cfahlgren1 HF Staff commited on
Commit
1cffd47
·
verified ·
1 Parent(s): 63b64fd

tinynext-v2: 12.5M params, 28 min on GPU

Browse files
v2/config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab": 8192,
3
+ "dim": 320,
4
+ "layers": 8,
5
+ "heads": 5,
6
+ "ffn": 864,
7
+ "parameters": 12539200,
8
+ "seq": 512,
9
+ "special_tokens": {
10
+ "<|endoftext|>": 0,
11
+ "<|pre|>": 1,
12
+ "<|suf|>": 2,
13
+ "<|mid|>": 3
14
+ },
15
+ "prompt": "No text after the cursor: the text before it. Otherwise: <|suf|> after <|pre|> before <|mid|>."
16
+ }
v2/metrics/tinynext-v2.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "tinynext-v2",
3
+ "sees_after": true,
4
+ "cutoffs": {
5
+ "0.3": {
6
+ "articles/typing": {
7
+ "pauses": 1000,
8
+ "shown": 0.188,
9
+ "right": 0.617,
10
+ "avg_right_chars": 5.91,
11
+ "multiword_shown": 0.067,
12
+ "multiword_right": 0.5373,
13
+ "saved_with_tab": 0.0572,
14
+ "saved_word_by_word": 0.0626
15
+ },
16
+ "articles/editing": {
17
+ "pauses": 1000,
18
+ "shown": 0.148,
19
+ "right": 0.6081,
20
+ "avg_right_chars": 5.94,
21
+ "multiword_shown": 0.058,
22
+ "multiword_right": 0.5862,
23
+ "saved_with_tab": 0.0446,
24
+ "saved_word_by_word": 0.0491
25
+ },
26
+ "messages/typing": {
27
+ "pauses": 1000,
28
+ "shown": 0.293,
29
+ "right": 0.5563,
30
+ "avg_right_chars": 7.71,
31
+ "multiword_shown": 0.163,
32
+ "multiword_right": 0.546,
33
+ "saved_with_tab": 0.1047,
34
+ "saved_word_by_word": 0.1232
35
+ },
36
+ "messages/editing": {
37
+ "pauses": 1000,
38
+ "shown": 0.276,
39
+ "right": 0.6159,
40
+ "avg_right_chars": 7.49,
41
+ "multiword_shown": 0.152,
42
+ "multiword_right": 0.6118,
43
+ "saved_with_tab": 0.1061,
44
+ "saved_word_by_word": 0.1183
45
+ },
46
+ "email/typing": {
47
+ "pauses": 1000,
48
+ "shown": 0.237,
49
+ "right": 0.5443,
50
+ "avg_right_chars": 6.09,
51
+ "multiword_shown": 0.084,
52
+ "multiword_right": 0.3929,
53
+ "saved_with_tab": 0.0655,
54
+ "saved_word_by_word": 0.0744
55
+ },
56
+ "email/editing": {
57
+ "pauses": 1000,
58
+ "shown": 0.22,
59
+ "right": 0.5273,
60
+ "avg_right_chars": 5.77,
61
+ "multiword_shown": 0.093,
62
+ "multiword_right": 0.4194,
63
+ "saved_with_tab": 0.0558,
64
+ "saved_word_by_word": 0.0645
65
+ }
66
+ },
67
+ "0.4": {
68
+ "articles/typing": {
69
+ "pauses": 1000,
70
+ "shown": 0.14,
71
+ "right": 0.7214,
72
+ "avg_right_chars": 5.94,
73
+ "multiword_shown": 0.043,
74
+ "multiword_right": 0.6744,
75
+ "saved_with_tab": 0.05,
76
+ "saved_word_by_word": 0.0522
77
+ },
78
+ "articles/editing": {
79
+ "pauses": 1000,
80
+ "shown": 0.102,
81
+ "right": 0.6667,
82
+ "avg_right_chars": 5.65,
83
+ "multiword_shown": 0.034,
84
+ "multiword_right": 0.7353,
85
+ "saved_with_tab": 0.032,
86
+ "saved_word_by_word": 0.0341
87
+ },
88
+ "messages/typing": {
89
+ "pauses": 1000,
90
+ "shown": 0.212,
91
+ "right": 0.6934,
92
+ "avg_right_chars": 7.19,
93
+ "multiword_shown": 0.105,
94
+ "multiword_right": 0.6571,
95
+ "saved_with_tab": 0.0881,
96
+ "saved_word_by_word": 0.0958
97
+ },
98
+ "messages/editing": {
99
+ "pauses": 1000,
100
+ "shown": 0.194,
101
+ "right": 0.7113,
102
+ "avg_right_chars": 6.83,
103
+ "multiword_shown": 0.097,
104
+ "multiword_right": 0.6907,
105
+ "saved_with_tab": 0.0785,
106
+ "saved_word_by_word": 0.086
107
+ },
108
+ "email/typing": {
109
+ "pauses": 1000,
110
+ "shown": 0.172,
111
+ "right": 0.686,
112
+ "avg_right_chars": 5.86,
113
+ "multiword_shown": 0.053,
114
+ "multiword_right": 0.434,
115
+ "saved_with_tab": 0.0576,
116
+ "saved_word_by_word": 0.0618
117
+ },
118
+ "email/editing": {
119
+ "pauses": 1000,
120
+ "shown": 0.147,
121
+ "right": 0.6395,
122
+ "avg_right_chars": 5.48,
123
+ "multiword_shown": 0.057,
124
+ "multiword_right": 0.5439,
125
+ "saved_with_tab": 0.0429,
126
+ "saved_word_by_word": 0.0459
127
+ }
128
+ },
129
+ "0.5": {
130
+ "articles/typing": {
131
+ "pauses": 1000,
132
+ "shown": 0.106,
133
+ "right": 0.7642,
134
+ "avg_right_chars": 5.9,
135
+ "multiword_shown": 0.034,
136
+ "multiword_right": 0.7353,
137
+ "saved_with_tab": 0.0398,
138
+ "saved_word_by_word": 0.0411
139
+ },
140
+ "articles/editing": {
141
+ "pauses": 1000,
142
+ "shown": 0.078,
143
+ "right": 0.7692,
144
+ "avg_right_chars": 5.55,
145
+ "multiword_shown": 0.022,
146
+ "multiword_right": 0.8636,
147
+ "saved_with_tab": 0.0278,
148
+ "saved_word_by_word": 0.0282
149
+ },
150
+ "messages/typing": {
151
+ "pauses": 1000,
152
+ "shown": 0.163,
153
+ "right": 0.7791,
154
+ "avg_right_chars": 6.86,
155
+ "multiword_shown": 0.078,
156
+ "multiword_right": 0.7179,
157
+ "saved_with_tab": 0.0726,
158
+ "saved_word_by_word": 0.078
159
+ },
160
+ "messages/editing": {
161
+ "pauses": 1000,
162
+ "shown": 0.146,
163
+ "right": 0.7877,
164
+ "avg_right_chars": 6.63,
165
+ "multiword_shown": 0.071,
166
+ "multiword_right": 0.7465,
167
+ "saved_with_tab": 0.0635,
168
+ "saved_word_by_word": 0.0679
169
+ },
170
+ "email/typing": {
171
+ "pauses": 1000,
172
+ "shown": 0.113,
173
+ "right": 0.7876,
174
+ "avg_right_chars": 5.84,
175
+ "multiword_shown": 0.03,
176
+ "multiword_right": 0.6,
177
+ "saved_with_tab": 0.0433,
178
+ "saved_word_by_word": 0.0452
179
+ },
180
+ "email/editing": {
181
+ "pauses": 1000,
182
+ "shown": 0.104,
183
+ "right": 0.7788,
184
+ "avg_right_chars": 5.32,
185
+ "multiword_shown": 0.03,
186
+ "multiword_right": 0.7,
187
+ "saved_with_tab": 0.0359,
188
+ "saved_word_by_word": 0.0369
189
+ }
190
+ },
191
+ "0.6": {
192
+ "articles/typing": {
193
+ "pauses": 1000,
194
+ "shown": 0.084,
195
+ "right": 0.8571,
196
+ "avg_right_chars": 5.86,
197
+ "multiword_shown": 0.022,
198
+ "multiword_right": 0.8636,
199
+ "saved_with_tab": 0.0352,
200
+ "saved_word_by_word": 0.0353
201
+ },
202
+ "articles/editing": {
203
+ "pauses": 1000,
204
+ "shown": 0.056,
205
+ "right": 0.8571,
206
+ "avg_right_chars": 5.62,
207
+ "multiword_shown": 0.016,
208
+ "multiword_right": 0.9375,
209
+ "saved_with_tab": 0.0225,
210
+ "saved_word_by_word": 0.0227
211
+ },
212
+ "messages/typing": {
213
+ "pauses": 1000,
214
+ "shown": 0.123,
215
+ "right": 0.8455,
216
+ "avg_right_chars": 6.73,
217
+ "multiword_shown": 0.06,
218
+ "multiword_right": 0.8167,
219
+ "saved_with_tab": 0.0583,
220
+ "saved_word_by_word": 0.061
221
+ },
222
+ "messages/editing": {
223
+ "pauses": 1000,
224
+ "shown": 0.108,
225
+ "right": 0.8426,
226
+ "avg_right_chars": 6.31,
227
+ "multiword_shown": 0.052,
228
+ "multiword_right": 0.7308,
229
+ "saved_with_tab": 0.0478,
230
+ "saved_word_by_word": 0.0512
231
+ },
232
+ "email/typing": {
233
+ "pauses": 1000,
234
+ "shown": 0.076,
235
+ "right": 0.8816,
236
+ "avg_right_chars": 5.79,
237
+ "multiword_shown": 0.016,
238
+ "multiword_right": 0.8125,
239
+ "saved_with_tab": 0.0323,
240
+ "saved_word_by_word": 0.0324
241
+ },
242
+ "email/editing": {
243
+ "pauses": 1000,
244
+ "shown": 0.071,
245
+ "right": 0.8873,
246
+ "avg_right_chars": 5.25,
247
+ "multiword_shown": 0.014,
248
+ "multiword_right": 0.8571,
249
+ "saved_with_tab": 0.0276,
250
+ "saved_word_by_word": 0.0279
251
+ }
252
+ },
253
+ "0.7": {
254
+ "articles/typing": {
255
+ "pauses": 1000,
256
+ "shown": 0.059,
257
+ "right": 0.9153,
258
+ "avg_right_chars": 5.76,
259
+ "multiword_shown": 0.018,
260
+ "multiword_right": 0.9444,
261
+ "saved_with_tab": 0.0259,
262
+ "saved_word_by_word": 0.0261
263
+ },
264
+ "articles/editing": {
265
+ "pauses": 1000,
266
+ "shown": 0.035,
267
+ "right": 0.8286,
268
+ "avg_right_chars": 5.34,
269
+ "multiword_shown": 0.007,
270
+ "multiword_right": 0.8571,
271
+ "saved_with_tab": 0.0129,
272
+ "saved_word_by_word": 0.0132
273
+ },
274
+ "messages/typing": {
275
+ "pauses": 1000,
276
+ "shown": 0.099,
277
+ "right": 0.9293,
278
+ "avg_right_chars": 6.37,
279
+ "multiword_shown": 0.042,
280
+ "multiword_right": 0.9048,
281
+ "saved_with_tab": 0.0488,
282
+ "saved_word_by_word": 0.0492
283
+ },
284
+ "messages/editing": {
285
+ "pauses": 1000,
286
+ "shown": 0.086,
287
+ "right": 0.8837,
288
+ "avg_right_chars": 5.97,
289
+ "multiword_shown": 0.036,
290
+ "multiword_right": 0.7222,
291
+ "saved_with_tab": 0.0378,
292
+ "saved_word_by_word": 0.0408
293
+ },
294
+ "email/typing": {
295
+ "pauses": 1000,
296
+ "shown": 0.05,
297
+ "right": 0.84,
298
+ "avg_right_chars": 5.45,
299
+ "multiword_shown": 0.006,
300
+ "multiword_right": 0.5,
301
+ "saved_with_tab": 0.0191,
302
+ "saved_word_by_word": 0.0192
303
+ },
304
+ "email/editing": {
305
+ "pauses": 1000,
306
+ "shown": 0.054,
307
+ "right": 0.9074,
308
+ "avg_right_chars": 5.16,
309
+ "multiword_shown": 0.01,
310
+ "multiword_right": 0.9,
311
+ "saved_with_tab": 0.0211,
312
+ "saved_word_by_word": 0.0211
313
+ }
314
+ }
315
+ },
316
+ "examples": [
317
+ {
318
+ "domain": "articles",
319
+ "scenario": "editing",
320
+ "before": " the Spaghetti Western film genre) and Hate Boat, were publi",
321
+ "suggestion": "shed",
322
+ "truth": "shed by Comico C",
323
+ "right": true
324
+ },
325
+ {
326
+ "domain": "messages",
327
+ "scenario": "editing",
328
+ "before": "e optimal level of production and pricing for businesses. L'",
329
+ "suggestion": "Hpital's Rule",
330
+ "truth": "Hpital's Rule can help an",
331
+ "right": true
332
+ },
333
+ {
334
+ "domain": "email",
335
+ "scenario": "editing",
336
+ "before": "ured products and marketing of electricity for the United St",
337
+ "suggestion": "ates",
338
+ "truth": "ates ? Actively ",
339
+ "right": true
340
+ }
341
+ ],
342
+ "latency_ms": {
343
+ "p50": 16.88,
344
+ "p95": 43.43,
345
+ "note": "Measured in this eval process, not in a browser."
346
+ }
347
+ }
v2/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:517b40693de7ff4618dbd6fe267416059e2b94cfa93d9e3a89c044008380b10f
3
+ size 60813575
v2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a8218faeefdd282109f42f22a019d28b19182bfa041c8f49039546726e63fea
3
+ size 50161328
v2/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e247edf2479b5a5073f33fb418a450c1d6ba82efcb54e06be2a8b728dd7df65e
3
+ size 23328690
v2/report.json ADDED
@@ -0,0 +1,1234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "args": {
3
+ "vocab": 8192,
4
+ "dim": 320,
5
+ "layers": 8,
6
+ "heads": 5,
7
+ "ffn": 864,
8
+ "seq": 512,
9
+ "tokens": 1500000000.0,
10
+ "val_tokens": 4000000.0,
11
+ "epochs": 1.0,
12
+ "batch": 512,
13
+ "lr": 0.003,
14
+ "fim_rate": 0.5,
15
+ "mix": "fineweb=0.6,smoltalk=0.3,enron=0.1",
16
+ "fineweb_files": 2,
17
+ "smoltalk_files": 9,
18
+ "tokenizer_docs": 200000,
19
+ "eval_pauses": 1000,
20
+ "log_every": 50,
21
+ "repo": "cfahlgren1/tinynext",
22
+ "folder": "v2",
23
+ "name": "tinynext-v2",
24
+ "trackio_space": "cfahlgren1/tinynext-trackio",
25
+ "stage": "train",
26
+ "data_repo": "cfahlgren1/tinynext-data",
27
+ "smoke": false,
28
+ "no_push": false
29
+ },
30
+ "parameters": 12539200,
31
+ "data": {
32
+ "fineweb": {
33
+ "docs": 1062484,
34
+ "train_tokens": 900000000
35
+ },
36
+ "smoltalk": {
37
+ "docs": 671427,
38
+ "train_tokens": 450000000
39
+ },
40
+ "enron": {
41
+ "docs": 268120,
42
+ "train_tokens": 150000000
43
+ }
44
+ },
45
+ "data_minutes": 0.2,
46
+ "train_minutes": 28.1,
47
+ "history": [
48
+ {
49
+ "step": 0,
50
+ "train_loss": 9.0697,
51
+ "lr": 2.6e-05,
52
+ "tokens_per_second": 13248,
53
+ "minutes": 0.33,
54
+ "mfu_percent": 0.3,
55
+ "gpu_util_percent": 98,
56
+ "gpu_memory_gb": 70.5,
57
+ "val_loss": 9.0682
58
+ },
59
+ {
60
+ "step": 50,
61
+ "train_loss": 7.0154,
62
+ "lr": 0.001342,
63
+ "tokens_per_second": 932232,
64
+ "minutes": 0.61,
65
+ "mfu_percent": 22.5,
66
+ "gpu_util_percent": 100,
67
+ "gpu_memory_gb": 79.1
68
+ },
69
+ {
70
+ "step": 100,
71
+ "train_loss": 6.0698,
72
+ "lr": 0.002656,
73
+ "tokens_per_second": 926160,
74
+ "minutes": 0.85,
75
+ "mfu_percent": 22.3,
76
+ "gpu_util_percent": 100,
77
+ "gpu_memory_gb": 79.1
78
+ },
79
+ {
80
+ "step": 150,
81
+ "train_loss": 5.5539,
82
+ "lr": 0.002995,
83
+ "tokens_per_second": 923370,
84
+ "minutes": 1.09,
85
+ "mfu_percent": 22.3,
86
+ "gpu_util_percent": 100,
87
+ "gpu_memory_gb": 79.1
88
+ },
89
+ {
90
+ "step": 200,
91
+ "train_loss": 5.0756,
92
+ "lr": 0.002992,
93
+ "tokens_per_second": 922463,
94
+ "minutes": 1.32,
95
+ "mfu_percent": 22.2,
96
+ "gpu_util_percent": 100,
97
+ "gpu_memory_gb": 79.1
98
+ },
99
+ {
100
+ "step": 250,
101
+ "train_loss": 4.6591,
102
+ "lr": 0.002987,
103
+ "tokens_per_second": 923079,
104
+ "minutes": 1.56,
105
+ "mfu_percent": 22.3,
106
+ "gpu_util_percent": 100,
107
+ "gpu_memory_gb": 79.1
108
+ },
109
+ {
110
+ "step": 300,
111
+ "train_loss": 4.3203,
112
+ "lr": 0.002982,
113
+ "tokens_per_second": 922918,
114
+ "minutes": 1.8,
115
+ "mfu_percent": 22.3,
116
+ "gpu_util_percent": 100,
117
+ "gpu_memory_gb": 79.1
118
+ },
119
+ {
120
+ "step": 350,
121
+ "train_loss": 4.0751,
122
+ "lr": 0.002975,
123
+ "tokens_per_second": 922585,
124
+ "minutes": 2.03,
125
+ "mfu_percent": 22.2,
126
+ "gpu_util_percent": 100,
127
+ "gpu_memory_gb": 79.1
128
+ },
129
+ {
130
+ "step": 400,
131
+ "train_loss": 3.8986,
132
+ "lr": 0.002967,
133
+ "tokens_per_second": 923709,
134
+ "minutes": 2.27,
135
+ "mfu_percent": 22.3,
136
+ "gpu_util_percent": 100,
137
+ "gpu_memory_gb": 79.1
138
+ },
139
+ {
140
+ "step": 450,
141
+ "train_loss": 3.7565,
142
+ "lr": 0.002959,
143
+ "tokens_per_second": 923903,
144
+ "minutes": 2.51,
145
+ "mfu_percent": 22.3,
146
+ "gpu_util_percent": 100,
147
+ "gpu_memory_gb": 79.1
148
+ },
149
+ {
150
+ "step": 500,
151
+ "train_loss": 3.6807,
152
+ "lr": 0.002949,
153
+ "tokens_per_second": 923528,
154
+ "minutes": 2.74,
155
+ "mfu_percent": 22.3,
156
+ "gpu_util_percent": 100,
157
+ "gpu_memory_gb": 79.1,
158
+ "val_loss": 3.7221
159
+ },
160
+ {
161
+ "step": 550,
162
+ "train_loss": 3.6681,
163
+ "lr": 0.002938,
164
+ "tokens_per_second": 922910,
165
+ "minutes": 3.03,
166
+ "mfu_percent": 22.3,
167
+ "gpu_util_percent": 100,
168
+ "gpu_memory_gb": 79.1
169
+ },
170
+ {
171
+ "step": 600,
172
+ "train_loss": 3.6275,
173
+ "lr": 0.002927,
174
+ "tokens_per_second": 921856,
175
+ "minutes": 3.26,
176
+ "mfu_percent": 22.2,
177
+ "gpu_util_percent": 100,
178
+ "gpu_memory_gb": 79.1
179
+ },
180
+ {
181
+ "step": 650,
182
+ "train_loss": 3.5235,
183
+ "lr": 0.002914,
184
+ "tokens_per_second": 920847,
185
+ "minutes": 3.5,
186
+ "mfu_percent": 22.2,
187
+ "gpu_util_percent": 100,
188
+ "gpu_memory_gb": 79.1
189
+ },
190
+ {
191
+ "step": 700,
192
+ "train_loss": 3.5007,
193
+ "lr": 0.002901,
194
+ "tokens_per_second": 920478,
195
+ "minutes": 3.74,
196
+ "mfu_percent": 22.2,
197
+ "gpu_util_percent": 100,
198
+ "gpu_memory_gb": 79.1
199
+ },
200
+ {
201
+ "step": 750,
202
+ "train_loss": 3.5063,
203
+ "lr": 0.002886,
204
+ "tokens_per_second": 920413,
205
+ "minutes": 3.97,
206
+ "mfu_percent": 22.2,
207
+ "gpu_util_percent": 100,
208
+ "gpu_memory_gb": 79.1
209
+ },
210
+ {
211
+ "step": 800,
212
+ "train_loss": 3.4786,
213
+ "lr": 0.002871,
214
+ "tokens_per_second": 919895,
215
+ "minutes": 4.21,
216
+ "mfu_percent": 22.2,
217
+ "gpu_util_percent": 100,
218
+ "gpu_memory_gb": 79.1
219
+ },
220
+ {
221
+ "step": 850,
222
+ "train_loss": 3.4053,
223
+ "lr": 0.002855,
224
+ "tokens_per_second": 919668,
225
+ "minutes": 4.45,
226
+ "mfu_percent": 22.2,
227
+ "gpu_util_percent": 100,
228
+ "gpu_memory_gb": 79.1
229
+ },
230
+ {
231
+ "step": 900,
232
+ "train_loss": 3.4465,
233
+ "lr": 0.002837,
234
+ "tokens_per_second": 919590,
235
+ "minutes": 4.69,
236
+ "mfu_percent": 22.2,
237
+ "gpu_util_percent": 100,
238
+ "gpu_memory_gb": 79.1
239
+ },
240
+ {
241
+ "step": 950,
242
+ "train_loss": 3.3967,
243
+ "lr": 0.002819,
244
+ "tokens_per_second": 919159,
245
+ "minutes": 4.92,
246
+ "mfu_percent": 22.2,
247
+ "gpu_util_percent": 100,
248
+ "gpu_memory_gb": 79.1
249
+ },
250
+ {
251
+ "step": 1000,
252
+ "train_loss": 3.3874,
253
+ "lr": 0.0028,
254
+ "tokens_per_second": 918998,
255
+ "minutes": 5.16,
256
+ "mfu_percent": 22.2,
257
+ "gpu_util_percent": 100,
258
+ "gpu_memory_gb": 79.1,
259
+ "val_loss": 3.4027
260
+ },
261
+ {
262
+ "step": 1050,
263
+ "train_loss": 3.3679,
264
+ "lr": 0.002781,
265
+ "tokens_per_second": 919250,
266
+ "minutes": 5.45,
267
+ "mfu_percent": 22.2,
268
+ "gpu_util_percent": 100,
269
+ "gpu_memory_gb": 79.1
270
+ },
271
+ {
272
+ "step": 1100,
273
+ "train_loss": 3.335,
274
+ "lr": 0.00276,
275
+ "tokens_per_second": 919050,
276
+ "minutes": 5.68,
277
+ "mfu_percent": 22.2,
278
+ "gpu_util_percent": 100,
279
+ "gpu_memory_gb": 79.1
280
+ },
281
+ {
282
+ "step": 1150,
283
+ "train_loss": 3.365,
284
+ "lr": 0.002738,
285
+ "tokens_per_second": 918695,
286
+ "minutes": 5.92,
287
+ "mfu_percent": 22.2,
288
+ "gpu_util_percent": 100,
289
+ "gpu_memory_gb": 79.1
290
+ },
291
+ {
292
+ "step": 1200,
293
+ "train_loss": 3.3143,
294
+ "lr": 0.002716,
295
+ "tokens_per_second": 918833,
296
+ "minutes": 6.16,
297
+ "mfu_percent": 22.2,
298
+ "gpu_util_percent": 100,
299
+ "gpu_memory_gb": 79.1
300
+ },
301
+ {
302
+ "step": 1250,
303
+ "train_loss": 3.2921,
304
+ "lr": 0.002693,
305
+ "tokens_per_second": 918924,
306
+ "minutes": 6.4,
307
+ "mfu_percent": 22.2,
308
+ "gpu_util_percent": 100,
309
+ "gpu_memory_gb": 79.1
310
+ },
311
+ {
312
+ "step": 1300,
313
+ "train_loss": 3.3627,
314
+ "lr": 0.002669,
315
+ "tokens_per_second": 919045,
316
+ "minutes": 6.64,
317
+ "mfu_percent": 22.2,
318
+ "gpu_util_percent": 100,
319
+ "gpu_memory_gb": 79.1
320
+ },
321
+ {
322
+ "step": 1350,
323
+ "train_loss": 3.3008,
324
+ "lr": 0.002644,
325
+ "tokens_per_second": 919010,
326
+ "minutes": 6.87,
327
+ "mfu_percent": 22.2,
328
+ "gpu_util_percent": 100,
329
+ "gpu_memory_gb": 79.1
330
+ },
331
+ {
332
+ "step": 1400,
333
+ "train_loss": 3.2552,
334
+ "lr": 0.002618,
335
+ "tokens_per_second": 919072,
336
+ "minutes": 7.11,
337
+ "mfu_percent": 22.2,
338
+ "gpu_util_percent": 100,
339
+ "gpu_memory_gb": 79.1
340
+ },
341
+ {
342
+ "step": 1450,
343
+ "train_loss": 3.2611,
344
+ "lr": 0.002592,
345
+ "tokens_per_second": 919238,
346
+ "minutes": 7.35,
347
+ "mfu_percent": 22.2,
348
+ "gpu_util_percent": 100,
349
+ "gpu_memory_gb": 79.1
350
+ },
351
+ {
352
+ "step": 1500,
353
+ "train_loss": 3.2515,
354
+ "lr": 0.002565,
355
+ "tokens_per_second": 919356,
356
+ "minutes": 7.59,
357
+ "mfu_percent": 22.2,
358
+ "gpu_util_percent": 100,
359
+ "gpu_memory_gb": 79.1,
360
+ "val_loss": 3.2835
361
+ },
362
+ {
363
+ "step": 1550,
364
+ "train_loss": 3.2331,
365
+ "lr": 0.002538,
366
+ "tokens_per_second": 919186,
367
+ "minutes": 7.87,
368
+ "mfu_percent": 22.2,
369
+ "gpu_util_percent": 100,
370
+ "gpu_memory_gb": 79.1
371
+ },
372
+ {
373
+ "step": 1600,
374
+ "train_loss": 3.3018,
375
+ "lr": 0.002509,
376
+ "tokens_per_second": 919216,
377
+ "minutes": 8.11,
378
+ "mfu_percent": 22.2,
379
+ "gpu_util_percent": 100,
380
+ "gpu_memory_gb": 79.1
381
+ },
382
+ {
383
+ "step": 1650,
384
+ "train_loss": 3.2305,
385
+ "lr": 0.00248,
386
+ "tokens_per_second": 918761,
387
+ "minutes": 8.35,
388
+ "mfu_percent": 22.2,
389
+ "gpu_util_percent": 100,
390
+ "gpu_memory_gb": 79.1
391
+ },
392
+ {
393
+ "step": 1700,
394
+ "train_loss": 3.2899,
395
+ "lr": 0.002451,
396
+ "tokens_per_second": 918918,
397
+ "minutes": 8.58,
398
+ "mfu_percent": 22.2,
399
+ "gpu_util_percent": 100,
400
+ "gpu_memory_gb": 79.1
401
+ },
402
+ {
403
+ "step": 1750,
404
+ "train_loss": 3.2422,
405
+ "lr": 0.002421,
406
+ "tokens_per_second": 918821,
407
+ "minutes": 8.82,
408
+ "mfu_percent": 22.2,
409
+ "gpu_util_percent": 100,
410
+ "gpu_memory_gb": 79.1
411
+ },
412
+ {
413
+ "step": 1800,
414
+ "train_loss": 3.2045,
415
+ "lr": 0.00239,
416
+ "tokens_per_second": 918803,
417
+ "minutes": 9.06,
418
+ "mfu_percent": 22.2,
419
+ "gpu_util_percent": 100,
420
+ "gpu_memory_gb": 79.1
421
+ },
422
+ {
423
+ "step": 1850,
424
+ "train_loss": 3.2057,
425
+ "lr": 0.002358,
426
+ "tokens_per_second": 918327,
427
+ "minutes": 9.3,
428
+ "mfu_percent": 22.1,
429
+ "gpu_util_percent": 100,
430
+ "gpu_memory_gb": 79.1
431
+ },
432
+ {
433
+ "step": 1900,
434
+ "train_loss": 3.1794,
435
+ "lr": 0.002327,
436
+ "tokens_per_second": 918460,
437
+ "minutes": 9.54,
438
+ "mfu_percent": 22.1,
439
+ "gpu_util_percent": 100,
440
+ "gpu_memory_gb": 79.1
441
+ },
442
+ {
443
+ "step": 1950,
444
+ "train_loss": 3.1661,
445
+ "lr": 0.002294,
446
+ "tokens_per_second": 918253,
447
+ "minutes": 9.77,
448
+ "mfu_percent": 22.1,
449
+ "gpu_util_percent": 100,
450
+ "gpu_memory_gb": 79.1
451
+ },
452
+ {
453
+ "step": 2000,
454
+ "train_loss": 3.1771,
455
+ "lr": 0.002261,
456
+ "tokens_per_second": 918444,
457
+ "minutes": 10.01,
458
+ "mfu_percent": 22.1,
459
+ "gpu_util_percent": 100,
460
+ "gpu_memory_gb": 79.1,
461
+ "val_loss": 3.2099
462
+ },
463
+ {
464
+ "step": 2050,
465
+ "train_loss": 3.1498,
466
+ "lr": 0.002228,
467
+ "tokens_per_second": 919237,
468
+ "minutes": 10.3,
469
+ "mfu_percent": 22.2,
470
+ "gpu_util_percent": 100,
471
+ "gpu_memory_gb": 79.1
472
+ },
473
+ {
474
+ "step": 2100,
475
+ "train_loss": 3.164,
476
+ "lr": 0.002194,
477
+ "tokens_per_second": 920523,
478
+ "minutes": 10.53,
479
+ "mfu_percent": 22.2,
480
+ "gpu_util_percent": 100,
481
+ "gpu_memory_gb": 79.1
482
+ },
483
+ {
484
+ "step": 2150,
485
+ "train_loss": 3.1412,
486
+ "lr": 0.00216,
487
+ "tokens_per_second": 921392,
488
+ "minutes": 10.77,
489
+ "mfu_percent": 22.2,
490
+ "gpu_util_percent": 100,
491
+ "gpu_memory_gb": 79.1
492
+ },
493
+ {
494
+ "step": 2200,
495
+ "train_loss": 3.1425,
496
+ "lr": 0.002125,
497
+ "tokens_per_second": 921489,
498
+ "minutes": 11.01,
499
+ "mfu_percent": 22.2,
500
+ "gpu_util_percent": 100,
501
+ "gpu_memory_gb": 79.1
502
+ },
503
+ {
504
+ "step": 2250,
505
+ "train_loss": 3.1489,
506
+ "lr": 0.00209,
507
+ "tokens_per_second": 921290,
508
+ "minutes": 11.24,
509
+ "mfu_percent": 22.2,
510
+ "gpu_util_percent": 100,
511
+ "gpu_memory_gb": 79.1
512
+ },
513
+ {
514
+ "step": 2300,
515
+ "train_loss": 3.1575,
516
+ "lr": 0.002055,
517
+ "tokens_per_second": 919970,
518
+ "minutes": 11.48,
519
+ "mfu_percent": 22.2,
520
+ "gpu_util_percent": 100,
521
+ "gpu_memory_gb": 79.1
522
+ },
523
+ {
524
+ "step": 2350,
525
+ "train_loss": 3.1278,
526
+ "lr": 0.00202,
527
+ "tokens_per_second": 919468,
528
+ "minutes": 11.72,
529
+ "mfu_percent": 22.2,
530
+ "gpu_util_percent": 100,
531
+ "gpu_memory_gb": 79.1
532
+ },
533
+ {
534
+ "step": 2400,
535
+ "train_loss": 3.1516,
536
+ "lr": 0.001984,
537
+ "tokens_per_second": 919200,
538
+ "minutes": 11.96,
539
+ "mfu_percent": 22.2,
540
+ "gpu_util_percent": 100,
541
+ "gpu_memory_gb": 79.1
542
+ },
543
+ {
544
+ "step": 2450,
545
+ "train_loss": 3.1655,
546
+ "lr": 0.001948,
547
+ "tokens_per_second": 918867,
548
+ "minutes": 12.2,
549
+ "mfu_percent": 22.2,
550
+ "gpu_util_percent": 100,
551
+ "gpu_memory_gb": 79.1
552
+ },
553
+ {
554
+ "step": 2500,
555
+ "train_loss": 3.1927,
556
+ "lr": 0.001911,
557
+ "tokens_per_second": 918862,
558
+ "minutes": 12.43,
559
+ "mfu_percent": 22.2,
560
+ "gpu_util_percent": 100,
561
+ "gpu_memory_gb": 79.1,
562
+ "val_loss": 3.1622
563
+ },
564
+ {
565
+ "step": 2550,
566
+ "train_loss": 3.1609,
567
+ "lr": 0.001875,
568
+ "tokens_per_second": 918878,
569
+ "minutes": 12.72,
570
+ "mfu_percent": 22.2,
571
+ "gpu_util_percent": 100,
572
+ "gpu_memory_gb": 79.1
573
+ },
574
+ {
575
+ "step": 2600,
576
+ "train_loss": 3.1732,
577
+ "lr": 0.001838,
578
+ "tokens_per_second": 919151,
579
+ "minutes": 12.96,
580
+ "mfu_percent": 22.2,
581
+ "gpu_util_percent": 100,
582
+ "gpu_memory_gb": 79.1
583
+ },
584
+ {
585
+ "step": 2650,
586
+ "train_loss": 3.0875,
587
+ "lr": 0.001801,
588
+ "tokens_per_second": 919485,
589
+ "minutes": 13.19,
590
+ "mfu_percent": 22.2,
591
+ "gpu_util_percent": 100,
592
+ "gpu_memory_gb": 79.1
593
+ },
594
+ {
595
+ "step": 2700,
596
+ "train_loss": 3.1417,
597
+ "lr": 0.001764,
598
+ "tokens_per_second": 919430,
599
+ "minutes": 13.43,
600
+ "mfu_percent": 22.2,
601
+ "gpu_util_percent": 100,
602
+ "gpu_memory_gb": 79.1
603
+ },
604
+ {
605
+ "step": 2750,
606
+ "train_loss": 3.1589,
607
+ "lr": 0.001727,
608
+ "tokens_per_second": 919254,
609
+ "minutes": 13.67,
610
+ "mfu_percent": 22.2,
611
+ "gpu_util_percent": 100,
612
+ "gpu_memory_gb": 79.1
613
+ },
614
+ {
615
+ "step": 2800,
616
