Hugging Face's logo

terry69
/
mistral_poe_small

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
trl
sft
Generated from Trainer
Model card Files Metrics Community
terry69 commited on
Commit
c9872c2
•
1 Parent(s): 61017db

Model save

Browse files
Files changed (6) hide show
  1. README.md +67 -0
  2. adapter_model.safetensors +1 -1
  3. all_results.json +8 -0
  4. runs/May14_05-10-08_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715663425.ip-172-31-69-60.ec2.internal.48805.0 +2 -2
  5. train_results.json +8 -0
  6. trainer_state.json +346 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-v0.1
9
+ model-index:
10
+ - name: mistral_poe_small
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_poe_small
18
+
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: nan
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: 0.0002
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 32
48
+ - total_eval_batch_size: 4
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:---------------:|
58
+ | 0.0056 | 1.0 | 217 | nan |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - PEFT 0.7.1
64
+ - Transformers 4.39.0.dev0
65
+ - Pytorch 2.2.2+cu121
66
+ - Datasets 2.14.6
67
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f2322ae4cfbeef77094de2270bb403a4b46e262f22203b5beeb0dbb61905e39
3
  size 31516744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ded62283a71473a7a81066397e380ec9ce8ada4ba92e92dd6ad263082c291478
3
  size 31516744
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.0019402640651178403,
4
+ "train_runtime": 4565.6051,
5
+ "train_samples": 10393,
6
+ "train_samples_per_second": 2.276,
7
+ "train_steps_per_second": 0.048
8
+ }
runs/May14_05-10-08_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715663425.ip-172-31-69-60.ec2.internal.48805.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44c6931de8b8b882ed126e0bd1fe5874c78fcdf14bc00b0c0811b728b8a9d395
3
- size 9677
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0e299a0b162ac8e28980b4d27c6595a9a0c2f7bd1ff4f35a1c9027cdbe4c05
3
+ size 12623
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.0019402640651178403,
4
+ "train_runtime": 4565.6051,
5
+ "train_samples": 10393,
6
+ "train_samples_per_second": 2.276,
7
+ "train_steps_per_second": 0.048
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 217,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 5.18852740291647,
14
+ "learning_rate": 9.090909090909091e-06,
15
+ "loss": 5.3084,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.02,
20
+ "grad_norm": 5.03901362055586,
21
+ "learning_rate": 4.545454545454546e-05,
22
+ "loss": 5.0728,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.05,
27
+ "grad_norm": 4.459588393324012,
28
+ "learning_rate": 9.090909090909092e-05,
29
+ "loss": 2.37,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.07,
34
+ "grad_norm": 0.43459848938578693,
35
+ "learning_rate": 0.00013636363636363637,
36
+ "loss": 0.1307,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.09,
41
+ "grad_norm": 0.0299929460934137,
42
+ "learning_rate": 0.00018181818181818183,
43
+ "loss": 0.0483,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "grad_norm": 0.013812266692594782,
49
+ "learning_rate": 0.00019988322268323268,
50
+ "loss": 0.0225,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.14,
55
+ "grad_norm": 0.009773102416496118,
56
+ "learning_rate": 0.0001991705709821562,
57
+ "loss": 0.0198,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.16,
62
+ "grad_norm": 0.0039386428485718465,
63
+ "learning_rate": 0.00019781476007338058,
64
+ "loss": 0.015,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.18,
69
+ "grad_norm": 0.002196082201771653,
70
+ "learning_rate": 0.00019582458291091663,
71
+ "loss": 0.0096,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.21,
76
+ "grad_norm": 0.018430687632200037,
77
+ "learning_rate": 0.0001932129465573568,
78
+ "loss": 0.0024,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.23,
83
+ "grad_norm": 0.9834813463855321,
84
+ "learning_rate": 0.0001899967884766212,
85
+ "loss": 0.0281,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.25,
90
+ "grad_norm": 0.005069811100933593,
91
+ "learning_rate": 0.00018619696668800492,
92
+ "loss": 0.0001,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.28,
97
+ "grad_norm": 0.007249668030582534,
98
+ "learning_rate": 0.0001818381244939187,
99
+ "loss": 0.0001,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.3,
104
+ "grad_norm": 0.0071458935911795545,
105
+ "learning_rate": 0.00017694853065861662,
106
+ "loss": 0.0001,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.32,
111
+ "grad_norm": 0.004757395926328272,
112
+ "learning_rate": 0.00017155989607441213,
113
+ "loss": 0.0001,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.35,
118
+ "grad_norm": 0.0027371110149472387,
119
+ "learning_rate": 0.0001657071681043731,
120
+ "loss": 0.0001,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.37,
125
+ "grad_norm": 0.0015303804705887707,
126
+ "learning_rate": 0.00015942830393526176,
127
+ "loss": 0.0,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.39,
