Training in progress, epoch 7, checkpoint
Browse files- checkpoint-3703/adapter_config.json +1 -1
- checkpoint-3703/adapter_model.bin +3 -0
- checkpoint-3703/added_tokens.json +3 -3
- checkpoint-3703/optimizer.pt +2 -2
- checkpoint-3703/rng_state_0.pth +1 -1
- checkpoint-3703/rng_state_1.pth +1 -1
- checkpoint-3703/rng_state_2.pth +1 -1
- checkpoint-3703/rng_state_3.pth +1 -1
- checkpoint-3703/special_tokens_map.json +4 -12
- checkpoint-3703/tokenizer.json +0 -0
- checkpoint-3703/tokenizer.model +3 -0
- checkpoint-3703/tokenizer_config.json +17 -20
- checkpoint-3703/trainer_state.json +122 -173
- checkpoint-3703/training_args.bin +2 -2
checkpoint-3703/adapter_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"auto_mapping": null,
|
3 |
-
"base_model_name_or_path": "
|
4 |
"bias": "none",
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
|
|
1 |
{
|
2 |
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
4 |
"bias": "none",
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
checkpoint-3703/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e85ade6c7ffd589a6d69cdef902199fa87c0d5c5fb9d367218e3af0711ab72b9
|
3 |
+
size 143269386
|
checkpoint-3703/added_tokens.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0
|
5 |
}
|
checkpoint-3703/optimizer.pt
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 sha256:9b3b88178ca4b502a8f1f5c8a94ec4778ab8e41bd1da7a4b9f56927e7665b4df
|
3 |
+
size 286585234
|
checkpoint-3703/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5e0b368023843c08c28713233d613b6b1c229944d28d1fdb682d1240a11e7c7
|
3 |
size 15024
|
checkpoint-3703/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:627e3c1ad80b30481621e0bf78bb055f566c75dc5822ee123502041caf1eb912
|
3 |
size 15024
|
checkpoint-3703/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ed254c4b972f3a5b1f393a7bf34a02afa61bee1b33f44753997b0f668e4df7b
|
3 |
size 15024
|
checkpoint-3703/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b48c717e229e6aec5fdc59e5593bfa79ab00b24eeeca3ffdba3cd86b0fe0fb2
|
3 |
size 15024
|
checkpoint-3703/special_tokens_map.json
CHANGED
@@ -1,14 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
"eos_token": {
|
7 |
-
"content": "<|endoftext|>",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false
|
12 |
-
},
|
13 |
-
"pad_token": "<|endoftext|>"
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "</s>",
|
5 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
checkpoint-3703/tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3703/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-3703/tokenizer_config.json
CHANGED
@@ -1,24 +1,23 @@
|
|
1 |
{
|
2 |
-
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
-
"
|
5 |
-
"content": "
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
-
"
|
13 |
-
"content": "
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
-
"
|
21 |
-
"content": "
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
@@ -26,18 +25,16 @@
|
|
26 |
"special": true
|
27 |
}
|
28 |
},
|
29 |
-
"additional_special_tokens": [
|
30 |
-
|
31 |
-
"<|im_end|>"
|
32 |
-
],
|
33 |
-
"bos_token": null,
|
34 |
-
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
-
"eos_token": "
|
37 |
-
"
|
38 |
-
"model_max_length":
|
39 |
-
"pad_token": "
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
|
|
|
|
43 |
}
|
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"bos_token": "<s>",
|
|
|
|
|
|
|
|
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"legacy": false,
|
33 |
+
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": "</s>",
|
35 |
+
"padding_side": "left",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": true
|
40 |
}
|
checkpoint-3703/trainer_state.json
CHANGED
@@ -9,155 +9,140 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm": 7.269421577453613,
|
14 |
"learning_rate": 0.0005,
|
15 |
-
"loss": 1.
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm": 1.071650505065918,
|
21 |
"learning_rate": 0.0005,
|
22 |
-
"loss": 1.
