate": 2.6955129420176196e-06,
358
+ "loss": 0.8012,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 9.444444444444445,
363
+ "grad_norm": 19.609375,
364
+ "learning_rate": 1.5192246987791981e-06,
365
+ "loss": 0.7831,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 9.62962962962963,
370
+ "grad_norm": 17.96875,
371
+ "learning_rate": 6.761642258056978e-07,
372
+ "loss": 0.783,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 9.814814814814815,
377
+ "grad_norm": 18.890625,
378
+ "learning_rate": 1.6918417287318245e-07,
379
+ "loss": 0.8059,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 10.0,
384
+ "grad_norm": 28.9375,
385
+ "learning_rate": 0.0,
386
+ "loss": 0.7967,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 10.0,
391
+ "step": 540,
392
+ "total_flos": 3.52542013784064e+16,
393
+ "train_loss": 0.7879019375200624,
394
+ "train_runtime": 461.2272,
395
+ "train_samples_per_second": 4.683,
396
+ "train_steps_per_second": 1.171
397
+ }
398
+ ],
399
+ "logging_steps": 10,
400
+ "max_steps": 540,
401
+ "num_input_tokens_seen": 0,
402
+ "num_train_epochs": 10,
403
+ "save_steps": 500,
404
+ "total_flos": 3.52542013784064e+16,
405
+ "train_batch_size": 1,
406
+ "trial_name": null,
407
+ "trial_params": null
408
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b51eec79b6b6e26ebdc364dc8be81036dae7469d70ea5bb9ff50f3f29409dfb3
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05d57bfba876cd326ab77cb5d7ba13b00b0682695ddbd577aa464d32859510d
3
  size 4984