Model save
Browse files- README.md +13 -6
- adapter_config.json +1 -1
- adapter_model.safetensors +1 -1
- all_results.json +6 -6
- eval_results.json +4 -4
- runs/Dec12_14-33-55_vista-trx/events.out.tfevents.1702384616.vista-trx.76389.0 +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +3 -1
- train_results.json +2 -2
- trainer_state.json +118 -116
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,10 +1,11 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- generator
|
|
|
8 |
model-index:
|
9 |
- name: zephyr-7b-sft-lora
|
10 |
results: []
|
@@ -17,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -47,19 +48,25 @@ The following hyperparameters were used during training:
|
|
47 |
- total_eval_batch_size: 64
|
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.
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
-
- Transformers 4.
|
63 |
- Pytorch 2.1.1+cu121
|
64 |
- Datasets 2.14.6
|
65 |
-
- Tokenizers 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- generator
|
8 |
+
base_model: mistralai/Mistral-7B-v0.1
|
9 |
model-index:
|
10 |
- name: zephyr-7b-sft-lora
|
11 |
results: []
|
|
|
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 generator dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.0922
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
48 |
- total_eval_batch_size: 64
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: cosine
|
|
|
51 |
- num_epochs: 1
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 1.3681 | 1.0 | 272 | 1.0922 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
+
- Transformers 4.36.0
|
63 |
- Pytorch 2.1.1+cu121
|
64 |
- Datasets 2.14.6
|
65 |
+
- Tokenizers 0.15.0
|
66 |
+
## Training procedure
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
|
72 |
+
- PEFT 0.6.1
|
adapter_config.json
CHANGED
@@ -16,9 +16,9 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"v_proj",
|
20 |
"o_proj",
|
21 |
-
"q_proj",
|
22 |
"k_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
"v_proj",
|
21 |
"o_proj",
|
|
|
22 |
"k_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109086672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46933e34b2e227ff195e628e2c8b61bf212c9ef7309bda18a4978b0225e175c2
|
3 |
size 109086672
|
all_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 23110,
|
6 |
-
"eval_samples_per_second": 6.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
-
"train_loss": 1.
|
9 |
-
"train_runtime":
|
10 |
"train_samples": 207865,
|
11 |
"train_samples_per_second": 1.924,
|
12 |
"train_steps_per_second": 0.004
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.0922234058380127,
|
4 |
+
"eval_runtime": 2385.5237,
|
5 |
"eval_samples": 23110,
|
6 |
+
"eval_samples_per_second": 6.469,
|
7 |
+
"eval_steps_per_second": 0.101,
|
8 |
+
"train_loss": 1.4444872824584736,
|
9 |
+
"train_runtime": 72477.8005,
|
10 |
"train_samples": 207865,
|
11 |
"train_samples_per_second": 1.924,
|
12 |
"train_steps_per_second": 0.004
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 23110,
|
6 |
-
"eval_samples_per_second": 6.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.0922234058380127,
|
4 |
+
"eval_runtime": 2385.5237,
|
5 |
"eval_samples": 23110,
|
6 |
+
"eval_samples_per_second": 6.469,
|
7 |
+
"eval_steps_per_second": 0.101
|
8 |
}
|
runs/Dec12_14-33-55_vista-trx/events.out.tfevents.1702384616.vista-trx.76389.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d671b24ef781b7c435904a85193eddc752de83ce5b7096e702d3afcf99aeab69
|
3 |
+
size 4426
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -37,5 +39,5 @@
|
|
37 |
"spaces_between_special_tokens": false,
|
38 |
"tokenizer_class": "LlamaTokenizer",
|
39 |
"unk_token": "<unk>",
|
40 |
-
"use_default_system_prompt":
|
41 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
}
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 207865,
|
6 |
"train_samples_per_second": 1.924,
|
7 |
"train_steps_per_second": 0.004
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 1.4444872824584736,
|
4 |
+
"train_runtime": 72477.8005,
|
5 |
"train_samples": 207865,
|
6 |
"train_samples_per_second": 1.924,
|
7 |
"train_steps_per_second": 0.004
|
trainer_state.json
CHANGED
@@ -10,357 +10,359 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
-
"learning_rate":
|
14 |
-
"loss": 1.
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.02,
|
19 |
-
"learning_rate":
|
20 |
-
"loss": 1.
|
21 |
"step": 5
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.04,
|
25 |
-
"learning_rate":
|
26 |
-
"loss": 1.
|
27 |
"step": 10
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.06,
|
31 |
-
"learning_rate": 1.
|
32 |
-
"loss": 1.
|
33 |
"step": 15
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.07,
|
37 |
-
"learning_rate": 1.
|
38 |
-
"loss": 1.
|
39 |
"step": 20
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.09,
|
43 |
-
"learning_rate": 1.
|
44 |
-
"loss": 1.
|
45 |
"step": 25
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.11,
|
49 |
-
"learning_rate": 1.
|
50 |
-
"loss": 1.
|
51 |
"step": 30
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.13,
|
55 |
-
"learning_rate": 1.
|
56 |
-
"loss": 1.
|
57 |
"step": 35
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.15,
|
61 |
-
"learning_rate": 1.
|
62 |
-
"loss": 1.
|
63 |
"step": 40
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.17,
|
67 |
-
"learning_rate": 1.
|
68 |
-
"loss": 1.
|
69 |
"step": 45
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.18,
|
73 |
-
"learning_rate": 1.
|
74 |
-
"loss": 1.
|
75 |
"step": 50
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.2,
|
79 |
-
"learning_rate": 1.
|
80 |
-
"loss": 1.
|
81 |
"step": 55
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.22,
|
85 |
-
"learning_rate": 1.
|
86 |
-
"loss": 1.
|
87 |
"step": 60
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.24,
|
91 |
-
"learning_rate": 1.
|
92 |
-
"loss": 1.
|
93 |
"step": 65
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.26,
|
97 |
-
"learning_rate": 1.
|
98 |
-
"loss": 1.
|
99 |
"step": 70
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.28,
|
103 |
-
"learning_rate": 1.
|
104 |
-
"loss": 1.
|
105 |
"step": 75
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.29,
|
109 |
-
"learning_rate": 1.
|
110 |
-
"loss": 1.
|
111 |
"step": 80
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.31,
|
115 |
-
"learning_rate": 1.
|
116 |
-
"loss": 1.
|
117 |
"step": 85
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.33,
|
121 |
-
"learning_rate": 1.
|
122 |
-
"loss": 1.
|
123 |
"step": 90
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.35,
|
127 |
-
"learning_rate": 1.
|
128 |
-
"loss": 1.
|
129 |
"step": 95
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.37,
|
133 |
-
"learning_rate": 1.
|
134 |
-
"loss": 1.
|
135 |
"step": 100
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.39,
|
139 |
-
"learning_rate": 1.
|
140 |
-
"loss": 1.
|
141 |
"step": 105
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.4,
|
145 |
-
"learning_rate": 1.
|
146 |
-
"loss": 1.
|
147 |
"step": 110
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.42,
|
151 |
-
"learning_rate": 1.
|
152 |
-
"loss": 1.
|
153 |
"step": 115
|
154 |
},
|
155 |
{
|
156 |
"epoch": 0.44,
|
157 |
-
"learning_rate": 1.
|
158 |
-
"loss": 1.
|
159 |
"step": 120
|
160 |
},
|
161 |
{
|
162 |
"epoch": 0.46,
|
163 |
-
"learning_rate": 1.
|
164 |
-
"loss": 1.
|
165 |
"step": 125
|
166 |
},
|
167 |
{
|
168 |
"epoch": 0.48,
|
169 |
-
"learning_rate": 1.
|
170 |
-
"loss": 1.
|
171 |
"step": 130
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.5,
|
175 |
-
"learning_rate": 1.
|
176 |
-
"loss": 1.
|
177 |
"step": 135
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.51,
|
181 |
-
"learning_rate":
|
182 |
-
"loss": 1.
|
183 |
"step": 140
|
184 |
},
|
185 |
{
|
186 |
"epoch": 0.53,
|
187 |
-
"learning_rate":
|
188 |
-
"loss": 1.
|
189 |
"step": 145
|
190 |
},
|
191 |
{
|
192 |
"epoch": 0.55,
|
193 |
-
"learning_rate":
|
194 |
-
"loss": 1.
|
195 |
"step": 150
|
196 |
},
|
197 |
{
|
198 |
"epoch": 0.57,
|
199 |
-
"learning_rate":
|
200 |
-
"loss": 1.
|
201 |
"step": 155
|
202 |
},
|
203 |
{
|
204 |
"epoch": 0.59,
|
205 |
-
"learning_rate":
|
206 |
-
"loss": 1.