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"grad_norm": 0.5662499070167542,
|
28 |
"learning_rate": 0.0005,
|
29 |
-
"loss":
|
30 |
"step": 300
|
31 |
},
|
32 |
{
|
33 |
-
"epoch": 0.
|
34 |
-
"grad_norm": 0.47088223695755005,
|
35 |
"learning_rate": 0.0005,
|
36 |
-
"loss": 1.
|
37 |
"step": 400
|
38 |
},
|
39 |
{
|
40 |
-
"epoch": 0.
|
41 |
-
"grad_norm": 0.3653932511806488,
|
42 |
"learning_rate": 0.0005,
|
43 |
-
"loss": 1.
|
44 |
"step": 500
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.0,
|
48 |
-
"eval_accuracy": 0.
|
49 |
-
"eval_loss": 1.
|
50 |
-
"eval_runtime":
|
51 |
-
"eval_samples_per_second":
|
52 |
-
"eval_steps_per_second":
|
53 |
"step": 529
|
54 |
},
|
55 |
{
|
56 |
"epoch": 1.0,
|
57 |
-
"eval_exact_match":
|
58 |
-
"eval_f1":
|
59 |
-
"eval_qa_bleu":
|
60 |
-
"eval_qa_exact_match": 0.
|
61 |
-
"eval_recite_bleu":
|
62 |
-
"eval_recite_exact_match": 0.
|
63 |
"step": 529
|
64 |
},
|
65 |
{
|
66 |
-
"epoch": 1.
|
67 |
-
"grad_norm": 0.5318541526794434,
|
68 |
"learning_rate": 0.0005,
|
69 |
-
"loss": 1.
|
70 |
"step": 600
|
71 |
},
|
72 |
{
|
73 |
-
"epoch": 1.
|
74 |
-
"grad_norm": 235.6529998779297,
|
75 |
"learning_rate": 0.0005,
|
76 |
-
"loss":
|
77 |
"step": 700
|
78 |
},
|
79 |
{
|
80 |
-
"epoch": 1.
|
81 |
-
"grad_norm": 0.5057249069213867,
|
82 |
"learning_rate": 0.0005,
|
83 |
-
"loss":
|
84 |
"step": 800
|
85 |
},
|
86 |
{
|
87 |
-
"epoch": 1.
|
88 |
-
"grad_norm": 0.5339187383651733,
|
89 |
"learning_rate": 0.0005,
|
90 |
-
"loss":
|
91 |
"step": 900
|
92 |
},
|
93 |
{
|
94 |
-
"epoch": 1.
|
95 |
-
"grad_norm": 0.5649825930595398,
|
96 |
"learning_rate": 0.0005,
|
97 |
-
"loss":
|
98 |
"step": 1000
|
99 |
},
|
100 |
{
|
101 |
"epoch": 2.0,
|
102 |
-
"eval_accuracy": 0.
|
103 |
-
"eval_loss":
|
104 |
-
"eval_runtime":
|
105 |
-
"eval_samples_per_second":
|
106 |
-
"eval_steps_per_second":
|
107 |
"step": 1058
|
108 |
},
|
109 |
{
|
110 |
"epoch": 2.0,
|
111 |
-
"eval_exact_match":
|
112 |
-
"eval_f1":
|
113 |
-
"eval_qa_bleu":
|
114 |
-
"eval_qa_exact_match": 0.
|
115 |
-
"eval_recite_bleu":
|
116 |
-
"eval_recite_exact_match": 0.
|
117 |
"step": 1058
|
118 |
},
|
119 |
{
|
120 |
-
"epoch": 2.
|
121 |
-
"grad_norm": 0.6042512655258179,
|
122 |
"learning_rate": 0.0005,
|
123 |
-
"loss":
|
124 |
"step": 1100
|
125 |
},
|
126 |
{
|
127 |
-
"epoch": 2.
|
128 |
-
"grad_norm": 965.2459106445312,
|
129 |
"learning_rate": 0.0005,
|
130 |
-
"loss": 8.
|
131 |
"step": 1200
|
132 |
},
|
133 |
{
|
134 |
-
"epoch": 2.
|
135 |
-
"grad_norm": 3.0128896236419678,
|
136 |
"learning_rate": 0.0005,
|
137 |
-
"loss":
|
138 |
"step": 1300
|
139 |
},
|
140 |
{
|
141 |
-
"epoch": 2.
|
142 |
-
"grad_norm": 108062179328.0,
|
143 |
"learning_rate": 0.0005,
|
144 |
-
"loss":
|
145 |
"step": 1400
|
146 |
},
|
147 |
{
|
148 |
-
"epoch": 2.
|
149 |
-
"grad_norm": 5002999889920.0,
|
150 |
"learning_rate": 0.0005,
|
151 |
-
"loss":
|
152 |
"step": 1500
|
153 |
},
|
154 |
{
|
155 |
"epoch": 3.0,
|
156 |
-
"eval_accuracy": 0.
|
157 |
-
"eval_loss":
|
158 |
-
"eval_runtime":
|
159 |
-
"eval_samples_per_second":
|
160 |
-
"eval_steps_per_second":
|
161 |
"step": 1587
|
162 |
},
|
163 |
{
|
@@ -171,54 +156,48 @@
|
|
171 |
"step": 1587
|
172 |
},
|
173 |
{
|
174 |
-
"epoch": 3.
|
175 |
-
"grad_norm": 62.19309616088867,
|
176 |
"learning_rate": 0.0005,
|
177 |
-
"loss":
|
178 |
"step": 1600
|
179 |
},
|
180 |
{
|
181 |
-
"epoch": 3.
|
182 |
-
"grad_norm": 4.109750747680664,
|
183 |
"learning_rate": 0.0005,
|
184 |
-
"loss":
|
185 |
"step": 1700
|
186 |
},
|
187 |
{
|
188 |
-
"epoch": 3.
|
189 |
-
"grad_norm": 7.620689392089844,
|
190 |
"learning_rate": 0.0005,
|
191 |
-
"loss":
|
192 |
"step": 1800
|
193 |
},
|
194 |
{
|
195 |
-
"epoch": 3.
|
196 |
-
"grad_norm": 33.092830657958984,
|
197 |
"learning_rate": 0.0005,
|
198 |
-
"loss": 7.
|
199 |
"step": 1900
|
200 |
},
|
201 |
{
|
202 |
-
"epoch": 3.
|
203 |
-
"grad_norm": 204828.203125,
|
204 |
"learning_rate": 0.0005,
|
205 |
-
"loss": 7.
|
206 |
"step": 2000
|
207 |
},
|
208 |
{
|
209 |
-
"epoch": 3.
|
210 |
-
"grad_norm": 229958729728.0,
|
211 |
"learning_rate": 0.0005,
|
212 |
-
"loss":
|
213 |
"step": 2100
|
214 |
},
|
215 |
{
|
216 |
"epoch": 4.0,
|
217 |
-
"eval_accuracy": 0.
|
218 |
-
"eval_loss":
|
219 |
-
"eval_runtime":
|
220 |
-
"eval_samples_per_second":
|
221 |
-
"eval_steps_per_second":
|
222 |
"step": 2116
|
223 |
},
|
224 |
{
|
@@ -232,47 +211,42 @@
|
|
232 |
"step": 2116
|
233 |
},
|
234 |
{
|
235 |
-
"epoch": 4.
|
236 |
-
"grad_norm": 17.098289489746094,
|
237 |
"learning_rate": 0.0005,
|
238 |
-
"loss":
|
239 |
"step": 2200
|
240 |
},
|
241 |
{
|
242 |
-
"epoch": 4.
|
243 |
-
"grad_norm": 1069.9039306640625,
|
244 |
"learning_rate": 0.0005,
|
245 |
-
"loss":
|
246 |
"step": 2300
|
247 |
},
|
248 |
{
|
249 |
-
"epoch": 4.
|
250 |
-
"grad_norm": 7.694222927093506,
|
251 |
"learning_rate": 0.0005,
|
252 |
-
"loss": 7.
|
253 |
"step": 2400
|
254 |
},
|
255 |
{
|
256 |
-
"epoch": 4.
|
257 |
-
"grad_norm": Infinity,
|
258 |
"learning_rate": 0.0005,
|
259 |
-
"loss":
|
260 |
"step": 2500
|
261 |
},
|
262 |
{
|
263 |
-
"epoch": 4.
|
264 |
-
"grad_norm": 396939770200064.0,
|
265 |
"learning_rate": 0.0005,
|
266 |
-
"loss":
|
267 |
"step": 2600
|
268 |
},
|
269 |
{
|
270 |
"epoch": 5.0,
|
271 |
-
"eval_accuracy": 0.
|
272 |
-
"eval_loss":
|
273 |
-
"eval_runtime":
|
274 |
-
"eval_samples_per_second":
|
275 |
-
"eval_steps_per_second":
|
276 |
"step": 2645
|
277 |
},
|
278 |
{
|
@@ -286,47 +260,42 @@
|
|
286 |
"step": 2645
|
287 |
},
|
288 |
{
|
289 |
-
"epoch": 5.
|
290 |
-
"grad_norm": 3.166937635134374e+18,
|
291 |
"learning_rate": 0.0005,
|
292 |
-
"loss":
|
293 |
"step": 2700
|
294 |
},
|
295 |
{
|
296 |
-
"epoch": 5.
|
297 |
-
"grad_norm": 1.8363503072027607e+18,
|
298 |
"learning_rate": 0.0005,
|
299 |
-
"loss":
|
300 |
"step": 2800
|
301 |
},
|
302 |
{
|
303 |
-
"epoch": 5.
|
304 |
-
"grad_norm": 113262112800768.0,
|
305 |
"learning_rate": 0.0005,
|
306 |
-
"loss":
|
307 |
"step": 2900
|
308 |
},
|
309 |
{
|
310 |
-
"epoch": 5.
|
311 |
-
"grad_norm": 1283434880.0,
|
312 |
"learning_rate": 0.0005,
|
313 |
-
"loss":
|
314 |
"step": 3000
|
315 |
},
|
316 |
{
|
317 |
-
"epoch": 5.
|
318 |
-
"grad_norm": 1221250.5,
|
319 |
"learning_rate": 0.0005,
|
320 |
-
"loss":
|
321 |
"step": 3100
|
322 |
},
|
323 |
{
|
324 |
"epoch": 6.0,
|
325 |
-
"eval_accuracy": 0.
|
326 |
-
"eval_loss":
|
327 |
-
"eval_runtime":
|
328 |
-
"eval_samples_per_second":
|
329 |
-
"eval_steps_per_second":
|
330 |
"step": 3174
|
331 |
},
|
332 |
{
|
@@ -340,54 +309,48 @@
|
|
340 |
"step": 3174
|
341 |
},
|
342 |
{
|
343 |
-
"epoch": 6.
|
344 |
-
"grad_norm": 2019.499267578125,
|
345 |
"learning_rate": 0.0005,
|
346 |
-
"loss":
|
347 |
"step": 3200
|
348 |
},
|
349 |
{
|
350 |
-
"epoch": 6.
|
351 |
-
"grad_norm": 164.9034881591797,
|
352 |
"learning_rate": 0.0005,
|
353 |
-
"loss":
|
354 |
"step": 3300
|
355 |
},
|
356 |
{
|
357 |
-
"epoch": 6.
|
358 |
-
"grad_norm": 434.93157958984375,
|
359 |
"learning_rate": 0.0005,
|
360 |
-
"loss": 7.
|
361 |
"step": 3400
|
362 |
},
|
363 |
{
|
364 |
-
"epoch": 6.
|
365 |
-
"grad_norm": 1324.7332763671875,
|
366 |
"learning_rate": 0.0005,
|
367 |
-
"loss": 7.
|
368 |
"step": 3500
|
369 |
},
|
370 |
{
|
371 |
-
"epoch": 6.
|
372 |
-
"grad_norm": 52531002605568.0,
|
373 |
"learning_rate": 0.0005,
|
374 |
-
"loss":
|
375 |
"step": 3600
|
376 |
},
|
377 |
{
|
378 |
-
"epoch": 6.
|
379 |
-
"grad_norm": Infinity,
|
380 |
"learning_rate": 0.0005,
|
381 |
-
"loss":
|
382 |
"step": 3700
|
383 |
},
|
384 |
{
|
385 |
"epoch": 7.0,
|
386 |
-
"eval_accuracy": 0.
