nthakur commited on
Commit
8f0db59
·
verified ·
1 Parent(s): 654b88f

Model save

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: mistralai/Mistral-7B-Instruct-v0.3
9
+ model-index:
10
+ - name: Mistral-7B-Instruct-v0.3-nomiracl-sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Mistral-7B-Instruct-v0.3-nomiracl-sft
18
+
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.4019
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 3e-06
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 32
47
+ - total_eval_batch_size: 32
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
+ | 1.4364 | 1.0 | 671 | 1.4019 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - PEFT 0.7.1
63
+ - Transformers 4.41.2
64
+ - Pytorch 2.3.0+cu121
65
+ - Datasets 2.20.0
66
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c4960f522e532b38996ebb94590e92ae12562d31b60ce56e4756e5b055a2a5a
3
  size 335605144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c03ff8f1418d08f977e5d22b53799262e06d27ab79cf28a25bbb2a8fa44057f
3
  size 335605144
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 2236028102377472.0,
4
+ "train_loss": 1.4386844755817987,
5
+ "train_runtime": 17062.4084,
6
+ "train_samples": 21471,
7
+ "train_samples_per_second": 1.258,
8
+ "train_steps_per_second": 0.039
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 2236028102377472.0,
4
+ "train_loss": 1.4386844755817987,
5
+ "train_runtime": 17062.4084,
6
+ "train_samples": 21471,
7
+ "train_samples_per_second": 1.258,
8
+ "train_steps_per_second": 0.039
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,995 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 671,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0014903129657228018,
13
+ "grad_norm": 0.7207538217956673,
14
+ "learning_rate": 4.411764705882353e-08,
15
+ "loss": 1.6077,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.007451564828614009,
20
+ "grad_norm": 0.65849854443806,
21
+ "learning_rate": 2.2058823529411765e-07,
22
+ "loss": 1.5945,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.014903129657228018,
27
+ "grad_norm": 0.6800875831730971,
28
+ "learning_rate": 4.411764705882353e-07,
29
+ "loss": 1.6315,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.022354694485842028,
34
+ "grad_norm": 0.8644630471455123,
35
+ "learning_rate": 6.61764705882353e-07,
36
+ "loss": 1.6271,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.029806259314456036,
41
+ "grad_norm": 0.7771872952949634,
42
+ "learning_rate": 8.823529411764706e-07,
43
+ "loss": 1.5795,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.037257824143070044,
48
+ "grad_norm": 0.7397975175907138,
49
+ "learning_rate": 1.1029411764705884e-06,
50
+ "loss": 1.6225,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.044709388971684055,
55
+ "grad_norm": 0.7702121293753343,
56
+ "learning_rate": 1.323529411764706e-06,
57
+ "loss": 1.6526,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.05216095380029806,
62
+ "grad_norm": 0.6644067274265962,
63
+ "learning_rate": 1.5441176470588234e-06,
64
+ "loss": 1.6006,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.05961251862891207,
69
+ "grad_norm": 0.6017633448350802,
70
+ "learning_rate": 1.7647058823529412e-06,
71
+ "loss": 1.6434,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.06706408345752608,
76
+ "grad_norm": 0.4509127973744261,
77
+ "learning_rate": 1.9852941176470586e-06,
78
+ "loss": 1.5392,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.07451564828614009,
83
+ "grad_norm": 0.4610064447084038,
84
+ "learning_rate": 2.2058823529411767e-06,
85
+ "loss": 1.589,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.08196721311475409,
90
+ "grad_norm": 0.35955958459549675,
91
+ "learning_rate": 2.4264705882352943e-06,
92
+ "loss": 1.5594,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.08941877794336811,
97
+ "grad_norm": 0.3478335776850152,
98
+ "learning_rate": 2.647058823529412e-06,
99
+ "loss": 1.5798,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.09687034277198212,
104
+ "grad_norm": 0.3527200373964567,
105
+ "learning_rate": 2.8676470588235296e-06,
106
+ "loss": 1.5693,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.10432190760059612,
111
+ "grad_norm": 0.29600438876672497,
112
+ "learning_rate": 2.999918570372821e-06,
113
+ "loss": 1.5045,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.11177347242921014,
118
+ "grad_norm": 0.2900544302757877,
119
+ "learning_rate": 2.9990025885979037e-06,
120
+ "loss": 1.483,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.11922503725782414,
125
+ "grad_norm": 0.2408233475597495,
126
+ "learning_rate": 2.997069461623824e-06,
127
+ "loss": 1.5672,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.12667660208643816,
132
+ "grad_norm": 0.28176854976259386,
133
+ "learning_rate": 2.9941205011700118e-06,
134
+ "loss": 1.5082,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.13412816691505217,
139
+ "grad_norm": 0.19913384731707087,
140
+ "learning_rate": 2.990157708247667e-06,
141
+ "loss": 1.4819,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.14157973174366617,
146
+ "grad_norm": 0.21083590352306433,
147
+ "learning_rate": 2.9851837718019762e-06,
148
+ "loss": 1.5531,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.14903129657228018,
153
+ "grad_norm": 0.20730699550159845,
154
+ "learning_rate": 2.9792020668875367e-06,
155
+ "loss": 1.481,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.15648286140089418,
160
+ "grad_norm": 0.18165412005960324,
161
+ "learning_rate": 2.9722166523782167e-06,
162
+ "loss": 1.4844,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.16393442622950818,
167
+ "grad_norm": 0.15838156755040073,
168
+ "learning_rate": 2.964232268213018e-06,
169
+ "loss": 1.4455,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.17138599105812222,
174
+ "grad_norm": 0.16340737391300794,
175
+ "learning_rate": 2.955254332179797e-06,
176
+ "loss": 1.469,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.17883755588673622,
181
+ "grad_norm": 0.14759052394480532,
182
+ "learning_rate": 2.9452889362390366e-06,
183
+ "loss": 1.5597,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.18628912071535023,
188
+ "grad_norm": 0.12914782899327282,
189
+ "learning_rate": 2.9343428423901614e-06,
190
+ "loss": 1.4765,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.19374068554396423,
195
+ "grad_norm": 0.12460225982681429,
196
+ "learning_rate": 2.9224234780831905e-06,
197
+ "loss": 1.4656,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.20119225037257824,
202
+ "grad_norm": 0.14217631629657101,
203
+ "learning_rate": 2.9095389311788626e-06,
204
+ "loss": 1.4872,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.20864381520119224,
209
+ "grad_norm": 0.1272863323148308,
210
+ "learning_rate": 2.8956979444606303e-06,
211
+ "loss": 1.4314,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.21609538002980627,
216
+ "grad_norm": 0.11983511963861297,
217
+ "learning_rate": 2.8809099097022624e-06,
218
+ "loss": 1.4734,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.22354694485842028,
223
+ "grad_norm": 0.12007606131316517,
224
+ "learning_rate": 2.8651848612950768e-06,
225
+ "loss": 1.4997,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.23099850968703428,
230
+ "grad_norm": 0.11593831929818996,
231
+ "learning_rate": 2.848533469439122e-06,
232
+ "loss": 1.3879,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.23845007451564829,
237
+ "grad_norm": 0.11598915986268504,
238
+ "learning_rate": 2.8309670329029358e-06,
239
+ "loss": 1.4192,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.2459016393442623,
244
+ "grad_norm": 0.11190528057252458,
245
+ "learning_rate": 2.8124974713567872e-06,
246
+ "loss": 1.452,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.2533532041728763,
251
+ "grad_norm": 0.1203691003615664,
252
+ "learning_rate": 2.79313731728461e-06,
253
+ "loss": 1.4819,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.2608047690014903,
258
+ "grad_norm": 0.10952238143478435,
259
+ "learning_rate": 2.772899707480108e-06,
260
+ "loss": 1.4173,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.26825633383010433,
265
+ "grad_norm": 0.10685505615273189,
266
+ "learning_rate": 2.7517983741328146e-06,
267
+ "loss": 1.4078,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.2757078986587183,
272
+ "grad_norm": 0.11464827031091669,
273
+ "learning_rate": 2.729847635510137e-06,
274
+ "loss": 1.5007,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.28315946348733234,
279
+ "grad_norm": 0.11122715995599067,
280
+ "learning_rate": 2.70706238624173e-06,
281
+ "loss": 1.4541,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.2906110283159464,
286
+ "grad_norm": 0.10752842550767219,
287
+ "learning_rate": 2.6834580872127733e-06,
288
+ "loss": 1.4129,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.29806259314456035,
293
+ "grad_norm": 0.11490358820200401,
294
+ "learning_rate": 2.6590507550730175e-06,
295
+ "loss": 1.3986,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.3055141579731744,
300
+ "grad_norm": 0.10706266255477938,
301
+ "learning_rate": 2.6338569513687182e-06,
302
+ "loss": 1.4404,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.31296572280178836,
307
+ "grad_norm": 0.1069097244298094,
308
+ "learning_rate": 2.6078937713048357e-06,
309
+ "loss": 1.3969,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.3204172876304024,
314
+ "grad_norm": 0.1160964307611302,
315
+ "learning_rate": 2.581178832145114e-06,
316
+ "loss": 1.4672,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.32786885245901637,
321
+ "grad_norm": 0.1097725420424586,
322
+ "learning_rate": 2.553730261257924e-06,
323
+ "loss": 1.387,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.3353204172876304,
328
+ "grad_norm": 0.10407180190964474,
329
+ "learning_rate": 2.525566683815973e-06,
330
+ "loss": 1.3973,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.34277198211624443,
335
+ "grad_norm": 0.11536030542488797,
336
+ "learning_rate": 2.496707210158233e-06,
337
+ "loss": 1.4624,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.3502235469448584,
342
+ "grad_norm": 0.10982670956660034,
343
+ "learning_rate": 2.4671714228226542e-06,
344
+ "loss": 1.4078,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.35767511177347244,
349
+ "grad_norm": 0.10587771136409477,
350
+ "learning_rate": 2.4369793632584796e-06,
351
+ "loss": 1.4285,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.3651266766020864,
356
+ "grad_norm": 0.1208719398977082,
357
+ "learning_rate": 2.4061515182271535e-06,
358
+ "loss": 1.4726,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.37257824143070045,
363
+ "grad_norm": 0.10511587252373167,
364
+ "learning_rate": 2.3747088059010745e-06,
365
+ "loss": 1.3548,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.38002980625931443,
370
+ "grad_norm": 0.10957225921751226,
371
+ "learning_rate": 2.342672561669611e-06,
372
+ "loss": 1.4678,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.38748137108792846,
377
+ "grad_norm": 0.10693917993857549,
378
+ "learning_rate": 2.3100645236620133e-06,
379
+ "loss": 1.3974,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.3949329359165425,
384
+ "grad_norm": 0.11581766322136706,
385
+ "learning_rate": 2.276906817997054e-06,
386
+ "loss": 1.4098,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.40238450074515647,
391
+ "grad_norm": 0.10904876454822796,
392
+ "learning_rate": 2.2432219437693897e-06,
393
+ "loss": 1.4056,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.4098360655737705,
398
+ "grad_norm": 0.10831229242143947,
399
+ "learning_rate": 2.209032757782848e-06,
400
+ "loss": 1.3776,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.4172876304023845,
405
+ "grad_norm": 0.11150103499322561,
406
+ "learning_rate": 2.174362459040989e-06,
407
+ "loss": 1.4279,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.4247391952309985,
412
+ "grad_norm": 0.11628953499023266,
413
+ "learning_rate": 2.139234573005468e-06,
414
+ "loss": 1.4328,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.43219076005961254,
419
+ "grad_norm": 0.1154264307480958,
420
+ "learning_rate": 2.1036729356328806e-06,
421
+ "loss": 1.4109,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.4396423248882265,
426
+ "grad_norm": 0.1060574220828385,
427
+ "learning_rate": 2.06770167720092e-06,
428
+ "loss": 1.3781,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.44709388971684055,
433
+ "grad_norm": 0.1053110442104737,
434
+ "learning_rate": 2.0313452059348308e-06,
435
+ "loss": 1.4444,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.45454545454545453,
440
+ "grad_norm": 0.10693306802856366,
441
+ "learning_rate": 1.99462819144525e-06,
442
+ "loss": 1.4359,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.46199701937406856,
447
+ "grad_norm": 0.11652642471380918,
448
+ "learning_rate": 1.957575547988697e-06,
449
+ "loss": 1.4028,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.46944858420268254,
454
+ "grad_norm": 0.11274466501498542,
455
+ "learning_rate": 1.9202124175620545e-06,
456
+ "loss": 1.3804,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.47690014903129657,
461
+ "grad_norm": 0.10861122941192258,
462
+ "learning_rate": 1.8825641528425148e-06,
463
+ "loss": 1.3951,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.4843517138599106,
468
+ "grad_norm": 0.11658514112563267,
469