+ "train_loss": 3.052,
617
+ "lr": 0.00169,
618
+ "tokens_per_second": 919224,
619
+ "minutes": 13.91,
620
+ "mfu_percent": 22.2,
621
+ "gpu_util_percent": 100,
622
+ "gpu_memory_gb": 79.1
623
+ },
624
+ {
625
+ "step": 2850,
626
+ "train_loss": 3.0945,
627
+ "lr": 0.001653,
628
+ "tokens_per_second": 919252,
629
+ "minutes": 14.14,
630
+ "mfu_percent": 22.2,
631
+ "gpu_util_percent": 100,
632
+ "gpu_memory_gb": 79.1
633
+ },
634
+ {
635
+ "step": 2900,
636
+ "train_loss": 3.0436,
637
+ "lr": 0.001616,
638
+ "tokens_per_second": 919765,
639
+ "minutes": 14.38,
640
+ "mfu_percent": 22.2,
641
+ "gpu_util_percent": 100,
642
+ "gpu_memory_gb": 79.1
643
+ },
644
+ {
645
+ "step": 2950,
646
+ "train_loss": 3.0525,
647
+ "lr": 0.001579,
648
+ "tokens_per_second": 919937,
649
+ "minutes": 14.62,
650
+ "mfu_percent": 22.2,
651
+ "gpu_util_percent": 100,
652
+ "gpu_memory_gb": 79.1
653
+ },
654
+ {
655
+ "step": 3000,
656
+ "train_loss": 3.019,
657
+ "lr": 0.001542,
658
+ "tokens_per_second": 919762,
659
+ "minutes": 14.86,
660
+ "mfu_percent": 22.2,
661
+ "gpu_util_percent": 100,
662
+ "gpu_memory_gb": 79.1,
663
+ "val_loss": 3.116
664
+ },
665
+ {
666
+ "step": 3050,
667
+ "train_loss": 3.13,
668
+ "lr": 0.001505,
669
+ "tokens_per_second": 920124,
670
+ "minutes": 15.14,
671
+ "mfu_percent": 22.2,
672
+ "gpu_util_percent": 100,
673
+ "gpu_memory_gb": 79.1
674
+ },
675
+ {
676
+ "step": 3100,
677
+ "train_loss": 3.0723,
678
+ "lr": 0.001468,
679
+ "tokens_per_second": 920009,
680
+ "minutes": 15.38,
681
+ "mfu_percent": 22.2,
682
+ "gpu_util_percent": 100,
683
+ "gpu_memory_gb": 79.1
684
+ },
685
+ {
686
+ "step": 3150,
687
+ "train_loss": 3.0721,
688
+ "lr": 0.001431,
689
+ "tokens_per_second": 919773,
690
+ "minutes": 15.62,
691
+ "mfu_percent": 22.2,
692
+ "gpu_util_percent": 100,
693
+ "gpu_memory_gb": 79.1
694
+ },
695
+ {
696
+ "step": 3200,
697
+ "train_loss": 3.082,
698
+ "lr": 0.001395,
699
+ "tokens_per_second": 919868,
700
+ "minutes": 15.85,
701
+ "mfu_percent": 22.2,
702
+ "gpu_util_percent": 100,
703
+ "gpu_memory_gb": 79.1
704
+ },
705
+ {
706
+ "step": 3250,
707
+ "train_loss": 3.1011,
708
+ "lr": 0.001358,
709
+ "tokens_per_second": 920018,
710
+ "minutes": 16.09,
711
+ "mfu_percent": 22.2,
712
+ "gpu_util_percent": 100,
713
+ "gpu_memory_gb": 79.1
714
+ },
715
+ {
716
+ "step": 3300,
717
+ "train_loss": 3.0397,
718
+ "lr": 0.001322,
719
+ "tokens_per_second": 919962,
720
+ "minutes": 16.33,
721
+ "mfu_percent": 22.2,
722
+ "gpu_util_percent": 100,
723
+ "gpu_memory_gb": 79.1
724
+ },
725
+ {
726
+ "step": 3350,
727
+ "train_loss": 3.0473,
728
+ "lr": 0.001286,
729
+ "tokens_per_second": 919990,
730
+ "minutes": 16.57,
731
+ "mfu_percent": 22.2,
732
+ "gpu_util_percent": 100,
733
+ "gpu_memory_gb": 79.1
734
+ },
735
+ {
736
+ "step": 3400,
737
+ "train_loss": 3.0615,
738
+ "lr": 0.001251,
739
+ "tokens_per_second": 923200,
740
+ "minutes": 16.8,
741
+ "mfu_percent": 22.3,
742
+ "gpu_util_percent": 100,
743
+ "gpu_memory_gb": 79.1
744
+ },
745
+ {
746
+ "step": 3450,
747
+ "train_loss": 3.0738,
748
+ "lr": 0.001215,
749
+ "tokens_per_second": 926033,
750
+ "minutes": 17.04,
751
+ "mfu_percent": 22.3,
752
+ "gpu_util_percent": 100,
753
+ "gpu_memory_gb": 79.1
754
+ },
755
+ {
756
+ "step": 3500,
757
+ "train_loss": 2.991,
758
+ "lr": 0.00118,
759
+ "tokens_per_second": 925099,
760
+ "minutes": 17.27,
761
+ "mfu_percent": 22.3,
762
+ "gpu_util_percent": 100,
763
+ "gpu_memory_gb": 79.1,
764
+ "val_loss": 3.0811
765
+ },
766
+ {
767
+ "step": 3550,
768
+ "train_loss": 3.0385,
769
+ "lr": 0.001146,
770
+ "tokens_per_second": 924905,
771
+ "minutes": 17.56,
772
+ "mfu_percent": 22.3,
773
+ "gpu_util_percent": 100,
774
+ "gpu_memory_gb": 79.1
775
+ },
776
+ {
777
+ "step": 3600,
778
+ "train_loss": 3.0725,
779
+ "lr": 0.001111,
780
+ "tokens_per_second": 924717,
781
+ "minutes": 17.79,
782
+ "mfu_percent": 22.3,
783
+ "gpu_util_percent": 100,
784
+ "gpu_memory_gb": 79.1
785
+ },
786
+ {
787
+ "step": 3650,
788
+ "train_loss": 3.0169,
789
+ "lr": 0.001077,
790
+ "tokens_per_second": 925574,
791
+ "minutes": 18.03,
792
+ "mfu_percent": 22.3,
793
+ "gpu_util_percent": 100,
794
+ "gpu_memory_gb": 79.1
795
+ },
796
+ {
797
+ "step": 3700,
798
+ "train_loss": 3.0391,
799
+ "lr": 0.001044,
800
+ "tokens_per_second": 926820,
801
+ "minutes": 18.27,
802
+ "mfu_percent": 22.3,
803
+ "gpu_util_percent": 100,
804
+ "gpu_memory_gb": 79.1
805
+ },
806
+ {
807
+ "step": 3750,
808
+ "train_loss": 3.0948,
809
+ "lr": 0.001011,
810
+ "tokens_per_second": 926733,
811
+ "minutes": 18.5,
812
+ "mfu_percent": 22.3,
813
+ "gpu_util_percent": 100,
814
+ "gpu_memory_gb": 79.1
815
+ },
816
+ {
817
+ "step": 3800,
818
+ "train_loss": 3.0155,
819
+ "lr": 0.000979,
820
+ "tokens_per_second": 926219,
821
+ "minutes": 18.74,
822
+ "mfu_percent": 22.3,
823
+ "gpu_util_percent": 100,
824
+ "gpu_memory_gb": 79.1
825
+ },
826
+ {
827
+ "step": 3850,
828
+ "train_loss": 3.0926,
829
+ "lr": 0.000947,
830
+ "tokens_per_second": 924590,
831
+ "minutes": 18.97,
832
+ "mfu_percent": 22.3,
833
+ "gpu_util_percent": 100,
834
+ "gpu_memory_gb": 79.1
835
+ },
836
+ {
837
+ "step": 3900,
838
+ "train_loss": 3.0346,
839
+ "lr": 0.000915,
840
+ "tokens_per_second": 924607,
841
+ "minutes": 19.21,
842
+ "mfu_percent": 22.3,
843
+ "gpu_util_percent": 100,
844
+ "gpu_memory_gb": 79.1
845
+ },
846
+ {
847
+ "step": 3950,
848
+ "train_loss": 3.0385,
849
+ "lr": 0.000884,
850
+ "tokens_per_second": 923474,
851
+ "minutes": 19.45,
852
+ "mfu_percent": 22.3,
853
+ "gpu_util_percent": 100,
854
+ "gpu_memory_gb": 79.1
855
+ },
856
+ {
857
+ "step": 4000,
858
+ "train_loss": 2.9716,
859
+ "lr": 0.000854,
860
+ "tokens_per_second": 922129,
861
+ "minutes": 19.68,
862
+ "mfu_percent": 22.2,
863
+ "gpu_util_percent": 100,
864
+ "gpu_memory_gb": 79.1,
865
+ "val_loss": 3.0478
866
+ },
867
+ {
868
+ "step": 4050,
869
+ "train_loss": 2.9443,
870
+ "lr": 0.000824,
871
+ "tokens_per_second": 920762,
872
+ "minutes": 19.97,
873
+ "mfu_percent": 22.2,
874
+ "gpu_util_percent": 100,
875
+ "gpu_memory_gb": 79.1
876
+ },
877
+ {
878
+ "step": 4100,
879
+ "train_loss": 2.9772,
880
+ "lr": 0.000795,
881
+ "tokens_per_second": 920133,
882
+ "minutes": 20.2,
883
+ "mfu_percent": 22.2,
884
+ "gpu_util_percent": 100,
885
+ "gpu_memory_gb": 79.1
886
+ },
887
+ {
888
+ "step": 4150,
889
+ "train_loss": 3.0015,
890
+ "lr": 0.000767,
891
+ "tokens_per_second": 919900,
892
+ "minutes": 20.44,
893
+ "mfu_percent": 22.2,
894
+ "gpu_util_percent": 100,
895
+ "gpu_memory_gb": 79.1
896
+ },
897
+ {
898
+ "step": 4200,
899
+ "train_loss": 3.0204,
900
+ "lr": 0.000739,
901
+ "tokens_per_second": 920172,
902
+ "minutes": 20.68,
903
+ "mfu_percent": 22.2,
904
+ "gpu_util_percent": 100,
905
+ "gpu_memory_gb": 79.1
906
+ },
907
+ {
908
+ "step": 4250,
909
+ "train_loss": 3.0105,
910
+ "lr": 0.000712,
911
+ "tokens_per_second": 923826,
912
+ "minutes": 20.92,
913
+ "mfu_percent": 22.3,
914
+ "gpu_util_percent": 100,
915
+ "gpu_memory_gb": 79.1
916
+ },
917
+ {
918
+ "step": 4300,
919
+ "train_loss": 3.0586,
920
+ "lr": 0.000686,
921
+ "tokens_per_second": 926224,
922
+ "minutes": 21.15,
923
+ "mfu_percent": 22.3,
924
+ "gpu_util_percent": 100,
925
+ "gpu_memory_gb": 79.1
926
+ },
927
+ {
928
+ "step": 4350,
929
+ "train_loss": 3.0093,
930
+ "lr": 0.00066,
931
+ "tokens_per_second": 925730,
932
+ "minutes": 21.39,
933
+ "mfu_percent": 22.3,
934
+ "gpu_util_percent": 100,
935
+ "gpu_memory_gb": 79.1
936
+ },
937
+ {
938
+ "step": 4400,
939
+ "train_loss": 3.0369,
940
+ "lr": 0.000635,
941
+ "tokens_per_second": 926216,
942
+ "minutes": 21.62,
943
+ "mfu_percent": 22.3,
944
+ "gpu_util_percent": 100,
945
+ "gpu_memory_gb": 79.1
946
+ },
947
+ {
948
+ "step": 4450,
949
+ "train_loss": 2.9631,
950
+ "lr": 0.000611,
951
+ "tokens_per_second": 926599,
952
+ "minutes": 21.86,
953
+ "mfu_percent": 22.3,
954
+ "gpu_util_percent": 100,
955
+ "gpu_memory_gb": 79.1
956
+ },
957
+ {
958
+ "step": 4500,
959
+ "train_loss": 3.0019,
960
+ "lr": 0.000588,
961
+ "tokens_per_second": 925142,
962
+ "minutes": 22.1,
963
+ "mfu_percent": 22.3,
964
+ "gpu_util_percent": 100,
965
+ "gpu_memory_gb": 79.1,
966
+ "val_loss": 3.0207
967
+ },
968
+ {
969
+ "step": 4550,
970
+ "train_loss": 2.963,
971
+ "lr": 0.000565,
972
+ "tokens_per_second": 923970,
973
+ "minutes": 22.38,
974
+ "mfu_percent": 22.3,
975
+ "gpu_util_percent": 100,
976
+ "gpu_memory_gb": 79.1
977
+ },
978
+ {
979
+ "step": 4600,
980
+ "train_loss": 3.0014,
981
+ "lr": 0.000544,
982
+ "tokens_per_second": 924314,
983
+ "minutes": 22.62,
984
+ "mfu_percent": 22.3,
985
+ "gpu_util_percent": 100,
986
+ "gpu_memory_gb": 79.1
987
+ },
988
+ {
989
+ "step": 4650,
990
+ "train_loss": 3.0158,
991
+ "lr": 0.000523,
992
+ "tokens_per_second": 926032,
993
+ "minutes": 22.85,
994
+ "mfu_percent": 22.3,
995
+ "gpu_util_percent": 100,
996
+ "gpu_memory_gb": 79.1
997
+ },
998
+ {
999
+ "step": 4700,
1000
+ "train_loss": 2.9781,
1001
+ "lr": 0.000503,
1002
+ "tokens_per_second": 926272,
1003
+ "minutes": 23.09,
1004
+ "mfu_percent": 22.3,
1005
+ "gpu_util_percent": 100,
1006
+ "gpu_memory_gb": 79.1
1007
+ },
1008
+ {
1009
+ "step": 4750,
1010
+ "train_loss": 3.0033,
1011
+ "lr": 0.000484,
1012
+ "tokens_per_second": 926281,
1013
+ "minutes": 23.32,
1014
+ "mfu_percent": 22.3,
1015
+ "gpu_util_percent": 100,
1016
+ "gpu_memory_gb": 79.1
1017
+ },
1018
+ {
1019
+ "step": 4800,
1020
+ "train_loss": 2.9712,
1021
+ "lr": 0.000465,
1022
+ "tokens_per_second": 925900,
1023
+ "minutes": 23.56,
1024
+ "mfu_percent": 22.3,
1025
+ "gpu_util_percent": 100,
1026
+ "gpu_memory_gb": 79.1
1027
+ },
1028
+ {
1029
+ "step": 4850,
1030
+ "train_loss": 2.9531,
1031
+ "lr": 0.000448,
1032
+ "tokens_per_second": 925757,
1033
+ "minutes": 23.79,
1034
+ "mfu_percent": 22.3,
1035
+ "gpu_util_percent": 100,
1036
+ "gpu_memory_gb": 79.1
1037
+ },
1038
+ {
1039
+ "step": 4900,
1040
+ "train_loss": 2.995,
1041
+ "lr": 0.000432,
1042
+ "tokens_per_second": 925796,
1043
+ "minutes": 24.03,
1044
+ "mfu_percent": 22.3,
1045
+ "gpu_util_percent": 100,
1046
+ "gpu_memory_gb": 79.1
1047
+ },
1048
+ {
1049
+ "step": 4950,
1050
+ "train_loss": 2.9912,
1051
+ "lr": 0.000416,
1052
+ "tokens_per_second": 925597,
1053
+ "minutes": 24.27,
1054
+ "mfu_percent": 22.3,
1055
+ "gpu_util_percent": 100,
1056
+ "gpu_memory_gb": 79.1
1057
+ },
1058
+ {
1059
+ "step": 5000,
1060
+ "train_loss": 2.9481,
1061
+ "lr": 0.000401,
1062
+ "tokens_per_second": 925036,
1063
+ "minutes": 24.5,
1064
+ "mfu_percent": 22.3,
1065
+ "gpu_util_percent": 100,
1066
+ "gpu_memory_gb": 79.1,
1067
+ "val_loss": 3.0002
1068
+ },
1069
+ {
1070
+ "step": 5050,
1071
+ "train_loss": 3.0146,
1072
+ "lr": 0.000388,
1073
+ "tokens_per_second": 924886,
1074
+ "minutes": 24.79,
1075
+ "mfu_percent": 22.3,
1076
+ "gpu_util_percent": 100,
1077
+ "gpu_memory_gb": 79.1
1078
+ },
1079
+ {
1080
+ "step": 5100,
1081
+ "train_loss": 2.9885,
1082
+ "lr": 0.000375,
1083
+ "tokens_per_second": 924816,
1084
+ "minutes": 25.02,
1085
+ "mfu_percent": 22.3,
1086
+ "gpu_util_percent": 100,
1087
+ "gpu_memory_gb": 79.1
1088
+ },
1089
+ {
1090
+ "step": 5150,
1091
+ "train_loss": 3.0184,
1092
+ "lr": 0.000363,
1093
+ "tokens_per_second": 924852,
1094
+ "minutes": 25.26,
1095
+ "mfu_percent": 22.3,
1096
+ "gpu_util_percent": 100,
1097
+ "gpu_memory_gb": 79.1
1098
+ },
1099
+ {
1100
+ "step": 5200,
1101
+ "train_loss": 2.9669,
1102
+ "lr": 0.000353,
1103
+ "tokens_per_second": 925481,
1104
+ "minutes": 25.5,
1105
+ "mfu_percent": 22.3,
1106
+ "gpu_util_percent": 100,
1107
+ "gpu_memory_gb": 79.1
1108
+ },
1109
+ {
1110
+ "step": 5250,
1111
+ "train_loss": 2.9598,
1112
+ "lr": 0.000343,
1113
+ "tokens_per_second": 926674,
1114
+ "minutes": 25.73,
1115
+ "mfu_percent": 22.3,
1116
+ "gpu_util_percent": 100,
1117
+ "gpu_memory_gb": 79.1
1118
+ },
1119
+ {
1120
+ "step": 5300,
1121
+ "train_loss": 2.9644,
1122
+ "lr": 0.000334,
1123
+ "tokens_per_second": 926065,
1124
+ "minutes": 25.97,
1125
+ "mfu_percent": 22.3,
1126
+ "gpu_util_percent": 100,
1127
+ "gpu_memory_gb": 79.1
1128
+ },
1129
+ {
1130
+ "step": 5350,
1131
+ "train_loss": 2.9615,
1132
+ "lr": 0.000326,
1133
+ "tokens_per_second": 926198,
1134
+ "minutes": 26.2,
1135
+ "mfu_percent": 22.3,
1136
+ "gpu_util_percent": 100,
1137
+ "gpu_memory_gb": 79.1
1138
+ },
1139
+ {
1140
+ "step": 5400,
1141
+ "train_loss": 2.9874,
1142
+ "lr": 0.000319,
1143
+ "tokens_per_second": 926366,
1144
+ "minutes": 26.44,
1145
+ "mfu_percent": 22.3,
1146
+ "gpu_util_percent": 100,
1147
+ "gpu_memory_gb": 79.1
1148
+ },
1149
+ {
1150
+ "step": 5450,
1151
+ "train_loss": 2.9591,
1152
+ "lr": 0.000314,
1153
+ "tokens_per_second": 926756,
1154
+ "minutes": 26.67,
1155
+ "mfu_percent": 22.3,
1156
+ "gpu_util_percent": 100,
1157
+ "gpu_memory_gb": 79.1
1158
+ },
1159
+ {
1160
+ "step": 5500,
1161
+ "train_loss": 2.9528,
1162
+ "lr": 0.000309,
1163
+ "tokens_per_second": 925140,
1164
+ "minutes": 26.91,
1165
+ "mfu_percent": 22.3,
1166
+ "gpu_util_percent": 100,
1167
+ "gpu_memory_gb": 79.1,
1168
+ "val_loss": 2.9883
1169
+ },
1170
+ {
1171
+ "step": 5550,
1172
+ "train_loss": 3.0098,
1173
+ "lr": 0.000305,
1174
+ "tokens_per_second": 925097,
1175
+ "minutes": 27.19,
1176
+ "mfu_percent": 22.3,
1177
+ "gpu_util_percent": 100,
1178
+ "gpu_memory_gb": 79.1
1179
+ },
1180
+ {
1181
+ "step": 5600,
1182
+ "train_loss": 3.0141,
1183
+ "lr": 0.000302,
1184
+ "tokens_per_second": 925982,
1185
+ "minutes": 27.43,
1186
+ "mfu_percent": 22.3,
1187
+ "gpu_util_percent": 100,
1188
+ "gpu_memory_gb": 79.1
1189
+ },
1190
+ {
1191
+ "step": 5650,
1192
+ "train_loss": 2.9269,
1193
+ "lr": 0.000301,
1194
+ "tokens_per_second": 927048,
1195
+ "minutes": 27.67,
1196
+ "mfu_percent": 22.4,
1197
+ "gpu_util_percent": 100,
1198
+ "gpu_memory_gb": 79.1
1199
+ },
1200
+ {
1201
+ "step": 5700,
1202
+ "train_loss": 2.9439,
1203
+ "lr": 0.0003,
1204
+ "tokens_per_second": 926122,
1205
+ "minutes": 27.9,
1206
+ "mfu_percent": 22.3,
1207
+ "gpu_util_percent": 100,
1208
+ "gpu_memory_gb": 79.1
1209
+ },
1210
+ {
1211
+ "step": 5709,
1212
+ "train_loss": 2.969,
1213
+ "lr": 0.0003,
1214
+ "tokens_per_second": 925339,
1215
+ "minutes": 27.94,
1216
+ "mfu_percent": 22.3,
1217
+ "gpu_util_percent": 100,
1218
+ "gpu_memory_gb": 79.1,
1219
+ "val_loss": 2.9852
1220
+ }
1221
+ ],
1222
+ "exports": {
1223
+ "float": {
1224
+ "megabytes": 60.81,
1225
+ "same_top_token": true,
1226
+ "cached_step_ms_p50_cpu": 2.882
1227
+ },
1228
+ "int8": {
1229
+ "megabytes": 23.33,
1230
+ "same_top_token": false,
1231
+ "cached_step_ms_p50_cpu": 2.125
1232
+ }
1233
+ }
1234
+ }
v2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff