Model save
Browse files
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:
|
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:
|
3 |
-
size
|
|
|
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 |
+
}
|