+ "learning_rate": 1.8446562999845715e-06,
470
+ "loss": 1.4377,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.4918032786885246,
475
+ "grad_norm": 0.11414477697164481,
476
+ "learning_rate": 1.8065145812857305e-06,
477
+ "loss": 1.3746,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.4992548435171386,
482
+ "grad_norm": 0.10815121580373825,
483
+ "learning_rate": 1.7681648777326943e-06,
484
+ "loss": 1.4422,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.5067064083457526,
489
+ "grad_norm": 0.11037495106798235,
490
+ "learning_rate": 1.7296332114398704e-06,
491
+ "loss": 1.3666,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.5141579731743666,
496
+ "grad_norm": 0.11676408141846001,
497
+ "learning_rate": 1.6909457279921186e-06,
498
+ "loss": 1.3734,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.5216095380029806,
503
+ "grad_norm": 0.1113201753442444,
504
+ "learning_rate": 1.6521286787037178e-06,
505
+ "loss": 1.4135,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.5290611028315947,
510
+ "grad_norm": 0.10247556885521109,
511
+ "learning_rate": 1.613208402805586e-06,
512
+ "loss": 1.4152,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.5365126676602087,
517
+ "grad_norm": 0.10445203605746987,
518
+ "learning_rate": 1.5742113095728515e-06,
519
+ "loss": 1.4376,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.5439642324888226,
524
+ "grad_norm": 0.10879333034477139,
525
+ "learning_rate": 1.535163860404891e-06,
526
+ "loss": 1.455,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.5514157973174366,
531
+ "grad_norm": 0.12869015642921014,
532
+ "learning_rate": 1.4960925508699984e-06,
533
+ "loss": 1.3821,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.5588673621460507,
538
+ "grad_norm": 0.10954384701245683,
539
+ "learning_rate": 1.4570238927268746e-06,
540
+ "loss": 1.4397,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.5663189269746647,
545
+ "grad_norm": 0.10796984723976862,
546
+ "learning_rate": 1.4179843959351213e-06,
547
+ "loss": 1.4644,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.5737704918032787,
552
+ "grad_norm": 0.11517040756519294,
553
+ "learning_rate": 1.3790005506669643e-06,
554
+ "loss": 1.4344,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.5812220566318927,
559
+ "grad_norm": 0.10926990342446409,
560
+ "learning_rate": 1.340098809332401e-06,
561
+ "loss": 1.4211,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.5886736214605067,
566
+ "grad_norm": 0.1115330774443057,
567
+ "learning_rate": 1.3013055686299683e-06,
568
+ "loss": 1.3726,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.5961251862891207,
573
+ "grad_norm": 0.10589693766514106,
574
+ "learning_rate": 1.2626471516353158e-06,
575
+ "loss": 1.4593,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.6035767511177347,
580
+ "grad_norm": 0.11370583262546306,
581
+ "learning_rate": 1.22414978993974e-06,
582
+ "loss": 1.3516,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.6110283159463488,
587
+ "grad_norm": 0.12504328760615357,
588
+ "learning_rate": 1.1858396058507837e-06,
589
+ "loss": 1.5039,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.6184798807749627,
594
+ "grad_norm": 0.11743701858841901,
595
+ "learning_rate": 1.1477425946670016e-06,
596
+ "loss": 1.413,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.6259314456035767,
601
+ "grad_norm": 0.11045498569848493,
602
+ "learning_rate": 1.1098846070389027e-06,
603
+ "loss": 1.3941,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.6333830104321908,
608
+ "grad_norm": 0.12144356998222744,
609
+ "learning_rate": 1.0722913314280395e-06,
610
+ "loss": 1.4172,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.6408345752608048,
615
+ "grad_norm": 0.10365373765687404,
616
+ "learning_rate": 1.0349882766761573e-06,
617
+ "loss": 1.3337,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.6482861400894188,
622
+ "grad_norm": 0.10647853031859235,
623
+ "learning_rate": 9.980007546962206e-07,
624
+ "loss": 1.3959,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.6557377049180327,
629
+ "grad_norm": 0.10731308955650487,
630
+ "learning_rate": 9.613538632970634e-07,
631
+ "loss": 1.4023,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.6631892697466468,
636
+ "grad_norm": 0.10450909600455241,
637
+ "learning_rate": 9.250724691533223e-07,
638
+ "loss": 1.3872,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.6706408345752608,
643
+ "grad_norm": 0.1041016914874247,
644
+ "learning_rate": 8.891811909322058e-07,
645
+ "loss": 1.4465,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.6780923994038748,
650
+ "grad_norm": 0.120460469459905,
651
+ "learning_rate": 8.537043825885445e-07,
652
+ "loss": 1.4501,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.6855439642324889,
657
+ "grad_norm": 0.1136665297817651,
658
+ "learning_rate": 8.186661168394658e-07,
659
+ "loss": 1.3963,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.6929955290611028,
664
+ "grad_norm": 0.11135508784322877,
665
+ "learning_rate": 7.840901688299e-07,
666
+ "loss": 1.4571,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.7004470938897168,
671
+ "grad_norm": 0.09679813596282592,
672
+ "learning_rate": 7.500000000000003e-07,
673
+ "loss": 1.3349,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.7078986587183308,
678
+ "grad_norm": 0.11033066007905798,
679
+ "learning_rate": 7.16418742165435e-07,
680
+ "loss": 1.4129,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.7153502235469449,
685
+ "grad_norm": 0.10642022161621655,
686
+ "learning_rate": 6.83369181821336e-07,
687
+ "loss": 1.4064,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.7228017883755589,
692
+ "grad_norm": 0.11256587052450513,
693
+ "learning_rate": 6.508737446805704e-07,
694
+ "loss": 1.4562,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.7302533532041728,
699
+ "grad_norm": 0.11453839206549224,
700
+ "learning_rate": 6.189544804568165e-07,
701
+ "loss": 1.375,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.7377049180327869,
706
+ "grad_norm": 0.10923398824173401,
707
+ "learning_rate": 5.876330479027766e-07,
708
+ "loss": 1.3996,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.7451564828614009,
713
+ "grad_norm": 0.10567442549564693,
714
+ "learning_rate": 5.56930700113673e-07,
715
+ "loss": 1.3151,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.7526080476900149,
720
+ "grad_norm": 0.11241400299999167,
721
+ "learning_rate": 5.268682701060012e-07,
722
+ "loss": 1.3493,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.7600596125186289,
727
+ "grad_norm": 0.12270530511888589,
728
+ "learning_rate": 4.974661566813315e-07,
729
+ "loss": 1.4556,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.767511177347243,
734
+ "grad_norm": 0.11388307104576878,
735
+ "learning_rate": 4.6874431058474127e-07,
736
+ "loss": 1.3664,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.7749627421758569,
741
+ "grad_norm": 0.11683819283505842,
742
+ "learning_rate": 4.4072222096727663e-07,
743
+ "loss": 1.3655,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.7824143070044709,
748
+ "grad_norm": 0.11164956386870885,
749
+ "learning_rate": 4.1341890216162934e-07,
750
+ "loss": 1.4173,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.789865871833085,
755
+ "grad_norm": 0.115617873949176,
756
+ "learning_rate": 3.868528807799988e-07,
757
+ "loss": 1.4142,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.797317436661699,
762
+ "grad_norm": 0.11850575487319875,
763
+ "learning_rate": 3.610421831428953e-07,
764
+ "loss": 1.4074,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.8047690014903129,
769
+ "grad_norm": 0.10945804497786706,
770
+ "learning_rate": 3.36004323047419e-07,
771
+ "loss": 1.4065,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.812220566318927,
776
+ "grad_norm": 0.1207296244907688,
777
+ "learning_rate": 3.11756289883306e-07,
778
+ "loss": 1.4036,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.819672131147541,
783
+ "grad_norm": 0.11721523752905044,
784
+ "learning_rate": 2.883145371048133e-07,
785
+ "loss": 1.4412,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.827123695976155,
790
+ "grad_norm": 0.1082841170490658,
791
+ "learning_rate": 2.656949710662591e-07,
792
+ "loss": 1.4002,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.834575260804769,
797
+ "grad_norm": 0.10851598999478153,
798
+ "learning_rate": 2.4391294022879947e-07,
799
+ "loss": 1.3989,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.842026825633383,
804
+ "grad_norm": 0.11994637882887171,
805
+ "learning_rate": 2.2298322474575838e-07,
806
+ "loss": 1.4249,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.849478390461997,
811
+ "grad_norm": 0.11657770238088389,
812
+ "learning_rate": 2.0292002643358892e-07,
813
+ "loss": 1.3606,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.856929955290611,
818
+ "grad_norm": 0.12222665777231102,
819
+ "learning_rate": 1.8373695913525317e-07,