|
387 |
-
"eval_loss":
|
388 |
-
"eval_runtime":
|
389 |
-
"eval_samples_per_second":
|
390 |
-
"eval_steps_per_second":
|
391 |
"step": 3703
|
392 |
},
|
393 |
{
|
@@ -403,23 +366,9 @@
|
|
403 |
],
|
404 |
"logging_steps": 100,
|
405 |
"max_steps": 26450,
|
406 |
-
"num_input_tokens_seen": 0,
|
407 |
"num_train_epochs": 50,
|
408 |
"save_steps": 500,
|
409 |
-
"
|
410 |
-
"TrainerControl": {
|
411 |
-
"args": {
|
412 |
-
"should_epoch_stop": false,
|
413 |
-
"should_evaluate": false,
|
414 |
-
"should_log": false,
|
415 |
-
"should_save": true,
|
416 |
-
"should_training_stop": false
|
417 |
-
},
|
418 |
-
"attributes": {}
|
419 |
-
}
|
420 |
-
},
|
421 |
-
"total_flos": 3.3748283761780326e+17,
|
422 |
-
"train_batch_size": 1,
|
423 |
"trial_name": null,
|
424 |
"trial_params": null
|
425 |
}
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.19,
|
|
|
13 |
"learning_rate": 0.0005,
|
14 |
+
"loss": 1.3631,
|
15 |
"step": 100
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.38,
|
|
|
19 |
"learning_rate": 0.0005,
|
20 |
+
"loss": 1.294,
|
21 |
"step": 200
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 0.57,
|
|
|
25 |
"learning_rate": 0.0005,
|
26 |
+
"loss": 1.302,
|
27 |
"step": 300
|
28 |
},
|
29 |
{
|
30 |
+
"epoch": 0.76,
|
|
|
31 |
"learning_rate": 0.0005,
|
32 |
+
"loss": 1.2626,
|
33 |
"step": 400
|
34 |
},
|
35 |
{
|
36 |
+
"epoch": 0.95,
|
|
|
37 |
"learning_rate": 0.0005,
|
38 |
+
"loss": 1.2156,
|
39 |
"step": 500
|
40 |
},
|
41 |
{
|
42 |
"epoch": 1.0,
|
43 |
+
"eval_accuracy": 0.6911294117647059,
|
44 |
+
"eval_loss": 1.012805700302124,
|
45 |
+
"eval_runtime": 7.0918,
|
46 |
+
"eval_samples_per_second": 70.504,
|
47 |
+
"eval_steps_per_second": 8.883,
|
48 |
"step": 529
|
49 |
},
|
50 |
{
|
51 |
"epoch": 1.0,
|
52 |
+
"eval_exact_match": 27.6,
|
53 |
+
"eval_f1": 35.68145743145743,
|
54 |
+
"eval_qa_bleu": 19.064111689202868,
|
55 |
+
"eval_qa_exact_match": 0.216,
|
56 |
+
"eval_recite_bleu": 17.898525975872754,
|
57 |
+
"eval_recite_exact_match": 0.006,
|
58 |
"step": 529
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 1.13,
|
|
|
62 |
"learning_rate": 0.0005,
|
63 |
+
"loss": 1.0305,
|
64 |
"step": 600
|
65 |
},
|
66 |
{
|
67 |
+
"epoch": 1.32,
|
|
|
68 |
"learning_rate": 0.0005,
|
69 |
+
"loss": 0.9199,
|
70 |
"step": 700
|
71 |
},
|
72 |
{
|
73 |
+
"epoch": 1.51,
|
|
|
74 |
"learning_rate": 0.0005,
|
75 |
+
"loss": 0.9086,
|
76 |
"step": 800
|
77 |
},
|
78 |
{
|
79 |
+
"epoch": 1.7,
|
|
|
80 |
"learning_rate": 0.0005,
|
81 |
+
"loss": 2.9245,
|
82 |
"step": 900
|
83 |
},
|
84 |
{
|
85 |
+
"epoch": 1.89,
|
|
|
86 |
"learning_rate": 0.0005,
|
87 |
+
"loss": 4.9199,
|
88 |
"step": 1000
|
89 |
},
|
90 |
{
|
91 |
"epoch": 2.0,
|
92 |
+
"eval_accuracy": 0.22922352941176471,
|
93 |
+
"eval_loss": 7.1224870681762695,
|
94 |
+
"eval_runtime": 7.7159,
|
95 |
+
"eval_samples_per_second": 64.801,
|
96 |
+
"eval_steps_per_second": 8.165,
|
