Hugging Face's logo

qingy2024
/
Gradience-T1-7B-checkpoint

PEFT
Safetensors
Model card Files
xet
Community
1
qingy2024 commited on
Commit
42f5ab7
·
verified ·
1 Parent(s): c64a1ae

Upload checkpoint 100

Browse files
Files changed (8) hide show
  1. .gitattributes +1 -0
  2. README.md +50 -0
  3. adapter_config.json +1 -1
  4. loss.png +3 -0
  5. optimizer.pt +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. trainer_state.json +734 -0
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ loss.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-Instruct
3
+ library_name: peft
4
+ ---
5
+ # Gradience T1 7B (Step 100 Checkpoint)
6
+
7
+ > [!NOTE]
8
+ > Training in progress...
9
+
10
+ <!DOCTYPE html>
11
+ <html lang="en">
12
+ <head>
13
+ <meta charset="UTF-8">
14
+ <title>Progress Bar Example</title>
15
+ <style>
16
+ .progress-container {
17
+ width: 100%;
18
+ background-color: #e0e0e0;
19
+ border-radius: 25px;
20
+ overflow: hidden;
21
+ margin: 20px 0;
22
+ }
23
+ .progress-bar {
24
+ height: 30px;
25
+ width: 0;
26
+ background-color: #44965a;
27
+ text-align: center;
28
+ line-height: 30px;
29
+ color: white;
30
+ border-radius: 25px 0 0 25px;
31
+ }
32
+ .progress-text {
33
+ margin-top: 10px;
34
+ font-size: 16px;
35
+ font-family: Arial, sans-serif;
36
+ }
37
+ </style>
38
+ </head>
39
+ <body>
40
+ <div style="width: 100%; background-color: #e0e0e0; border-radius: 25px; overflow: hidden; margin: 20px 0;">
41
+ <div style="height: 30px; width: 2.03%; background-color: #76c7c0; text-align: center; line-height: 30px; color: white; border-radius: 25px 0 0 25px;">
42
+ <!-- 2.03% -->
43
+ </div>
44
+ </div>
45
+ <p style="font-family: Arial, sans-serif; font-size: 16px;">Progress: 100 out of 4918 steps</p>
46
+ </body>
47
+ </html>
48
+
49
+ ## Training Loss
50
+ ![Training Loss Chart](loss.png)
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "./Qwen-2.5-7B-Instruct",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
loss.png ADDED

Git LFS Details

  • SHA256: 8501a433dfcf414b32f78cccb3ac60df9ab87df21749dfe16f65f786d4d40789
  • Pointer size: 131 Bytes
  • Size of remote file: 119 kB
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7145c19acaa434746f69007c984cb4fcafd82d83c7db6f41530135117930cb3
3
+ size 82460660
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:608fccb6c056ce88cdfd5355e6be2046f4d107a24a87c6b0d2c3b200ce6bb4ea
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da86d96d5e8283f1822f3d593be5e334f336f6576f11a726b2db42770e20bc22
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.04065867046147591,
6
+ "eval_steps": 500,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0004065867046147591,
14
+ "grad_norm": 0.22144322097301483,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.3598,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0008131734092295182,
21
+ "grad_norm": 0.199473574757576,
22
+ "learning_rate": 4e-05,
23
+ "loss": 1.405,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0012197601138442774,
28
+ "grad_norm": 0.20758001506328583,
29
+ "learning_rate": 8e-05,
30
+ "loss": 1.2815,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0016263468184590363,
35
+ "grad_norm": 0.21362783014774323,
36
+ "learning_rate": 0.00012,
37
+ "loss": 1.245,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.0020329335230737954,
42
+ "grad_norm": 0.24631692469120026,
43
+ "learning_rate": 0.00016,
44
+ "loss": 1.3086,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.002439520227688555,
49
+ "grad_norm": 0.20009225606918335,
50
+ "learning_rate": 0.0002,
51
+ "loss": 1.2443,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0028461069323033137,
56
+ "grad_norm": 0.1735246330499649,
57
+ "learning_rate": 0.00019995929167514756,
58
+ "loss": 1.1878,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0032526936369180726,
63
+ "grad_norm": 0.18904437124729156,
64
+ "learning_rate": 0.00019991858335029514,
65
+ "loss": 1.2478,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.003659280341532832,
70
+ "grad_norm": 0.1645248979330063,
71
+ "learning_rate": 0.0001998778750254427,
72
+ "loss": 1.2098,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.004065867046147591,