132
+ "grad_norm": 0.0019029295128688208,
133
+ "learning_rate": 0.0001527640244106133,
134
+ "loss": 0.0191,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.41,
139
+ "grad_norm": 0.002913339239522618,
140
+ "learning_rate": 0.00014575754994043956,
141
+ "loss": 0.0,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.44,
146
+ "grad_norm": 0.002526914206171285,
147
+ "learning_rate": 0.0001384543202002851,
148
+ "loss": 0.0,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.46,
153
+ "grad_norm": 0.002364320350741189,
154
+ "learning_rate": 0.00013090169943749476,
155
+ "loss": 0.0,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.48,
160
+ "grad_norm": 0.001415040670977836,
161
+ "learning_rate": 0.00012314866929589432,
162
+ "loss": 0.0,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.51,
167
+ "grad_norm": 0.0014806660372118452,
168
+ "learning_rate": 0.00011524551115103454,
169
+ "loss": 0.0,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.53,
174
+ "grad_norm": 0.0009238152395960922,
175
+ "learning_rate": 0.00010724348001617625,
176
+ "loss": 0.0,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.55,
181
+ "grad_norm": 0.316858259539684,
182
+ "learning_rate": 9.919447213386103e-05,
183
+ "loss": 0.0175,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.58,
188
+ "grad_norm": 0.0013793498850558623,
189
+ "learning_rate": 9.115068840886417e-05,
190
+ "loss": 0.0,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.6,
195
+ "grad_norm": 0.03179793467382126,
196
+ "learning_rate": 8.316429586529615e-05,
197
+ "loss": 0.0,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.62,
202
+ "grad_norm": 0.008302429594092641,
203
+ "learning_rate": 7.528708932343304e-05,
204
+ "loss": 0.0104,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.65,
209
+ "grad_norm": 0.024284403402931108,
210
+ "learning_rate": 6.757015549043175e-05,
211
+ "loss": 0.0001,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.67,
216
+ "grad_norm": 0.007160721938093322,
217
+ "learning_rate": 6.006354164343046e-05,
218
+ "loss": 0.0001,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.69,
223
+ "grad_norm": 0.00442645759914904,
224
+ "learning_rate": 5.28159310537518e-05,
225
+ "loss": 0.0,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.71,
230
+ "grad_norm": 0.001965826516583593,
231
+ "learning_rate": 4.587432725720687e-05,
232
+ "loss": 0.0,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.74,
237
+ "grad_norm": 0.0012986955816234175,
238
+ "learning_rate": 3.9283749218128885e-05,
239
+ "loss": 0.0,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.76,
244
+ "grad_norm": 0.0010247882146462446,
245
+ "learning_rate": 3.308693936411421e-05,
246
+ "loss": 0.0,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.78,
251
+ "grad_norm": 0.000977980722589858,
252
+ "learning_rate": 2.7324086384977698e-05,
253
+ "loss": 0.0,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.81,
258
+ "grad_norm": 0.0008640860356404602,
259
+ "learning_rate": 2.2032564593677774e-05,
260
+ "loss": 0.0,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.83,
265
+ "grad_norm": 0.0007152715573634965,
266
+ "learning_rate": 1.7246691539555028e-05,
267
+ "loss": 0.0,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.85,
272
+ "grad_norm": 0.0008068934592673394,
273
+ "learning_rate": 1.2997505445856084e-05,
274
+ "loss": 0.0,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.88,
279
+ "grad_norm": 0.000785102458262206,
280
+ "learning_rate": 9.31256391494546e-06,
281
+ "loss": 0.0,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.9,
286
+ "grad_norm": 0.0006662070791456656,
287
+ "learning_rate": 6.215765206679569e-06,
288
+ "loss": 0.0,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.92,
293
+ "grad_norm": 0.0006676407776271578,
294
+ "learning_rate": 3.7271932490209328e-06,
295
+ "loss": 0.0,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.94,
300
+ "grad_norm": 0.0006248827839313129,
301
+ "learning_rate": 1.8629873860586566e-06,
302
+ "loss": 0.0,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.97,
307
+ "grad_norm": 0.0006849249794092451,
308
+ "learning_rate": 6.352377081687011e-07,
309
+ "loss": 0.0,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.99,
314
+ "grad_norm": 0.0007915981269703633,
315
+ "learning_rate": 5.190664313851068e-08,
316
+ "loss": 0.0056,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 1.0,
321
+ "eval_loss": NaN,
322
+ "eval_runtime": 745.5269,
323
+ "eval_samples_per_second": 1.551,
324
+ "eval_steps_per_second": 0.388,
325
+ "step": 217
326
+ },
327
+ {
328
+ "epoch": 1.0,
329
+ "step": 217,
330
+ "total_flos": 1973257544663040.0,
331
+ "train_loss": 0.0019402640651178403,
332
+ "train_runtime": 4565.6051,
333
+ "train_samples_per_second": 2.276,
334
+ "train_steps_per_second": 0.048
335
+ }
336
+ ],
337
+ "logging_steps": 5,
338
+ "max_steps": 217,
339
+ "num_input_tokens_seen": 0,
340
+ "num_train_epochs": 1,
341
+ "save_steps": 40,
342
+ "total_flos": 1973257544663040.0,
343
+ "train_batch_size": 6,
344
+ "trial_name": null,
345
+ "trial_params": null
346
+ }