97 |
"step": 1058
|
98 |
},
|
99 |
{
|
100 |
"epoch": 2.0,
|
101 |
+
"eval_exact_match": 0.0,
|
102 |
+
"eval_f1": 0.0,
|
103 |
+
"eval_qa_bleu": 0.0,
|
104 |
+
"eval_qa_exact_match": 0.0,
|
105 |
+
"eval_recite_bleu": 0.0,
|
106 |
+
"eval_recite_exact_match": 0.0,
|
107 |
"step": 1058
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 2.08,
|
|
|
111 |
"learning_rate": 0.0005,
|
112 |
+
"loss": 7.4349,
|
113 |
"step": 1100
|
114 |
},
|
115 |
{
|
116 |
+
"epoch": 2.27,
|
|
|
117 |
"learning_rate": 0.0005,
|
118 |
+
"loss": 8.0921,
|
119 |
"step": 1200
|
120 |
},
|
121 |
{
|
122 |
+
"epoch": 2.46,
|
|
|
123 |
"learning_rate": 0.0005,
|
124 |
+
"loss": 7.889,
|
125 |
"step": 1300
|
126 |
},
|
127 |
{
|
128 |
+
"epoch": 2.65,
|
|
|
129 |
"learning_rate": 0.0005,
|
130 |
+
"loss": 7.2559,
|
131 |
"step": 1400
|
132 |
},
|
133 |
{
|
134 |
+
"epoch": 2.84,
|
|
|
135 |
"learning_rate": 0.0005,
|
136 |
+
"loss": 7.3563,
|
137 |
"step": 1500
|
138 |
},
|
139 |
{
|
140 |
"epoch": 3.0,
|
141 |
+
"eval_accuracy": 0.24235294117647058,
|
142 |
+
"eval_loss": 7.308440685272217,
|
143 |
+
"eval_runtime": 7.7087,
|
144 |
+
"eval_samples_per_second": 64.862,
|
145 |
+
"eval_steps_per_second": 8.173,
|
146 |
"step": 1587
|
147 |
},
|
148 |
{
|
|
|
156 |
"step": 1587
|
157 |
},
|
158 |
{
|
159 |
+
"epoch": 3.02,
|
|
|
160 |
"learning_rate": 0.0005,
|
161 |
+
"loss": 7.2721,
|
162 |
"step": 1600
|
163 |
},
|
164 |
{
|
165 |
+
"epoch": 3.21,
|
|
|
166 |
"learning_rate": 0.0005,
|
167 |
+
"loss": 7.2743,
|
168 |
"step": 1700
|
169 |
},
|
170 |
{
|
171 |
+
"epoch": 3.4,
|
|
|
172 |
"learning_rate": 0.0005,
|
173 |
+
"loss": 7.3151,
|
174 |
"step": 1800
|
175 |
},
|
176 |
{
|
177 |
+
"epoch": 3.59,
|
|
|
178 |
"learning_rate": 0.0005,
|
179 |
+
"loss": 7.3366,
|
180 |
"step": 1900
|
181 |
},
|
182 |
{
|
183 |
+
"epoch": 3.78,
|
|
|
184 |
"learning_rate": 0.0005,
|
185 |
+
"loss": 7.3294,
|
186 |
"step": 2000
|
187 |
},
|
188 |
{
|
189 |
+
"epoch": 3.97,
|
|
|
190 |
"learning_rate": 0.0005,
|
191 |
+
"loss": 7.3158,
|
192 |
"step": 2100
|
193 |
},
|
194 |
{
|
195 |
"epoch": 4.0,
|
196 |
+
"eval_accuracy": 0.23965490196078432,
|
197 |
+
"eval_loss": 7.242833614349365,
|
198 |
+
"eval_runtime": 6.6551,
|
199 |
+
"eval_samples_per_second": 75.13,
|
200 |
+
"eval_steps_per_second": 9.466,
|
201 |
"step": 2116
|
202 |
},
|
203 |
{
|
|
|
211 |
"step": 2116
|
212 |
},
|
213 |
{
|
214 |
+
"epoch": 4.16,
|
|
|
215 |
"learning_rate": 0.0005,
|
216 |
+
"loss": 7.3307,
|
217 |
"step": 2200
|
218 |
},
|
219 |
{
|
220 |
+
"epoch": 4.35,
|
|
|
221 |
"learning_rate": 0.0005,
|
222 |
+
"loss": 7.3307,
|
223 |
"step": 2300
|
224 |
},
|
225 |
{
|
226 |
+
"epoch": 4.54,
|
|
|
227 |
"learning_rate": 0.0005,
|
228 |
+
"loss": 7.3197,
|
229 |
"step": 2400
|
230 |
},
|
231 |
{
|
232 |
+
"epoch": 4.73,
|
|
|
233 |
"learning_rate": 0.0005,
|
234 |
+
"loss": 7.3238,
|
235 |
"step": 2500
|
236 |
},
|
237 |
{
|
238 |
+
