terry69 commited on
Commit
5cebddb
1 Parent(s): c6aadea

Model save

Browse files
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ base_model: meta-llama/Meta-Llama-3-8B
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: llama5pEnt
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # llama5pEnt
17
+
18
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.0853
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0002
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 3
45
+ - gradient_accumulation_steps: 8
46
+ - total_train_batch_size: 192
47
+ - total_eval_batch_size: 12
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 1
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:----:|:---------------:|
57
+ | 0.8639 | 0.9993 | 541 | 1.0853 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.41.1
63
+ - Pytorch 2.3.0+cu121
64
+ - Datasets 2.19.1
65
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9993073193257908,
3
+ "total_flos": 2.705944628841939e+18,
4
+ "train_loss": 0.860630649956229,
5
+ "train_runtime": 42250.2981,
6
+ "train_samples": 103932,
7
+ "train_samples_per_second": 2.46,
8
+ "train_steps_per_second": 0.013
9
+ }
runs/May31_06-00-44_COE-CS-sv003/events.out.tfevents.1717135532.COE-CS-sv003.3638172.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e16b3492e81d744af6d20d0e25059f2f1557d96b2e588e09f4a15592dd47f8a4
3
- size 27322
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5afea1fcc31932252827bf3303e1be07cf926e6f549843fb63d2318f9ad229
3
+ size 28580
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9993073193257908,
3
+ "total_flos": 2.705944628841939e+18,
4
+ "train_loss": 0.860630649956229,
5
+ "train_runtime": 42250.2981,
6
+ "train_samples": 103932,
7
+ "train_samples_per_second": 2.46,
8
+ "train_steps_per_second": 0.013
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,813 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9993073193257908,
5
+ "eval_steps": 500,
6
+ "global_step": 541,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0018471484645578389,
13
+ "grad_norm": 0.2646295130252838,
14
+ "learning_rate": 3.636363636363636e-06,
15
+ "loss": 0.9117,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.009235742322789195,
20
+ "grad_norm": 0.29179853200912476,
21
+ "learning_rate": 1.8181818181818182e-05,
22
+ "loss": 0.9579,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.01847148464557839,
27
+ "grad_norm": 0.30512726306915283,
28
+ "learning_rate": 3.6363636363636364e-05,
29
+ "loss": 0.9489,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.027707226968367582,
34
+ "grad_norm": 0.08514489233493805,
35
+ "learning_rate": 5.4545454545454546e-05,
36
+ "loss": 0.9274,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.03694296929115678,
41
+ "grad_norm": 0.07719692587852478,
42
+ "learning_rate": 7.272727272727273e-05,
43
+ "loss": 0.9257,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.04617871161394597,
48
+ "grad_norm": 0.08602738380432129,
49
+ "learning_rate": 9.090909090909092e-05,
50
+ "loss": 0.9255,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.055414453936735164,
55
+ "grad_norm": 0.08664494752883911,
56
+ "learning_rate": 0.00010909090909090909,
57
+ "loss": 0.8889,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.06465019625952435,
62
+ "grad_norm": 0.07322084158658981,
63
+ "learning_rate": 0.00012727272727272728,
64
+ "loss": 0.8809,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.07388593858231356,
69
+ "grad_norm": 0.08361256867647171,
70
+ "learning_rate": 0.00014545454545454546,
71
+ "loss": 0.8901,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.08312168090510275,
76
+ "grad_norm": 0.0712098553776741,
77
+ "learning_rate": 0.00016363636363636366,
78
+ "loss": 0.8712,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.09235742322789194,
83
+ "grad_norm": 0.07038867473602295,
84
+ "learning_rate": 0.00018181818181818183,
85
+ "loss": 0.8779,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.10159316555068114,
90
+ "grad_norm": 0.08133558183908463,
91
+ "learning_rate": 0.0002,
92
+ "loss": 0.8549,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.11082890787347033,
97
+ "grad_norm": 0.07199383527040482,
98
+ "learning_rate": 0.00019994777247895855,
99
+ "loss": 0.8655,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.12006465019625952,
104
+ "grad_norm": 0.08243429660797119,
105
+ "learning_rate": 0.00019979114447011323,
106
+ "loss": 0.891,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.1293003925190487,
