reaperdoesntknow commited on
Commit
a27533c
·
verified ·
1 Parent(s): d52efc7

Upload 4 files

Browse files
events.out.tfevents.1762685027.0cffba888970 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd62417c97776e029f3a58542008f89ba0e8b2f05b35ce1c22f814986e05b6a
3
+ size 12931
events.out.tfevents.1762685267.0cffba888970 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92817600ef1b85ca036bb45c866c362b9cca7c6ca5419a66543e1249e86eb701
3
+ size 18932
events.out.tfevents.1762685613.0cffba888970 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a4473231952872cba14281432ea7af3abdc79e15aa0d75c4347ba086af3e34
3
+ size 18928
trainer_state (1).json ADDED
@@ -0,0 +1,354 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.019536019536019536,
6
+ "eval_steps": 500,
7
+ "global_step": 32,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 4.13485050201416,
14
+ "epoch": 0.0006105006105006105,
15
+ "grad_norm": 6.779195785522461,
16
+ "learning_rate": 0.0003,
17
+ "loss": 6.2653,
18
+ "mean_token_accuracy": 0.16929133236408234,
19
+ "num_tokens": 1024.0,
20
+ "step": 1
21
+ },
22
+ {
23
+ "entropy": 5.793717861175537,
24
+ "epoch": 0.001221001221001221,
25
+ "grad_norm": 16.547292709350586,
26
+ "learning_rate": 0.00029927770900082954,
27
+ "loss": 7.4425,
28
+ "mean_token_accuracy": 0.07185039669275284,
29
+ "num_tokens": 2048.0,
30
+ "step": 2
31
+ },
32
+ {
33
+ "entropy": 5.173164367675781,
34
+ "epoch": 0.0018315018315018315,
35
+ "grad_norm": 8.281397819519043,
36
+ "learning_rate": 0.00029711779206048454,
37
+ "loss": 7.0805,
38
+ "mean_token_accuracy": 0.04595404490828514,
39
+ "num_tokens": 3072.0,
40
+ "step": 3
41
+ },
42
+ {
43
+ "entropy": 5.790804862976074,
44
+ "epoch": 0.002442002442002442,
45
+ "grad_norm": 7.232938289642334,
46
+ "learning_rate": 0.0002935410503598313,
47
+ "loss": 5.9113,
48
+ "mean_token_accuracy": 0.09690721333026886,
49
+ "num_tokens": 4096.0,
50
+ "step": 4
51
+ },
52
+ {
53
+ "entropy": 5.514730453491211,
54
+ "epoch": 0.0030525030525030525,
55
+ "grad_norm": 5.750503063201904,
56
+ "learning_rate": 0.000288581929876693,
57
+ "loss": 5.9462,
58
+ "mean_token_accuracy": 0.10728346556425095,
59
+ "num_tokens": 5120.0,
60
+ "step": 5
61
+ },
62
+ {
63
+ "entropy": 4.5655198097229,
64
+ "epoch": 0.003663003663003663,
65
+ "grad_norm": 9.491901397705078,
66
+ "learning_rate": 0.0002822881896522532,
67
+ "loss": 5.7517,
68
+ "mean_token_accuracy": 0.18307086825370789,
69
+ "num_tokens": 6144.0,
70
+ "step": 6
71
+ },
72
+ {
73
+ "entropy": 4.92832088470459,
74
+ "epoch": 0.004273504273504274,
75
+ "grad_norm": 4.776255130767822,
76
+ "learning_rate": 0.0002747204418453818,
77
+ "loss": 5.6682,
78
+ "mean_token_accuracy": 0.17814961075782776,
79
+ "num_tokens": 7168.0,
80
+ "step": 7
81
+ },
82
+ {
83
+ "entropy": 6.124536991119385,
84
+ "epoch": 0.004884004884004884,
85
+ "grad_norm": 11.058452606201172,
86
+ "learning_rate": 0.0002659515680044105,
87
+ "loss": 4.9755,
88
+ "mean_token_accuracy": 0.18397626280784607,
89
+ "num_tokens": 8192.0,
90
+ "step": 8
91
+ },
92
+ {
93
+ "entropy": 4.757119655609131,
94
+ "epoch": 0.005494505494505495,
95
+ "grad_norm": 30.98914909362793,
96
+ "learning_rate": 0.00025606601717798207,
97
+ "loss": 5.5204,
98
+ "mean_token_accuracy": 0.1530286967754364,
99
+ "num_tokens": 9216.0,
100
+ "step": 9
101
+ },
102
+ {
103
+ "entropy": 3.9111785888671875,
104
+ "epoch": 0.006105006105006105,
105
+ "grad_norm": 6.036701202392578,
106
+ "learning_rate": 0.0002451589926245468,
107
+ "loss": 5.7534,
108