|
207 |
"step": 160
|
208 |
},
|
209 |
{
|
210 |
"epoch": 0.61,
|
211 |
-
"learning_rate":
|
212 |
-
"loss": 1.
|
213 |
"step": 165
|
214 |
},
|
215 |
{
|
216 |
"epoch": 0.62,
|
217 |
-
"learning_rate":
|
218 |
-
"loss": 1.
|
219 |
"step": 170
|
220 |
},
|
221 |
{
|
222 |
"epoch": 0.64,
|
223 |
-
"learning_rate":
|
224 |
-
"loss": 1.
|
225 |
"step": 175
|
226 |
},
|
227 |
{
|
228 |
"epoch": 0.66,
|
229 |
-
"learning_rate":
|
230 |
-
"loss": 1.
|
231 |
"step": 180
|
232 |
},
|
233 |
{
|
234 |
"epoch": 0.68,
|
235 |
-
"learning_rate":
|
236 |
-
"loss": 1.
|
237 |
"step": 185
|
238 |
},
|
239 |
{
|
240 |
"epoch": 0.7,
|
241 |
-
"learning_rate":
|
242 |
-
"loss": 1.
|
243 |
"step": 190
|
244 |
},
|
245 |
{
|
246 |
"epoch": 0.72,
|
247 |
-
"learning_rate":
|
248 |
-
"loss": 1.
|
249 |
"step": 195
|
250 |
},
|
251 |
{
|
252 |
"epoch": 0.73,
|
253 |
-
"learning_rate": 3.
|
254 |
-
"loss": 1.
|
255 |
"step": 200
|
256 |
},
|
257 |
{
|
258 |
"epoch": 0.75,
|
259 |
-
"learning_rate":
|
260 |
-
"loss": 1.
|
261 |
"step": 205
|
262 |
},
|
263 |
{
|
264 |
"epoch": 0.77,
|
265 |
-
"learning_rate":
|
266 |
-
"loss": 1.
|
267 |
"step": 210
|
268 |
},
|
269 |
{
|
270 |
"epoch": 0.79,
|
271 |
-
"learning_rate": 2.
|
272 |
-
"loss": 1.
|
273 |
"step": 215
|
274 |
},
|
275 |
{
|
276 |
"epoch": 0.81,
|
277 |
-
"learning_rate":
|
278 |
-
"loss": 1.
|
279 |
"step": 220
|
280 |
},
|
281 |
{
|
282 |
"epoch": 0.83,
|
283 |
-
"learning_rate": 1.
|
284 |
-
"loss": 1.
|
285 |
"step": 225
|
286 |
},
|
287 |
{
|
288 |
"epoch": 0.84,
|
289 |
-
"learning_rate": 1.
|
290 |
-
"loss": 1.
|
291 |
"step": 230
|
292 |
},
|
293 |
{
|
294 |
"epoch": 0.86,
|
295 |
-
"learning_rate":
|
296 |
-
"loss": 1.
|
297 |
"step": 235
|
298 |
},
|
299 |
{
|
300 |
"epoch": 0.88,
|
301 |
-
"learning_rate":
|
302 |
-
"loss": 1.
|
303 |
"step": 240
|
304 |
},
|
305 |
{
|
306 |
"epoch": 0.9,
|
307 |
-
"learning_rate":
|
308 |
-
"loss": 1.
|
309 |
"step": 245
|
310 |
},
|
311 |
{
|
312 |
"epoch": 0.92,
|
313 |
-
"learning_rate": 3.
|
314 |
-
"loss": 1.
|
315 |
"step": 250
|
316 |
},
|
317 |
{
|
318 |
"epoch": 0.94,
|
319 |
-
"learning_rate":
|
320 |
-
"loss": 1.
|
321 |
"step": 255
|
322 |
},
|
323 |
{
|
324 |
"epoch": 0.95,
|
325 |
-
"learning_rate":
|
326 |
-
"loss": 1.
|
327 |
"step": 260
|
328 |
},
|
329 |
{
|
330 |
"epoch": 0.97,
|
331 |
-
"learning_rate":
|
332 |
-
"loss": 1.
|
333 |
"step": 265
|
334 |
},
|
335 |
{
|
336 |
"epoch": 0.99,
|
337 |
-
"learning_rate":
|
338 |
-
"loss": 1.
|
339 |
"step": 270
|
340 |
},
|
341 |
{
|
342 |
"epoch": 1.0,
|
343 |
-
"eval_loss": 1.