"epoch": 4.91,
|
|
|
239 |
"learning_rate": 0.0005,
|
240 |
+
"loss": 7.3017,
|
241 |
"step": 2600
|
242 |
},
|
243 |
{
|
244 |
"epoch": 5.0,
|
245 |
+
"eval_accuracy": 0.24474509803921568,
|
246 |
+
"eval_loss": 7.229503631591797,
|
247 |
+
"eval_runtime": 7.0755,
|
248 |
+
"eval_samples_per_second": 70.667,
|
249 |
+
"eval_steps_per_second": 8.904,
|
250 |
"step": 2645
|
251 |
},
|
252 |
{
|
|
|
260 |
"step": 2645
|
261 |
},
|
262 |
{
|
263 |
+
"epoch": 5.1,
|
|
|
264 |
"learning_rate": 0.0005,
|
265 |
+
"loss": 7.2926,
|
266 |
"step": 2700
|
267 |
},
|
268 |
{
|
269 |
+
"epoch": 5.29,
|
|
|
270 |
"learning_rate": 0.0005,
|
271 |
+
"loss": 7.3006,
|
272 |
"step": 2800
|
273 |
},
|
274 |
{
|
275 |
+
"epoch": 5.48,
|
|
|
276 |
"learning_rate": 0.0005,
|
277 |
+
"loss": 7.3051,
|
278 |
"step": 2900
|
279 |
},
|
280 |
{
|
281 |
+
"epoch": 5.67,
|
|
|
282 |
"learning_rate": 0.0005,
|
283 |
+
"loss": 7.2973,
|
284 |
"step": 3000
|
285 |
},
|
286 |
{
|
287 |
+
"epoch": 5.86,
|
|
|
288 |
"learning_rate": 0.0005,
|
289 |
+
"loss": 7.281,
|
290 |
"step": 3100
|
291 |
},
|
292 |
{
|
293 |
"epoch": 6.0,
|
294 |
+
"eval_accuracy": 0.24474509803921568,
|
295 |
+
"eval_loss": 7.229503631591797,
|
296 |
+
"eval_runtime": 7.1043,
|
297 |
+
"eval_samples_per_second": 70.38,
|
298 |
+
"eval_steps_per_second": 8.868,
|
299 |
"step": 3174
|
300 |
},
|
301 |
{
|
|
|
309 |
"step": 3174
|
310 |
},
|
311 |
{
|
312 |
+
"epoch": 6.05,
|
|
|
313 |
"learning_rate": 0.0005,
|
314 |
+
"loss": 7.3017,
|
315 |
"step": 3200
|
316 |
},
|
317 |
{
|
318 |
+
"epoch": 6.24,
|
|
|
319 |
"learning_rate": 0.0005,
|
320 |
+
"loss": 7.297,
|
321 |
"step": 3300
|
322 |
},
|
323 |
{
|
324 |
+
"epoch": 6.43,
|
|
|
325 |
"learning_rate": 0.0005,
|
326 |
+
"loss": 7.2877,
|
327 |
"step": 3400
|
328 |
},
|
329 |
{
|
330 |
+
"epoch": 6.62,
|
|
|
331 |
"learning_rate": 0.0005,
|
332 |
+
"loss": 7.296,
|
333 |
"step": 3500
|
334 |
},
|
335 |
{
|
336 |
+
"epoch": 6.81,
|
|
|
337 |
"learning_rate": 0.0005,
|
338 |
+
"loss": 7.2993,
|
339 |
"step": 3600
|
340 |
},
|
341 |
{
|
342 |
+
"epoch": 6.99,
|
|
|
343 |
"learning_rate": 0.0005,
|
344 |
+
"loss": 7.3056,
|
345 |
"step": 3700
|
346 |
},
|
347 |
{
|
348 |
"epoch": 7.0,
|
349 |
+
"eval_accuracy": 0.24474509803921568,
|
350 |
+
"eval_loss": 7.229503631591797,
|
351 |
+
"eval_runtime": 7.6931,
|
352 |
+
"eval_samples_per_second": 64.993,
|
353 |
+
"eval_steps_per_second": 8.189,
|
354 |
"step": 3703
|
355 |
},
|
356 |
{
|
|
|
366 |
],
|
367 |
"logging_steps": 100,
|
368 |
"max_steps": 26450,
|
|
|
369 |
"num_train_epochs": 50,
|
370 |
"save_steps": 500,
|
371 |
+
"total_flos": 7.853374087941325e+17,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
372 |
"trial_name": null,
|
373 |
"trial_params": null
|
374 |
}
|
checkpoint-3703/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:b01f751e6b30f6919dad64453b51b9e04d3c36ac30d2f54e574df56cf37b82bc
|
3 |
+
size 4728
|