+ "mean_token_accuracy": 0.15548455715179443,
109
+ "num_tokens": 10240.0,
110
+ "step": 10
111
+ },
112
+ {
113
+ "entropy": 5.500742435455322,
114
+ "epoch": 0.006715506715506716,
115
+ "grad_norm": 3.4777474403381348,
116
+ "learning_rate": 0.0002333355349529403,
117
+ "loss": 5.7081,
118
+ "mean_token_accuracy": 0.15589743852615356,
119
+ "num_tokens": 11264.0,
120
+ "step": 11
121
+ },
122
+ {
123
+ "entropy": 5.70326566696167,
124
+ "epoch": 0.007326007326007326,
125
+ "grad_norm": 3.508657217025757,
126
+ "learning_rate": 0.00022070951052389966,
127
+ "loss": 5.0422,
128
+ "mean_token_accuracy": 0.18095238506793976,
129
+ "num_tokens": 12288.0,
130
+ "step": 12
131
+ },
132
+ {
133
+ "entropy": 4.923552513122559,
134
+ "epoch": 0.007936507936507936,
135
+ "grad_norm": 3.8143184185028076,
136
+ "learning_rate": 0.00020740251485476345,
137
+ "loss": 5.1931,
138
+ "mean_token_accuracy": 0.169199600815773,
139
+ "num_tokens": 13312.0,
140
+ "step": 13
141
+ },
142
+ {
143
+ "entropy": 4.681103706359863,
144
+ "epoch": 0.008547008547008548,
145
+ "grad_norm": 3.4933412075042725,
146
+ "learning_rate": 0.0001935427015881693,
147
+ "loss": 5.573,
148
+ "mean_token_accuracy": 0.17606329917907715,
149
+ "num_tokens": 14336.0,
150
+ "step": 14
151
+ },
152
+ {
153
+ "entropy": 5.161688327789307,
154
+ "epoch": 0.009157509157509158,
155
+ "grad_norm": 6.412088394165039,
156
+ "learning_rate": 0.00017926354830241924,
157
+ "loss": 5.2034,
158
+ "mean_token_accuracy": 0.20263424515724182,
159
+ "num_tokens": 15360.0,
160
+ "step": 15
161
+ },
162
+ {
163
+ "entropy": 5.262051582336426,
164
+ "epoch": 0.009768009768009768,
165
+ "grad_norm": 3.836217164993286,
166
+ "learning_rate": 0.0001647025710494341,
167
+ "loss": 4.6478,
168
+ "mean_token_accuracy": 0.22834645211696625,
169
+ "num_tokens": 16384.0,
170
+ "step": 16
171
+ },
172
+ {
173
+ "entropy": 5.14174747467041,
174
+ "epoch": 0.010378510378510378,
175
+ "grad_norm": 6.356348037719727,
176
+ "learning_rate": 0.00015,
177
+ "loss": 5.7193,
178
+ "mean_token_accuracy": 0.174869105219841,
179
+ "num_tokens": 17408.0,
180
+ "step": 17
181
+ },
182
+ {
183
+ "entropy": 4.554754734039307,
184
+ "epoch": 0.01098901098901099,
185
+ "grad_norm": 3.5281262397766113,
186
+ "learning_rate": 0.0001352974289505659,
187
+ "loss": 4.8491,
188
+ "mean_token_accuracy": 0.22342519462108612,
189
+ "num_tokens": 18432.0,
190
+ "step": 18
191
+ },
192
+ {
193
+ "entropy": 5.017117500305176,
194
+ "epoch": 0.0115995115995116,
195
+ "grad_norm": 3.1419517993927,
196
+ "learning_rate": 0.00012073645169758076,
197
+ "loss": 5.3589,
198
+ "mean_token_accuracy": 0.20088790357112885,
199
+ "num_tokens": 19456.0,
200
+ "step": 19
201
+ },
202
+ {
203
+ "entropy": 4.860474586486816,
204
+ "epoch": 0.01221001221001221,
205
+ "grad_norm": 3.614912986755371,
206
+ "learning_rate": 0.00010645729841183066,
207
+ "loss": 5.1,
208
+ "mean_token_accuracy": 0.19789473712444305,
209
+ "num_tokens": 20480.0,
210
+ "step": 20
211
+ },
212
+ {
213
+ "entropy": 5.405769348144531,
214
+ "epoch": 0.01282051282051282,
215
+ "grad_norm": 17.46617317199707,
216
+ "learning_rate": 9.259748514523653e-05,
217
+ "loss": 5.4736,
218
+ "mean_token_accuracy": 0.17610710859298706,
219
+ "num_tokens": 21504.0,
220
+ "step": 21
221
+ },
222
+ {
223
+ "entropy": 5.062948703765869,
224
+ "epoch": 0.013431013431013432,
225
+ "grad_norm": 3.2527050971984863,
226
+ "learning_rate": 7.929048947610034e-05,
227
+ "loss": 4.5604,
228
+ "mean_token_accuracy": 0.21810699999332428,