|
344 |
-
"eval_runtime":
|
345 |
-
"eval_samples_per_second": 6.
|
346 |
-
"eval_steps_per_second": 0.
|
347 |
"step": 272
|
348 |
},
|
349 |
{
|
350 |
"epoch": 1.0,
|
351 |
"step": 272,
|
352 |
"total_flos": 7631468079611904.0,
|
353 |
-
"train_loss": 1.
|
354 |
-
"train_runtime":
|
355 |
"train_samples_per_second": 1.924,
|
356 |
"train_steps_per_second": 0.004
|
357 |
}
|
358 |
],
|
359 |
"logging_steps": 5,
|
360 |
"max_steps": 272,
|
|
|
361 |
"num_train_epochs": 1,
|
362 |
"save_steps": 500,
|
363 |
"total_flos": 7631468079611904.0,
|
|
|
364 |
"trial_name": null,
|
365 |
"trial_params": null
|
366 |
}
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
+
"learning_rate": 1.9999332998034515e-05,
|
14 |
+
"loss": 1.9596,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.02,
|
19 |
+
"learning_rate": 1.99833293993636e-05,
|
20 |
+
"loss": 1.9397,
|
21 |
"step": 5
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.04,
|
25 |
+
"learning_rate": 1.99333731792395e-05,
|
26 |
+
"loss": 1.8704,
|
27 |
"step": 10
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.06,
|
31 |
+
"learning_rate": 1.985029789966671e-05,
|
32 |
+
"loss": 1.7903,
|
33 |
"step": 15
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.07,
|
37 |
+
"learning_rate": 1.9734380543606932e-05,
|
38 |
+
"loss": 1.6992,
|
39 |
"step": 20
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.09,
|
43 |
+
"learning_rate": 1.9586007593450098e-05,
|
44 |
+
"loss": 1.6678,
|
45 |
"step": 25
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.11,
|
49 |
+
"learning_rate": 1.9405673742435677e-05,
|
50 |
+
"loss": 1.6189,
|
51 |
"step": 30
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.13,
|
55 |
+
"learning_rate": 1.9193980245285967e-05,
|
56 |
+
"loss": 1.6122,
|
57 |
"step": 35
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.15,
|
61 |
+
"learning_rate": 1.8951632913550625e-05,
|
62 |
+
"loss": 1.5687,
|
63 |
"step": 40
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.17,
|
67 |
+
"learning_rate": 1.8679439762346186e-05,
|
68 |
+
"loss": 1.5472,
|
69 |
"step": 45
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.18,
|
73 |
+
"learning_rate": 1.8378308316336585e-05,
|
74 |
+
"loss": 1.5302,
|
75 |
"step": 50
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.2,
|
79 |
+
"learning_rate": 1.8049242583936923e-05,
|
80 |
+
"loss": 1.5045,
|
81 |
"step": 55
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.22,
|
85 |
+
"learning_rate": 1.769333970982879e-05,
|
86 |
+
"loss": 1.49,
|
87 |
"step": 60
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.24,
|
91 |
+
"learning_rate": 1.7311786316948112e-05,
|
92 |
+
"loss": 1.4782,
|
93 |
"step": 65
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.26,
|
97 |
+
"learning_rate": 1.6905854550141717e-05,
|
98 |
+
"loss": 1.4596,
|
99 |
"step": 70
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.28,
|
103 |
+
"learning_rate": 1.647689783468362e-05,
|
104 |
+
"loss": 1.4509,
|
105 |
"step": 75
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.29,
|
109 |
+
"learning_rate": 1.6026346363792565e-05,
|
110 |
+
"loss": 1.4295,
|
111 |
"step": 80
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.31,