77
+ "grad_norm": 0.22034819424152374,
78
+ "learning_rate": 0.00019983716670059028,
79
+ "loss": 1.1183,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.00447245375076235,
84
+ "grad_norm": 0.3233634829521179,
85
+ "learning_rate": 0.00019979645837573783,
86
+ "loss": 1.0974,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.00487904045537711,
91
+ "grad_norm": 0.2592090368270874,
92
+ "learning_rate": 0.00019975575005088542,
93
+ "loss": 1.1611,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.005285627159991868,
98
+ "grad_norm": 0.14754348993301392,
99
+ "learning_rate": 0.000199715041726033,
100
+ "loss": 1.1932,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.005692213864606627,
105
+ "grad_norm": 0.09341374039649963,
106
+ "learning_rate": 0.00019967433340118055,
107
+ "loss": 1.348,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.006098800569221387,
112
+ "grad_norm": 0.10229193419218063,
113
+ "learning_rate": 0.00019963362507632813,
114
+ "loss": 1.0927,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.006505387273836145,
119
+ "grad_norm": 0.14015386998653412,
120
+ "learning_rate": 0.00019959291675147569,
121
+ "loss": 1.2263,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.006911973978450905,
126
+ "grad_norm": 0.17507047951221466,
127
+ "learning_rate": 0.00019955220842662327,
128
+ "loss": 1.1951,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.007318560683065664,
133
+ "grad_norm": 0.17176274955272675,
134
+ "learning_rate": 0.00019951150010177082,
135
+ "loss": 1.1895,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.007725147387680423,
140
+ "grad_norm": 0.13839803636074066,
141
+ "learning_rate": 0.00019947079177691838,
142
+ "loss": 0.9549,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.008131734092295182,
147
+ "grad_norm": 0.0970696285367012,
148
+ "learning_rate": 0.00019943008345206596,
149
+ "loss": 1.0867,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.008538320796909941,
154
+ "grad_norm": 0.08836886286735535,
155
+ "learning_rate": 0.0001993893751272135,
156
+ "loss": 1.155,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.0089449075015247,
161
+ "grad_norm": 0.11885025352239609,
162
+ "learning_rate": 0.0001993486668023611,
163
+ "loss": 1.1231,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.00935149420613946,
168
+ "grad_norm": 0.15120816230773926,
169
+ "learning_rate": 0.00019930795847750865,
170
+ "loss": 1.1078,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.00975808091075422,
175
+ "grad_norm": 0.16326424479484558,
176
+ "learning_rate": 0.00019926725015265623,
177
+ "loss": 1.079,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.010164667615368977,
182
+ "grad_norm": 0.1179085448384285,
183
+ "learning_rate": 0.0001992265418278038,
184
+ "loss": 0.932,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.010571254319983736,
189
+ "grad_norm": 0.10621985793113708,
190
+ "learning_rate": 0.00019918583350295136,
191
+ "loss": 1.1386,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.010977841024598495,
196
+ "grad_norm": 0.08408638089895248,
197
+ "learning_rate": 0.00019914512517809894,
198
+ "loss": 1.0987,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.011384427729213255,
203
+ "grad_norm": 0.08222135156393051,
204
+ "learning_rate": 0.0001991044168532465,
205
+ "loss": 1.0378,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.011791014433828014,
210
+ "grad_norm": 0.08763129264116287,
211
+ "learning_rate": 0.00019906370852839408,
212
+ "loss": 0.983,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.012197601138442773,
217
+ "grad_norm": 0.10638878494501114,
218
+ "learning_rate": 0.00019902300020354163,
219
+ "loss": 1.0258,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.012604187843057533,
224
+ "grad_norm": 0.10155023634433746,
225
+ "learning_rate": 0.0001989822918786892,
226
+ "loss": 0.9579,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.01301077454767229,
231
+ "grad_norm": 0.08844579011201859,
232
+ "learning_rate": 0.00019894158355383677,
233
+ "loss": 1.1007,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.01341736125228705,
238
+ "grad_norm": 0.10394158959388733,