111
+ "grad_norm": 0.0855724886059761,
112
+ "learning_rate": 0.00019953027957931658,
113
+ "loss": 0.8675,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.1385361348418379,
118
+ "grad_norm": 0.0847950428724289,
119
+ "learning_rate": 0.00019916545029310012,
120
+ "loss": 0.8579,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.1477718771646271,
125
+ "grad_norm": 0.07739102840423584,
126
+ "learning_rate": 0.00019869703769404828,
127
+ "loss": 0.8643,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.1570076194874163,
132
+ "grad_norm": 0.08714427053928375,
133
+ "learning_rate": 0.00019812553106273847,
134
+ "loss": 0.8766,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.1662433618102055,
139
+ "grad_norm": 0.06926970183849335,
140
+ "learning_rate": 0.00019745152736666302,
141
+ "loss": 0.8539,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.1754791041329947,
146
+ "grad_norm": 0.08098109066486359,
147
+ "learning_rate": 0.0001966757306366662,
148
+ "loss": 0.8823,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.18471484645578387,
153
+ "grad_norm": 0.09138432890176773,
154
+ "learning_rate": 0.0001957989512315489,
155
+ "loss": 0.8601,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.19395058877857307,
160
+ "grad_norm": 0.09067590534687042,
161
+ "learning_rate": 0.00019482210499160765,
162
+ "loss": 0.8551,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.20318633110136228,
167
+ "grad_norm": 0.08557430654764175,
168
+ "learning_rate": 0.0001937462122819935,
169
+ "loss": 0.8582,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.21242207342415145,
174
+ "grad_norm": 0.07583803683519363,
175
+ "learning_rate": 0.00019257239692688907,
176
+ "loss": 0.8468,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.22165781574694066,
181
+ "grad_norm": 0.10376883298158646,
182
+ "learning_rate": 0.00019130188503561741,
183
+ "loss": 0.8722,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.23089355806972986,
188
+ "grad_norm": 0.07388196140527725,
189
+ "learning_rate": 0.00018993600372190932,
190
+ "loss": 0.8715,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.24012930039251904,
195
+ "grad_norm": 0.07768449187278748,
196
+ "learning_rate": 0.00018847617971766577,
197
+ "loss": 0.8632,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.24936504271530824,
202
+ "grad_norm": 0.07902154326438904,
203
+ "learning_rate": 0.00018692393788266479,
204
+ "loss": 0.8746,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.2586007850380974,
209
+ "grad_norm": 0.07420278340578079,
210
+ "learning_rate": 0.0001852808996117683,
211
+ "loss": 0.8676,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.26783652736088664,
216
+ "grad_norm": 0.07562129944562912,
217
+ "learning_rate": 0.00018354878114129367,
218
+ "loss": 0.8829,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.2770722696836758,
223
+ "grad_norm": 0.07764951884746552,
224
+ "learning_rate": 0.00018172939175631808,
225
+ "loss": 0.8766,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.286308012006465,
230
+ "grad_norm": 0.07714657485485077,
231
+ "learning_rate": 0.0001798246319007893,
232
+ "loss": 0.8802,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.2955437543292542,
237
+ "grad_norm": 0.08166080713272095,
238
+ "learning_rate": 0.00017783649119241602,
239
+ "loss": 0.8504,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.3047794966520434,
244
+ "grad_norm": 0.07295581698417664,
245
+ "learning_rate": 0.0001757670463444118,
246
+ "loss": 0.8578,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.3140152389748326,
251
+ "grad_norm": 0.08463213592767715,
252
+ "learning_rate": 0.00017361845899626355,
253
+ "loss": 0.8465,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.3232509812976218,
258
+ "grad_norm": 0.07825674116611481,
259
+ "learning_rate": 0.00017139297345578994,
260
+ "loss": 0.8581,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.332486723620411,
265
+ "grad_norm": 0.08157385140657425,
266
+ "learning_rate": 0.0001690929143548488,
267
+ "loss": 0.8598,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.34172246594320016,
272
+ "grad_norm": 0.08528893440961838,
273
+ "learning_rate": 0.00016672068422114196,
274
+ "loss": 0.85,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.3509582082659894,
279
+ "grad_norm": 0.07343052327632904,
280
+ "learning_rate": 0.00016427876096865394,
281
+ "loss": 0.8515,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.36019395058877857,
286
+ "grad_norm": 0.07675015926361084,
287
+ "learning_rate": 0.00016176969530934572,
288
+ "loss": 0.8628,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.36942969291156774,
293
+ "grad_norm": 0.07422856241464615,
294
+ "learning_rate": 0.0001591961080888076,
295
+ "loss": 0.866,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.378665435234357,
300
+ "grad_norm": 0.0853537917137146,
301
+ "learning_rate": 0.00015656068754865387,
302
+ "loss": 0.8652,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.38790117755714615,
307
+ "grad_norm": 0.07879694551229477,
308
+ "learning_rate": 0.0001538661865185188,
309
+ "loss": 0.8613,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.3971369198799353,
314
+ "grad_norm": 0.0811944380402565,
315
+ "learning_rate": 0.00015111541954058734,
316
+ "loss": 0.8723,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.40637266220272455,
321
+ "grad_norm": 0.08038283884525299,
322
+ "learning_rate": 0.00014831125992966385,
323
+ "loss": 0.8709,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.41560840452551373,
328
+ "grad_norm": 0.07797664403915405,
329
+ "learning_rate": 0.00014545663677185006,
330
+ "loss": 0.8583,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.4248441468483029,
335
+ "grad_norm": 0.08307761698961258,
336
+ "learning_rate": 0.00014255453186496673,
337
+ "loss": 0.8467,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.43407988917109214,
342
+ "grad_norm": 0.07691530138254166,
343
+ "learning_rate": 0.0001396079766039157,
344
+ "loss": 0.8435,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.4433156314938813,
349
+ "grad_norm": 0.09281527251005173,
350
+ "learning_rate": 0.0001366200488142348,
351
+ "loss": 0.8605,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.4525513738166705,
356
+ "grad_norm": 0.07799265533685684,
357
+ "learning_rate": 0.00013359386953715421,
358
+ "loss": 0.85,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.4617871161394597,
363
+ "grad_norm": 0.07675463706254959,
364
+ "learning_rate": 0.00013053259976951133,
365
+ "loss": 0.8434,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.4710228584622489,
370
+ "grad_norm": 0.09029978513717651,
371
+ "learning_rate": 0.00012743943716193016,
372
+ "loss": 0.8587,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.48025860078503807,
377
+ "grad_norm": 0.07997170835733414,
378
+ "learning_rate": 0.00012431761267871417,
379
+ "loss": 0.8436,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.4894943431078273,
384
+ "grad_norm": 0.08595962822437286,
385
+ "learning_rate": 0.0001211703872229411,
386
+ "loss": 0.8682,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.4987300854306165,
391
+ "grad_norm": 0.08949116617441177,
392
+ "learning_rate": 0.00011800104823028515,
393
+ "loss": 0.8663,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.5079658277534057,
398
+ "grad_norm": 0.08509814739227295,
399
+ "learning_rate": 0.0001148129062351249,
400
+ "loss": 0.8359,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.5172015700761948,
405
+ "grad_norm": 0.08007588982582092,
406
+ "learning_rate": 0.00011160929141252303,
407
+ "loss": 0.8494,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.5264373123989841,
412
+ "grad_norm": 0.07660423964262009,
413
+ "learning_rate": 0.00010839355009969068,
414
+ "loss": 0.8403,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.5356730547217733,
419
+ "grad_norm": 0.07779201865196228,
420
+ "learning_rate": 0.00010516904130056946,
421
+ "loss": 0.863,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.5449087970445624,
426
+ "grad_norm": 0.07425861805677414,
427
+ "learning_rate": 0.00010193913317718244,
428
+ "loss": 0.8732,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.5541445393673516,
433
+ "grad_norm": 0.08780544251203537,
434
+ "learning_rate": 9.870719953141917e-05,
435
+ "loss": 0.856,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.5633802816901409,
440
+ "grad_norm": 0.07546891272068024,
441
+ "learning_rate": 9.547661628092937e-05,
442
+ "loss": 0.8418,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.57261602401293,
447
+ "grad_norm": 0.08621185272932053,
448
+ "learning_rate": 9.225075793280692e-05,
449
+ "loss": 0.8463,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.5818517663357192,
454
+ "grad_norm": 0.07618840038776398,
455
+ "learning_rate": 8.903299405874684e-05,
456
+ "loss": 0.8257,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.5910875086585085,
461
+ "grad_norm": 0.07749903202056885,
462
+ "learning_rate": 8.582668577535797e-05,
463
+ "loss": 0.8442,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.6003232509812976,
468
+ "grad_norm": 0.08626076579093933,
469
+ "learning_rate": 8.263518223330697e-05,
470
+ "loss": 0.8739,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.6095589933040868,
475
+ "grad_norm": 0.07912192493677139,
476
+ "learning_rate": 7.94618171189618e-05,
477
+ "loss": 0.816,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.618794735626876,
482
+ "grad_norm": 0.08324088156223297,
483
+ "learning_rate": 7.630990517218808e-05,
484
+ "loss": 0.853,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.6280304779496652,
489
+ "grad_norm": 0.08155480027198792,
490
+ "learning_rate": 7.318273872393625e-05,
491
+ "loss": 0.86,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.6372662202724544,
496
+ "grad_norm": 0.10541233420372009,
497
+ "learning_rate": 7.008358425723585e-05,
498
+ "loss": 0.8674,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.6465019625952436,
503
+ "grad_norm": 0.08856544643640518,
504
+ "learning_rate": 6.701567899518924e-05,
505
+ "loss": 0.8542,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.6557377049180327,
510
+ "grad_norm": 0.0975981131196022,
511
+ "learning_rate": 6.398222751952899e-05,
512
+ "loss": 0.8441,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.664973447240822,
517
+ "grad_norm": 0.0872284546494484,
518
+ "learning_rate": 6.098639842327052e-05,
519
+ "loss": 0.8661,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.6742091895636112,
524
+ "grad_norm": 0.08079314976930618,
525
+ "learning_rate": 5.80313210009571e-05,
526
+ "loss": 0.8465,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.6834449318864003,
531
+ "grad_norm": 0.08326224982738495,
532
+ "learning_rate": 5.5120081979953785e-05,
533
+ "loss": 0.8551,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.6926806742091896,
538
+ "grad_norm": 0.07942940294742584,
539
+ "learning_rate": 5.22557222962051e-05,
540
+ "loss": 0.8673,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.7019164165319788,
545
+ "grad_norm": 0.08273901045322418,
546
+ "learning_rate": 4.9441233917824106e-05,
547
+ "loss": 0.8424,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.7111521588547679,
552
+ "grad_norm": 0.07538026571273804,
553
+ "learning_rate": 4.66795567198309e-05,
554
+ "loss": 0.8448,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.7203879011775571,
559
+ "grad_norm": 0.07920888811349869,
560
+ "learning_rate": 4.397357541330476e-05,
561
+ "loss": 0.874,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.7296236435003464,
566
+ "grad_norm": 0.09400610625743866,
567
+ "learning_rate": 4.132611653215822e-05,
568
+ "loss": 0.8487,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.7388593858231355,
573
+ "grad_norm": 0.08254476636648178,
574
+ "learning_rate": 3.873994548067972e-05,
575
+ "loss": 0.836,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.7480951281459247,
580
+ "grad_norm": 0.08779824525117874,
581
+ "learning_rate": 3.621776364492939e-05,
582
+ "loss": 0.8621,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.757330870468714,
587
+ "grad_norm": 0.08715569227933884,
588
+ "learning_rate": 3.376220557100523e-05,
589
+ "loss": 0.8413,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.7665666127915031,
594
+ "grad_norm": 0.08005767315626144,
595
+ "learning_rate": 3.137583621312665e-05,
596
+ "loss": 0.8563,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.7758023551142923,
601
+ "grad_norm": 0.08362836390733719,
602
+ "learning_rate": 2.906114825441072e-05,
603
+ "loss": 0.8431,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.7850380974370815,
608
+ "grad_norm": 0.08525697141885757,
609
+ "learning_rate": 2.6820559503138797e-05,
610
+ "loss": 0.8619,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.7942738397598706,
615
+ "grad_norm": 0.08668297529220581,
616
+ "learning_rate": 2.465641036723393e-05,
617
+ "loss": 0.8525,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.8035095820826599,
622
+ "grad_norm": 0.08923713862895966,
623
+ "learning_rate": 2.2570961409586754e-05,
624
+ "loss": 0.854,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.8127453244054491,
629
+ "grad_norm": 0.08294524252414703,
630
+ "learning_rate": 2.0566390986783646e-05,
631
+ "loss": 0.867,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.8219810667282382,
636
+ "grad_norm": 0.08329101651906967,
637
+ "learning_rate": 1.864479297370325e-05,
638
+ "loss": 0.8454,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.8312168090510275,
643
+ "grad_norm": 0.08947557955980301,
644
+ "learning_rate": 1.6808174576358848e-05,
645
+ "loss": 0.8663,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.8404525513738167,
650
+ "grad_norm": 0.08388309925794601,
651
+ "learning_rate": 1.505845423527027e-05,
652
+ "loss": 0.8663,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.8496882936966058,
657
+ "grad_norm": 0.07886148244142532,
658
+ "learning_rate": 1.339745962155613e-05,
659
+ "loss": 0.8484,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.858924036019395,
664
+ "grad_norm": 0.08021736145019531,
665
+ "learning_rate": 1.18269257278392e-05,
666
+ "loss": 0.8613,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.8681597783421843,
671
+ "grad_norm": 0.0815872773528099,
672
+ "learning_rate": 1.0348493055959062e-05,
673
+ "loss": 0.8361,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.8773955206649734,
678
+ "grad_norm": 0.08512595295906067,
679
+ "learning_rate": 8.963705903385345e-06,
680
+ "loss": 0.8236,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.8866312629877626,
685
+ "grad_norm": 0.07890893518924713,
686
+ "learning_rate": 7.674010750120964e-06,
687
+ "loss": 0.8398,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.8958670053105519,
692
+ "grad_norm": 0.08390273153781891,
693
+ "learning_rate": 6.480754747781037e-06,
694
+ "loss": 0.8392,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.905102747633341,
699
+ "grad_norm": 0.07941864430904388,
700
+ "learning_rate": 5.385184312424974e-06,
701
+ "loss": 0.8344,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.9143384899561302,
706
+ "grad_norm": 0.0822635293006897,
707
+ "learning_rate": 4.3884438226120424e-06,
708
+ "loss": 0.8492,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.9235742322789194,
713
+ "grad_norm": 0.07574615627527237,
714
+ "learning_rate": 3.4915744240403558e-06,
715
+ "loss": 0.8499,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.9328099746017086,
720
+ "grad_norm": 0.08466410636901855,
721
+ "learning_rate": 2.6955129420176196e-06,
722
+ "loss": 0.848,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.9420457169244978,
727
+ "grad_norm": 0.0831914022564888,
728
+ "learning_rate": 2.0010909028998827e-06,
729
+ "loss": 0.8442,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.951281459247287,
734
+ "grad_norm": 0.08431433886289597,
735
+ "learning_rate": 1.409033665520354e-06,
736
+ "loss": 0.8491,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.9605172015700761,
741
+ "grad_norm": 0.08757560700178146,
742
+ "learning_rate": 9.199596635154683e-07,
743
+ "loss": 0.8526,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.9697529438928654,
748
+ "grad_norm": 0.0839475765824318,
749
+ "learning_rate": 5.343797593398536e-07,
750
+ "loss": 0.8663,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.9789886862156546,
755
+ "grad_norm": 0.07811986654996872,
756
+ "learning_rate": 2.5269671064467313e-07,
757
+ "loss": 0.8473,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.9882244285384437,
762
+ "grad_norm": 0.08186525851488113,
763
+ "learning_rate": 7.520474957699586e-08,
764
+ "loss": 0.8295,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.997460170861233,
769
+ "grad_norm": 0.0831933468580246,
770
+ "learning_rate": 2.0892754394208346e-09,
771
+ "loss": 0.8639,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.9993073193257908,
776
+ "eval_loss": 1.0852999687194824,
777
+ "eval_runtime": 177.1887,
778
+ "eval_samples_per_second": 6.518,
779
+ "eval_steps_per_second": 0.547,
780
+ "step": 541
781
+ },
782
+ {
783
+ "epoch": 0.9993073193257908,
784
+ "step": 541,
785
+ "total_flos": 2.705944628841939e+18,
786
+ "train_loss": 0.860630649956229,
787
+ "train_runtime": 42250.2981,
788
+ "train_samples_per_second": 2.46,
789
+ "train_steps_per_second": 0.013
790
+ }
791
+ ],
792
+ "logging_steps": 5,
793
+ "max_steps": 541,
794
+ "num_input_tokens_seen": 0,
795
+ "num_train_epochs": 1,
796
+ "save_steps": 25,
797
+ "stateful_callbacks": {
798
+ "TrainerControl": {
799
+ "args": {
800
+ "should_epoch_stop": false,
801
+ "should_evaluate": false,
802
+ "should_log": false,
803
+ "should_save": true,
804
+ "should_training_stop": false
805
+ },
806
+ "attributes": {}
807
+ }
808
+ },
809
+ "total_flos": 2.705944628841939e+18,
810
+ "train_batch_size": 8,
811
+ "trial_name": null,
812
+ "trial_params": null
813
+ }