|
115 |
+
"learning_rate": 1.5555702330196024e-05,
|
116 |
+
"loss": 1.4301,
|
117 |
"step": 85
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.33,
|
121 |
+
"learning_rate": 1.5066534917639195e-05,
|
122 |
+
"loss": 1.4297,
|
123 |
"step": 90
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.35,
|
127 |
+
"learning_rate": 1.4560475069037895e-05,
|
128 |
+
"loss": 1.4161,
|
129 |
"step": 95
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.37,
|
133 |
+
"learning_rate": 1.403921004871895e-05,
|
134 |
+
"loss": 1.4144,
|
135 |
"step": 100
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.39,
|
139 |
+
"learning_rate": 1.350447781687826e-05,
|
140 |
+
"loss": 1.4051,
|
141 |
"step": 105
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.4,
|
145 |
+
"learning_rate": 1.2958061235012707e-05,
|
146 |
+
"loss": 1.4061,
|
147 |
"step": 110
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.42,
|
151 |
+
"learning_rate": 1.2401782121645767e-05,
|
152 |
+
"loss": 1.3968,
|
153 |
"step": 115
|
154 |
},
|
155 |
{
|
156 |
"epoch": 0.44,
|
157 |
+
"learning_rate": 1.1837495178165706e-05,
|
158 |
+
"loss": 1.3946,
|
159 |
"step": 120
|
160 |
},
|
161 |
{
|
162 |
"epoch": 0.46,
|
163 |
+
"learning_rate": 1.126708180502834e-05,
|
164 |
+
"loss": 1.382,
|
165 |
"step": 125
|
166 |
},
|
167 |
{
|
168 |
"epoch": 0.48,
|
169 |
+
"learning_rate": 1.0692443828941918e-05,
|
170 |
+
"loss": 1.3844,
|
171 |
"step": 130
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.5,
|
175 |
+
"learning_rate": 1.0115497161948409e-05,
|
176 |
+
"loss": 1.3857,
|
177 |
"step": 135
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.51,
|
181 |
+
"learning_rate": 9.538165413542607e-06,
|
182 |
+
"loss": 1.3812,
|
183 |
"step": 140
|
184 |
},
|
185 |
{
|
186 |
"epoch": 0.53,
|
187 |
+
"learning_rate": 8.962373477126983e-06,
|
188 |
+
"loss": 1.3657,
|
189 |
"step": 145
|
190 |
},
|
191 |
{
|
192 |
"epoch": 0.55,
|
193 |
+
"learning_rate": 8.39004111218587e-06,
|
194 |
+
"loss": 1.3757,
|
195 |
"step": 150
|
196 |
},
|
197 |
{
|
198 |
"epoch": 0.57,
|
199 |
+
"learning_rate": 7.823076543576718e-06,
|
200 |
+
"loss": 1.3713,
|
201 |
"step": 155
|
202 |
},
|
203 |
{
|
204 |
"epoch": 0.59,
|
205 |
+
"learning_rate": 7.263370099279173e-06,
|
206 |
+
"loss": 1.3653,
|
207 |
"step": 160
|
208 |
},
|
209 |
{
|
210 |
"epoch": 0.61,
|
211 |
+
"learning_rate": 6.712787907814542e-06,
|
212 |
+
"loss": 1.3749,
|
213 |
"step": 165
|
214 |
},
|
215 |
{
|
216 |
"epoch": 0.62,
|
217 |
+
"learning_rate": 6.173165676349103e-06,
|
218 |
+
"loss": 1.3718,
|
219 |
"step": 170
|
220 |
},
|
221 |
{
|
222 |
"epoch": 0.64,
|
223 |
+
"learning_rate": 5.646302570225919e-06,
|
224 |
+
"loss": 1.3728,
|
225 |
"step": 175
|
226 |
},
|
227 |
{
|
228 |
"epoch": 0.66,
|
229 |
+
"learning_rate": 5.133955214331439e-06,
|
230 |
+
"loss": 1.3672,
|
231 |
"step": 180
|
232 |
},
|
233 |
{
|
234 |
"epoch": 0.68,
|
235 |
+
"learning_rate": 4.637831836297103e-06,
|
236 |
+
"loss": 1.366,
|
237 |
"step": 185
|
238 |
},
|
239 |
{
|
240 |
"epoch": 0.7,
|
241 |
+
"learning_rate": 4.1595865710632366e-06,
|
242 |
+
"loss": 1.3708,
|
243 |
"step": 190
|
244 |
},
|
245 |
{
|
246 |
"epoch": 0.72,
|
247 |
+
"learning_rate": 3.700813945794425e-06,
|
248 |
+
"loss": 1.37,
|
249 |
"step": 195
|
250 |
},
|
251 |
{
|
252 |
"epoch": 0.73,
|
253 |
+
"learning_rate": 3.2630435635344283e-06,
|
254 |
+
"loss": 1.3679,
|
255 |
"step": 200
|
256 |
},
|
257 |
{
|
258 |
"epoch": 0.75,
|
259 |
+
"learning_rate": 2.847735003325868e-06,
|
260 |
+
"loss": 1.3671,
|
261 |
"step": 205
|
262 |
},
|
263 |
{
|
264 |
"epoch": 0.77,
|
265 |
+
"learning_rate": 2.456272953798361e-06,
|
266 |
+
"loss": 1.3677,
|
267 |
"step": 210
|
268 |
},
|
269 |
{
|
270 |
"epoch": 0.79,
|
271 |
+
"learning_rate": 2.0899625964503113e-06,
|
272 |
+
"loss": 1.3675,
|
273 |
"step": 215
|
274 |
},
|
275 |
{
|
276 |
"epoch": 0.81,
|
277 |
+
"learning_rate": 1.7500252540169782e-06,
|
278 |
+
"loss": 1.3647,
|
279 |
"step": 220
|
280 |
},
|
281 |
{
|
282 |
"epoch": 0.83,
|
283 |
+
"learning_rate": 1.4375943184337871e-06,
|
284 |
+
"loss": 1.371,
|
285 |
"step": 225
|
286 |
},
|
287 |
{
|
288 |
"epoch": 0.84,
|
289 |
+
"learning_rate": 1.1537114719714482e-06,
|
290 |
+
"loss": 1.3622,
|
291 |
"step": 230
|
292 |
},
|
293 |
{
|
294 |
"epoch": 0.86,
|
295 |
+
"learning_rate": 8.993232141421415e-07,
|
296 |
+
"loss": 1.3596,
|
297 |
"step": 235
|
298 |
},
|
299 |
{
|
300 |
"epoch": 0.88,
|
301 |
+
"learning_rate": 6.752777059564431e-07,
|
302 |
+
"loss": 1.369,
|
303 |
"step": 240
|
304 |
},
|
305 |
{
|
306 |
"epoch": 0.9,
|
307 |
+
"learning_rate": 4.823219420526182e-07,
|
308 |
+
"loss": 1.3621,
|
309 |
"step": 245
|
310 |
},
|
311 |
{
|
312 |
"epoch": 0.92,
|
313 |
+
"learning_rate": 3.2109926012677484e-07,
|
314 |
+
"loss": 1.3649,
|
315 |
"step": 250
|
316 |
},
|
317 |
{
|
318 |
"epoch": 0.94,
|
319 |
+
"learning_rate": 1.921471959676957e-07,
|
320 |
+
"loss": 1.3646,
|
321 |
"step": 255
|
322 |
},
|
323 |
{
|
324 |
"epoch": 0.95,
|
325 |
+
"learning_rate": 9.589569124794918e-08,
|
326 |
+
"loss": 1.3552,
|
327 |
"step": 260
|
328 |
},
|
329 |
{
|
330 |
"epoch": 0.97,
|
331 |
+
"learning_rate": 3.266566004670013e-08,
|
332 |
+
"loss": 1.3669,
|
333 |
"step": 265
|
334 |
},
|
335 |
{
|
336 |
"epoch": 0.99,
|
337 |
+
"learning_rate": 2.667918883627607e-09,
|
338 |
+
"loss": 1.3681,
|
339 |
"step": 270
|
340 |
},
|
341 |
{
|
342 |
"epoch": 1.0,
|
343 |
+
"eval_loss": 1.0922234058380127,
|
344 |
+
"eval_runtime": 2386.6161,
|
345 |
+
"eval_samples_per_second": 6.466,
|
346 |
+
"eval_steps_per_second": 0.101,
|
347 |
"step": 272
|
348 |
},
|
349 |
{
|
350 |
"epoch": 1.0,
|
351 |
"step": 272,
|
352 |
"total_flos": 7631468079611904.0,
|
353 |
+
"train_loss": 1.4444872824584736,
|
354 |
+
"train_runtime": 72477.8005,
|
355 |
"train_samples_per_second": 1.924,
|
356 |
"train_steps_per_second": 0.004
|
357 |
}
|
358 |
],
|
359 |
"logging_steps": 5,
|
360 |
"max_steps": 272,
|
361 |
+
"num_input_tokens_seen": 0,
|
362 |
"num_train_epochs": 1,
|
363 |
"save_steps": 500,
|
364 |
"total_flos": 7631468079611904.0,
|
365 |
+
"train_batch_size": 16,
|
366 |
"trial_name": null,
|
367 |
"trial_params": null
|
368 |
}
|
training_args.bin
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 sha256:4c87469285d4d700c58756e9373aa90df9e87013e22d4b14969e26b47131d2b4
|
3 |
+
size 5752
|