239
+ "learning_rate": 0.00019890087522898432,
240
+ "loss": 1.0459,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.01382394795690181,
245
+ "grad_norm": 0.08938682824373245,
246
+ "learning_rate": 0.0001988601669041319,
247
+ "loss": 1.0985,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.014230534661516568,
252
+ "grad_norm": 0.08639086782932281,
253
+ "learning_rate": 0.00019881945857927948,
254
+ "loss": 1.0712,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.014637121366131328,
259
+ "grad_norm": 0.08568435162305832,
260
+ "learning_rate": 0.00019877875025442704,
261
+ "loss": 1.0549,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.015043708070746087,
266
+ "grad_norm": 0.0859316885471344,
267
+ "learning_rate": 0.00019873804192957462,
268
+ "loss": 1.1042,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.015450294775360847,
273
+ "grad_norm": 0.09534381330013275,
274
+ "learning_rate": 0.00019869733360472217,
275
+ "loss": 1.0127,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.015856881479975604,
280
+ "grad_norm": 0.09103580564260483,
281
+ "learning_rate": 0.00019865662527986976,
282
+ "loss": 0.9347,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.016263468184590364,
287
+ "grad_norm": 0.0928095132112503,
288
+ "learning_rate": 0.0001986159169550173,
289
+ "loss": 1.0559,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.016670054889205123,
294
+ "grad_norm": 0.09370871633291245,
295
+ "learning_rate": 0.0001985752086301649,
296
+ "loss": 1.1473,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.017076641593819882,
301
+ "grad_norm": 0.07691123336553574,
302
+ "learning_rate": 0.00019853450030531244,
303
+ "loss": 1.0128,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.01748322829843464,
308
+ "grad_norm": 0.09201047569513321,
309
+ "learning_rate": 0.00019849379198046,
310
+ "loss": 1.1296,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.0178898150030494,
315
+ "grad_norm": 0.08490074425935745,
316
+ "learning_rate": 0.00019845308365560758,
317
+ "loss": 1.0444,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.01829640170766416,
322
+ "grad_norm": 0.08623114228248596,
323
+ "learning_rate": 0.00019841237533075513,
324
+ "loss": 1.066,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.01870298841227892,
329
+ "grad_norm": 0.09486474096775055,
330
+ "learning_rate": 0.00019837166700590271,
331
+ "loss": 1.0788,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.01910957511689368,
336
+ "grad_norm": 0.08024484664201736,
337
+ "learning_rate": 0.0001983309586810503,
338
+ "loss": 1.0262,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.01951616182150844,
343
+ "grad_norm": 0.09256327897310257,
344
+ "learning_rate": 0.00019829025035619785,
345
+ "loss": 1.107,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.019922748526123194,
350
+ "grad_norm": 0.09877921640872955,
351
+ "learning_rate": 0.00019824954203134543,
352
+ "loss": 1.1731,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.020329335230737954,
357
+ "grad_norm": 0.08699575811624527,
358
+ "learning_rate": 0.00019820883370649299,
359
+ "loss": 1.0809,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.020735921935352713,
364
+ "grad_norm": 0.089649498462677,
365
+ "learning_rate": 0.00019816812538164057,
366
+ "loss": 1.1564,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.021142508639967472,
371
+ "grad_norm": 0.08757214993238449,
372
+ "learning_rate": 0.00019812741705678812,
373
+ "loss": 1.0272,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.02154909534458223,
378
+ "grad_norm": 0.08320939540863037,
379
+ "learning_rate": 0.0001980867087319357,
380
+ "loss": 0.9931,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.02195568204919699,
385
+ "grad_norm": 0.08898070454597473,
386
+ "learning_rate": 0.00019804600040708326,
387
+ "loss": 0.9421,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.02236226875381175,
392
+ "grad_norm": 0.08072236180305481,
393
+ "learning_rate": 0.0001980052920822308,
394
+ "loss": 1.0304,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.02276885545842651,
399
+ "grad_norm": 0.09354112297296524,
400