820
+ "loss": 1.4042,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.8643815201192251,
825
+ "grad_norm": 0.11933591684408021,
826
+ "learning_rate": 1.6544703948258172e-07,
827
+ "loss": 1.3801,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.8718330849478391,
832
+ "grad_norm": 0.11512513535214042,
833
+ "learning_rate": 1.4806267806386093e-07,
834
+ "loss": 1.4339,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.879284649776453,
839
+ "grad_norm": 0.10887999147831859,
840
+ "learning_rate": 1.3159567100265506e-07,
841
+ "loss": 1.3578,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.886736214605067,
846
+ "grad_norm": 0.10936406330567362,
847
+ "learning_rate": 1.1605719195356806e-07,
848
+ "loss": 1.4209,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.8941877794336811,
853
+ "grad_norm": 0.11262116794609218,
854
+ "learning_rate": 1.0145778452038629e-07,
855
+ "loss": 1.3144,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.9016393442622951,
860
+ "grad_norm": 0.10899372973775676,
861
+ "learning_rate": 8.780735510173316e-08,
862
+ "loss": 1.3914,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.9090909090909091,
867
+ "grad_norm": 0.10967422102767481,
868
+ "learning_rate": 7.51151661691048e-08,
869
+ "loss": 1.4328,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.9165424739195231,
874
+ "grad_norm": 0.1195412132912122,
875
+ "learning_rate": 6.338982998183856e-08,
876
+ "loss": 1.4603,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.9239940387481371,
881
+ "grad_norm": 0.11487548750982872,
882
+ "learning_rate": 5.263930274328044e-08,
883
+ "loss": 1.3718,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.9314456035767511,
888
+ "grad_norm": 0.10425903788261691,
889
+ "learning_rate": 4.287087920212035e-08,
890
+ "loss": 1.3577,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.9388971684053651,
895
+ "grad_norm": 0.10782320142147576,
896
+ "learning_rate": 3.4091187702554485e-08,
897
+ "loss": 1.4204,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.9463487332339792,
902
+ "grad_norm": 0.11831408481668713,
903
+ "learning_rate": 2.630618568663584e-08,
904
+ "loss": 1.3797,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.9538002980625931,
909
+ "grad_norm": 0.10973676611006619,
910
+ "learning_rate": 1.9521155651863854e-08,
911
+ "loss": 1.4409,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.9612518628912071,
916
+ "grad_norm": 0.1141554461719489,
917
+ "learning_rate": 1.3740701566756276e-08,
918
+ "loss": 1.3842,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.9687034277198212,
923
+ "grad_norm": 0.11403561646592845,
924
+ "learning_rate": 8.968745746835983e-09,
925
+ "loss": 1.3295,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.9761549925484352,
930
+ "grad_norm": 0.11455606102253561,
931
+ "learning_rate": 5.208526193150764e-09,
932
+ "loss": 1.434,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.9836065573770492,
937
+ "grad_norm": 0.10758938639100596,
938
+ "learning_rate": 2.462594395134854e-09,
939
+ "loss": 1.433,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.9910581222056631,
944
+ "grad_norm": 0.11199281621555614,
945
+ "learning_rate": 7.328135993011631e-10,
946
+ "loss": 1.4072,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.9985096870342772,
951
+ "grad_norm": 0.10839803620089897,
952
+ "learning_rate": 2.035754493812103e-11,
953
+ "loss": 1.4364,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 1.0,
958
+ "eval_loss": 1.4019134044647217,
959
+ "eval_runtime": 563.36,
960
+ "eval_samples_per_second": 4.235,
961
+ "eval_steps_per_second": 0.133,
962
+ "step": 671
963
+ },
964
+ {
965
+ "epoch": 1.0,
966
+ "step": 671,
967
+ "total_flos": 2236028102377472.0,
968
+ "train_loss": 1.4386844755817987,
969
+ "train_runtime": 17062.4084,
970
+ "train_samples_per_second": 1.258,
971
+ "train_steps_per_second": 0.039
972
+ }
973
+ ],
974
+ "logging_steps": 5,
975
+ "max_steps": 671,
976
+ "num_input_tokens_seen": 0,
977
+ "num_train_epochs": 1,
978
+ "save_steps": 200,
979
+ "stateful_callbacks": {
980
+ "TrainerControl": {
981
+ "args": {
982
+ "should_epoch_stop": false,
983
+ "should_evaluate": false,
984
+ "should_log": false,
985
+ "should_save": true,
986
+ "should_training_stop": false
987
+ },
988
+ "attributes": {}
989
+ }
990
+ },
991
+ "total_flos": 2236028102377472.0,
992
+ "train_batch_size": 8,
993
+ "trial_name": null,
994
+ "trial_params": null
995
+ }