229
+ "num_tokens": 22528.0,
230
+ "step": 22
231
+ },
232
+ {
233
+ "entropy": 4.796494483947754,
234
+ "epoch": 0.014041514041514042,
235
+ "grad_norm": 3.152696132659912,
236
+ "learning_rate": 6.66644650470597e-05,
237
+ "loss": 4.1272,
238
+ "mean_token_accuracy": 0.28236493468284607,
239
+ "num_tokens": 23552.0,
240
+ "step": 23
241
+ },
242
+ {
243
+ "entropy": 4.756124496459961,
244
+ "epoch": 0.014652014652014652,
245
+ "grad_norm": 2.406891345977783,
246
+ "learning_rate": 5.4841007375453186e-05,
247
+ "loss": 4.5433,
248
+ "mean_token_accuracy": 0.24015748500823975,
249
+ "num_tokens": 24576.0,
250
+ "step": 24
251
+ },
252
+ {
253
+ "entropy": 4.696354389190674,
254
+ "epoch": 0.015262515262515262,
255
+ "grad_norm": 3.4845199584960938,
256
+ "learning_rate": 4.3933982822017876e-05,
257
+ "loss": 4.6104,
258
+ "mean_token_accuracy": 0.24015748500823975,
259
+ "num_tokens": 25600.0,
260
+ "step": 25
261
+ },
262
+ {
263
+ "entropy": 4.748116493225098,
264
+ "epoch": 0.015873015873015872,
265
+ "grad_norm": 63.001136779785156,
266
+ "learning_rate": 3.404843199558945e-05,
267
+ "loss": 4.5619,
268
+ "mean_token_accuracy": 0.24924011528491974,
269
+ "num_tokens": 26624.0,
270
+ "step": 26
271
+ },
272
+ {
273
+ "entropy": 4.614930152893066,
274
+ "epoch": 0.016483516483516484,
275
+ "grad_norm": 2.197350025177002,
276
+ "learning_rate": 2.5279558154618197e-05,
277
+ "loss": 4.7666,
278
+ "mean_token_accuracy": 0.24020101130008698,
279
+ "num_tokens": 27648.0,
280
+ "step": 27
281
+ },
282
+ {
283
+ "entropy": 4.691383361816406,
284
+ "epoch": 0.017094017094017096,
285
+ "grad_norm": 2.5826752185821533,
286
+ "learning_rate": 1.7711810347746757e-05,
287
+ "loss": 4.6907,
288
+ "mean_token_accuracy": 0.2278876155614853,
289
+ "num_tokens": 28672.0,
290
+ "step": 28
291
+ },
292
+ {
293
+ "entropy": 4.772076606750488,
294
+ "epoch": 0.017704517704517704,
295
+ "grad_norm": 3.7122533321380615,
296
+ "learning_rate": 1.1418070123306989e-05,
297
+ "loss": 4.6573,
298
+ "mean_token_accuracy": 0.20523138344287872,
299
+ "num_tokens": 29696.0,
300
+ "step": 29
301
+ },
302
+ {
303
+ "entropy": 4.471816062927246,
304
+ "epoch": 0.018315018315018316,
305
+ "grad_norm": 2.352668285369873,
306
+ "learning_rate": 6.458949640168675e-06,
307
+ "loss": 4.3323,
308
+ "mean_token_accuracy": 0.2381889820098877,
309
+ "num_tokens": 30720.0,
310
+ "step": 30
311
+ },
312
+ {
313
+ "entropy": 4.810123443603516,
314
+ "epoch": 0.018925518925518924,
315
+ "grad_norm": 2.075646162033081,
316
+ "learning_rate": 2.882207939515435e-06,
317
+ "loss": 4.9162,
318
+ "mean_token_accuracy": 0.2311507910490036,
319
+ "num_tokens": 31744.0,
320
+ "step": 31
321
+ },
322
+ {
323
+ "entropy": 4.847671031951904,
324
+ "epoch": 0.019536019536019536,
325
+ "grad_norm": 2.874021291732788,
326
+ "learning_rate": 7.222909991704773e-07,
327
+ "loss": 4.9275,
328
+ "mean_token_accuracy": 0.20472441613674164,
329
+ "num_tokens": 32768.0,
330
+ "step": 32
331
+ }
332
+ ],
333
+ "logging_steps": 1,
334
+ "max_steps": 32,
335
+ "num_input_tokens_seen": 0,
336
+ "num_train_epochs": 1,
337
+ "save_steps": 16,
338
+ "stateful_callbacks": {
339
+ "TrainerControl": {
340
+ "args": {
341
+ "should_epoch_stop": false,
342
+ "should_evaluate": false,
343
+ "should_log": false,
344
+ "should_save": true,
345
+ "should_training_stop": true
346
+ },
347
+ "attributes": {}
348
+ }
349
+ },
350
+ "total_flos": 137211949350912.0,
351
+ "train_batch_size": 8,
352
+ "trial_name": null,
353
+ "trial_params": null
354
+ }