+ "learning_rate": 0.0001979645837573784,
401
+ "loss": 1.1041,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.02317544216304127,
406
+ "grad_norm": 0.09214304387569427,
407
+ "learning_rate": 0.00019792387543252595,
408
+ "loss": 1.0666,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.02358202886765603,
413
+ "grad_norm": 0.08546210825443268,
414
+ "learning_rate": 0.00019788316710767353,
415
+ "loss": 1.0795,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.023988615572270788,
420
+ "grad_norm": 0.09029046446084976,
421
+ "learning_rate": 0.0001978424587828211,
422
+ "loss": 1.199,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.024395202276885547,
427
+ "grad_norm": 0.08200937509536743,
428
+ "learning_rate": 0.00019780175045796866,
429
+ "loss": 0.9853,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.024801788981500306,
434
+ "grad_norm": 0.08928566426038742,
435
+ "learning_rate": 0.00019776104213311624,
436
+ "loss": 0.9948,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.025208375686115066,
441
+ "grad_norm": 0.08067034929990768,
442
+ "learning_rate": 0.0001977203338082638,
443
+ "loss": 0.9824,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.02561496239072982,
448
+ "grad_norm": 0.07509499788284302,
449
+ "learning_rate": 0.00019767962548341138,
450
+ "loss": 0.9166,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.02602154909534458,
455
+ "grad_norm": 0.10127029567956924,
456
+ "learning_rate": 0.00019763891715855893,
457
+ "loss": 0.978,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.02642813579995934,
462
+ "grad_norm": 0.08480218052864075,
463
+ "learning_rate": 0.0001975982088337065,
464
+ "loss": 1.0019,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.0268347225045741,
469
+ "grad_norm": 0.0922696441411972,
470
+ "learning_rate": 0.00019755750050885407,
471
+ "loss": 1.0213,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.02724130920918886,
476
+ "grad_norm": 0.0819278433918953,
477
+ "learning_rate": 0.00019751679218400162,
478
+ "loss": 0.9792,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.02764789591380362,
483
+ "grad_norm": 0.09971120208501816,
484
+ "learning_rate": 0.0001974760838591492,
485
+ "loss": 0.9605,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.028054482618418378,
490
+ "grad_norm": 0.09195531904697418,
491
+ "learning_rate": 0.00019743537553429676,
492
+ "loss": 1.1203,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.028461069323033137,
497
+ "grad_norm": 0.09179981052875519,
498
+ "learning_rate": 0.00019739466720944434,
499
+ "loss": 1.0586,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.028867656027647896,
504
+ "grad_norm": 0.0866156816482544,
505
+ "learning_rate": 0.00019735395888459192,
506
+ "loss": 1.0558,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.029274242732262656,
511
+ "grad_norm": 0.09198956191539764,
512
+ "learning_rate": 0.00019731325055973947,
513
+ "loss": 1.117,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.029680829436877415,
518
+ "grad_norm": 0.0912180244922638,
519
+ "learning_rate": 0.00019727254223488705,
520
+ "loss": 1.0235,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.030087416141492174,
525
+ "grad_norm": 0.092186838388443,
526
+ "learning_rate": 0.0001972318339100346,
527
+ "loss": 1.0119,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.030494002846106934,
532
+ "grad_norm": 0.091013602912426,
533
+ "learning_rate": 0.0001971911255851822,
534
+ "loss": 1.0523,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.030900589550721693,
539
+ "grad_norm": 0.0932595282793045,
540
+ "learning_rate": 0.00019715041726032974,
541
+ "loss": 1.0471,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.03130717625533645,
546
+ "grad_norm": 0.089345782995224,
547
+ "learning_rate": 0.0001971097089354773,
548
+ "loss": 1.0214,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.03171376295995121,
553
+ "grad_norm": 0.09476006776094437,
554
+ "learning_rate": 0.00019706900061062488,
555
+ "loss": 0.9888,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.03212034966456597,
560
+ "grad_norm": 0.09379832446575165,
561
+ "learning_rate": 0.00019702829228577243,
562
+ "loss": 1.1039,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.03252693636918073,
567
+ "grad_norm": 0.10659569501876831,
568
+ "learning_rate": 0.00019698758396092001,
569
+ "loss": 1.1377,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.03293352307379549,
574
+ "grad_norm": 0.09652398526668549,
575
+ "learning_rate": 0.0001969468756360676,
576
+ "loss": 1.0194,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.033340109778410246,
581
+ "grad_norm": 0.08641666918992996,
582
+ "learning_rate": 0.00019690616731121515,
583
+ "loss": 1.0239,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.03374669648302501,
588
+ "grad_norm": 0.0956072062253952,
589
+ "learning_rate": 0.00019686545898636273,
590
+ "loss": 1.032,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.034153283187639764,
595
+ "grad_norm": 0.08402691036462784,
596
+ "learning_rate": 0.00019682475066151029,
597
+ "loss": 0.9802,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.03455986989225452,
602
+ "grad_norm": 0.08827648311853409,
603
+ "learning_rate": 0.00019678404233665787,
604
+ "loss": 1.1805,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.03496645659686928,
609
+ "grad_norm": 0.08757660537958145,
610
+ "learning_rate": 0.00019674333401180542,
611
+ "loss": 0.952,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.03537304330148404,
616
+ "grad_norm": 0.09728538244962692,
617
+ "learning_rate": 0.000196702625686953,
618
+ "loss": 1.0875,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.0357796300060988,
623
+ "grad_norm": 0.08561044931411743,
624
+ "learning_rate": 0.00019666191736210056,
625
+ "loss": 0.9818,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.03618621671071356,
630
+ "grad_norm": 0.08389468491077423,
631
+ "learning_rate": 0.0001966212090372481,
632
+ "loss": 0.9962,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.03659280341532832,
637
+ "grad_norm": 0.08847957849502563,
638
+ "learning_rate": 0.0001965805007123957,
639
+ "loss": 1.0138,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.036999390119943076,
644
+ "grad_norm": 0.08515489101409912,
645
+ "learning_rate": 0.00019653979238754324,
646
+ "loss": 1.0119,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.03740597682455784,
651
+ "grad_norm": 0.09340325742959976,
652
+ "learning_rate": 0.00019649908406269083,
653
+ "loss": 1.0635,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.037812563529172595,
658
+ "grad_norm": 0.09383916854858398,
659
+ "learning_rate": 0.0001964583757378384,
660
+ "loss": 1.0999,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.03821915023378736,
665
+ "grad_norm": 0.09956547617912292,
666
+ "learning_rate": 0.00019641766741298596,
667
+ "loss": 1.0186,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.038625736938402114,
672
+ "grad_norm": 0.09809234738349915,
673
+ "learning_rate": 0.00019637695908813354,
674
+ "loss": 1.0641,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.03903232364301688,
679
+ "grad_norm": 0.08520065993070602,
680
+ "learning_rate": 0.0001963362507632811,
681
+ "loss": 0.9255,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.03943891034763163,
686
+ "grad_norm": 0.09007880836725235,
687
+ "learning_rate": 0.00019629554243842868,
688
+ "loss": 1.0963,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.03984549705224639,
693
+ "grad_norm": 0.08900373429059982,
694
+ "learning_rate": 0.00019625483411357623,
695
+ "loss": 0.9908,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.04025208375686115,
700
+ "grad_norm": 0.09613076597452164,
701
+ "learning_rate": 0.0001962141257887238,
702
+ "loss": 0.9729,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.04065867046147591,
707
+ "grad_norm": 0.09987878054380417,
708
+ "learning_rate": 0.00019617341746387137,
709
+ "loss": 1.0554,
710
+ "step": 100
711
+ }
712
+ ],
713
+ "logging_steps": 1,
714
+ "max_steps": 4918,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 2,
717
+ "save_steps": 100,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": false
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 3.129379145742582e+17,
731
+ "train_batch_size": 16,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }