Marvin
commited on
Commit
•
f436953
0
Parent(s):
Initial commit
Browse files- .gitattributes +4 -0
- README.md +129 -0
- added_tokens.json +3 -0
- all_results.json +64 -0
- config.json +36 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- special_tokens_map.json +8 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +12 -0
- trainer_state.json +768 -0
- training_args.bin +0 -0
.gitattributes
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
3 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
4 |
+
runs/** filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- de
|
4 |
+
tags:
|
5 |
+
- question-generation
|
6 |
+
- german
|
7 |
+
- text2text-generation
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- lmqg/qg_dequad
|
11 |
+
metrics:
|
12 |
+
- bleu4
|
13 |
+
- f1
|
14 |
+
- rouge
|
15 |
+
- exact_match
|
16 |
+
model-index:
|
17 |
+
- name: german-jeopardy-mt5-large-256
|
18 |
+
results:
|
19 |
+
- task:
|
20 |
+
name: Sequence-to-sequence Language Modeling
|
21 |
+
type: text2text-generation
|
22 |
+
dataset:
|
23 |
+
name: lmqg/qg_dequad
|
24 |
+
type: default
|
25 |
+
args: default
|
26 |
+
metrics:
|
27 |
+
- name: BLEU-4
|
28 |
+
type: bleu4
|
29 |
+
value: 16.43
|
30 |
+
- name: F1
|
31 |
+
type: f1
|
32 |
+
value: 42.48
|
33 |
+
- name: ROUGE-1
|
34 |
+
type: rouge1
|
35 |
+
value: 43.56
|
36 |
+
- name: ROUGE-2
|
37 |
+
type: rouge2
|
38 |
+
value: 23.78
|
39 |
+
- name: ROUGE-L
|
40 |
+
type: rougel
|
41 |
+
value: 41.81
|
42 |
+
- name: ROUGE-Lsum
|
43 |
+
type: rougelsum
|
44 |
+
value: 41.80
|
45 |
+
- name: Exact Match
|
46 |
+
type: exact_match
|
47 |
+
value: 3.13
|
48 |
+
---
|
49 |
+
|
50 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
51 |
+
should probably proofread and complete it, then remove this comment. -->
|
52 |
+
|
53 |
+
# german-jeopardy-mt5-large-256
|
54 |
+
|
55 |
+
This model is a fine-tuned version of [google/mt5-large](https://huggingface.co/google/mt5-large) on the [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) dataset.
|
56 |
+
It achieves the following results on the evaluation set:
|
57 |
+
- Loss: 1.3943
|
58 |
+
- Brevity Penalty: 0.9201
|
59 |
+
- System Length: 19195
|
60 |
+
- Reference Length: 20793
|
61 |
+
- ROUGE-1: 43.56
|
62 |
+
- ROUGE-2: 23.78
|
63 |
+
- ROUGE-L: 41.81
|
64 |
+
- ROUGE-Lsum: 41.80
|
65 |
+
- Exact Match: 3.13
|
66 |
+
- BLEU: 16.43
|
67 |
+
- F1: 42.48
|
68 |
+
|
69 |
+
## Model description
|
70 |
+
|
71 |
+
|
72 |
+
See [google/mt5-large](https://huggingface.co/google/mt5-large) for the model architecture.
|
73 |
+
The model was trained on a single NVIDIA RTX 3090 GPU with 24GB of VRAM.
|
74 |
+
|
75 |
+
## Intended uses & limitations
|
76 |
+
|
77 |
+
This model can be used for question generation on German text.
|
78 |
+
|
79 |
+
## Training and evaluation data
|
80 |
+
|
81 |
+
See [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad).
|
82 |
+
|
83 |
+
## Training procedure
|
84 |
+
|
85 |
+
### Training hyperparameters
|
86 |
+
|
87 |
+
The following hyperparameters were used during training:
|
88 |
+
- learning_rate: 0.0001
|
89 |
+
- train_batch_size: 1
|
90 |
+
- eval_batch_size: 1
|
91 |
+
- seed: 7
|
92 |
+
- gradient_accumulation_steps: 256
|
93 |
+
- total_train_batch_size: 256
|
94 |
+
- optimizer: Adafactor
|
95 |
+
- lr_scheduler_type: constant
|
96 |
+
- num_epochs: 20
|
97 |
+
|
98 |
+
### Training results
|
99 |
+
|
100 |
+
| Training Loss | Epoch | Step | Validation Loss | Counts 1 | Counts 2 | Counts 3 | Counts 4 | Totals 1 | Totals 2 | Totals 3 | Totals 4 | Precisions 1 | Precisions 2 | Precisions 3 | Precisions 4 | Brevity Penalty | System Length | Reference Length | ROUGE-1 | ROUGE-2 | ROUGE-L | ROUGE-Lsum | Exact Match | BLEU | Mean Generated Length | F1 |
|
101 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:----------------:|:-------:|:-------:|:-------:|:----------:|:-----------:|:-------:|:---------------------:|:------:|
|
102 |
+
| 5.932 | 0.99 | 36 | 2.4510 | 5614 | 1426 | 527 | 204 | 28835 | 26631 | 24427 | 22223 | 19.4694 | 5.3547 | 2.1574 | 0.918 | 1.0 | 28835 | 21250 | 0.1946 | 0.0763 | 0.1843 | 0.1843 | 0.0 | 3.7906 | 11.4306 | 0.2127 |
|
103 |
+
| 2.3089 | 1.98 | 72 | 1.3964 | 7578 | 2696 | 1244 | 580 | 17203 | 14999 | 12795 | 10591 | 44.0505 | 17.9745 | 9.7225 | 5.4763 | 0.7904 | 17203 | 21250 | 0.3312 | 0.1655 | 0.316 | 0.3162 | 0.01 | 11.3254 | 12.6583 | 0.3246 |
|
104 |
+
| 1.6778 | 3.0 | 109 | 1.2660 | 7961 | 3020 | 1480 | 747 | 17067 | 14863 | 12659 | 10455 | 46.6456 | 20.3189 | 11.6913 | 7.1449 | 0.7826 | 17067 | 21250 | 0.3608 | 0.1881 | 0.3456 | 0.3454 | 0.0195 | 13.128 | 12.4682 | 0.3517 |
|
105 |
+
| 1.5383 | 3.99 | 145 | 1.2212 | 7948 | 3121 | 1558 | 796 | 16694 | 14490 | 12286 | 10082 | 47.6099 | 21.539 | 12.6811 | 7.8953 | 0.7612 | 16694 | 21250 | 0.3663 | 0.1989 | 0.3523 | 0.352 | 0.024 | 13.625 | 12.221 | 0.3554 |
|
106 |
+
| 1.423 | 4.97 | 181 | 1.1706 | 8746 | 3590 | 1840 | 963 | 17765 | 15561 | 13357 | 11153 | 49.2316 | 23.0705 | 13.7755 | 8.6344 | 0.8219 | 17765 | 21250 | 0.4033 | 0.2224 | 0.3876 | 0.3874 | 0.0304 | 15.7567 | 13.0277 | 0.3941 |
|
107 |
+
| 1.2861 | 5.99 | 218 | 1.1327 | 8885 | 3646 | 1864 | 1005 | 17406 | 15202 | 12998 | 10794 | 51.0456 | 23.9837 | 14.3407 | 9.3107 | 0.8018 | 17406 | 21250 | 0.4181 | 0.2295 | 0.4022 | 0.402 | 0.0331 | 16.123 | 12.9142 | 0.4092 |
|
108 |
+
| 1.2372 | 6.98 | 254 | 1.1248 | 9122 | 3824 | 1997 | 1084 | 17310 | 15106 | 12902 | 10698 | 52.6979 | 25.3144 | 15.4782 | 10.1327 | 0.7964 | 17310 | 21250 | 0.4313 | 0.239 | 0.4175 | 0.4172 | 0.0358 | 17.0334 | 12.8412 | 0.4236 |
|
109 |
+
| 1.1307 | 8.0 | 291 | 1.0998 | 9423 | 4019 | 2136 | 1190 | 18074 | 15870 | 13666 | 11462 | 52.1357 | 25.3245 | 15.63 | 10.3821 | 0.8389 | 18074 | 21250 | 0.441 | 0.249 | 0.4255 | 0.4252 | 0.0404 | 18.0474 | 13.4138 | 0.4327 |
|
110 |
+
| 1.0982 | 8.99 | 327 | 1.1052 | 9450 | 4003 | 2147 | 1184 | 18145 | 15941 | 13737 | 11533 | 52.0805 | 25.1113 | 15.6293 | 10.2662 | 0.8427 | 18145 | 21250 | 0.4427 | 0.2492 | 0.4266 | 0.4261 | 0.0426 | 18.0367 | 13.4465 | 0.4344 |
|
111 |
+
| 1.0449 | 9.98 | 363 | 1.0996 | 9471 | 4036 | 2149 | 1180 | 18067 | 15863 | 13659 | 11455 | 52.4215 | 25.4429 | 15.7332 | 10.3012 | 0.8385 | 18067 | 21250 | 0.4422 | 0.2477 | 0.4261 | 0.4257 | 0.0404 | 18.0793 | 13.333 | 0.4341 |
|
112 |
+
| 0.9686 | 10.99 | 400 | 1.1012 | 9612 | 4165 | 2240 | 1233 | 17983 | 15779 | 13575 | 11371 | 53.4505 | 26.3958 | 16.5009 | 10.8434 | 0.8339 | 17983 | 21250 | 0.4534 | 0.2591 | 0.4381 | 0.4378 | 0.0449 | 18.6914 | 13.3534 | 0.4458 |
|
113 |
+
| 0.9465 | 11.98 | 436 | 1.1027 | 9670 | 4154 | 2229 | 1239 | 18217 | 16013 | 13809 | 11605 | 53.0823 | 25.9414 | 16.1416 | 10.6764 | 0.8466 | 18217 | 21250 | 0.4531 | 0.258 | 0.4377 | 0.4374 | 0.0445 | 18.6863 | 13.5912 | 0.4452 |
|
114 |
+
| 0.9025 | 12.97 | 472 | 1.1124 | 9627 | 4155 | 2241 | 1247 | 18076 | 15872 | 13668 | 11464 | 53.2585 | 26.1782 | 16.396 | 10.8775 | 0.839 | 18076 | 21250 | 0.4531 | 0.2583 | 0.4386 | 0.4382 | 0.0436 | 18.7344 | 13.5259 | 0.4452 |
|
115 |
+
| 0.8402 | 13.99 | 509 | 1.1392 | 9425 | 4071 | 2176 | 1207 | 17339 | 15135 | 12931 | 10727 | 54.3572 | 26.8979 | 16.8278 | 11.252 | 0.7981 | 17339 | 21250 | 0.4495 | 0.2568 | 0.4365 | 0.4358 | 0.0445 | 18.3062 | 12.9129 | 0.4417 |
|
116 |
+
| 0.8282 | 14.98 | 545 | 1.1227 | 9803 | 4274 | 2316 | 1305 | 18652 | 16448 | 14244 | 12040 | 52.5574 | 25.9849 | 16.2595 | 10.8389 | 0.87 | 18652 | 21250 | 0.4573 | 0.2627 | 0.4418 | 0.4414 | 0.0463 | 19.2695 | 14.0104 | 0.4496 |
|
117 |
+
| 0.7694 | 16.0 | 582 | 1.1394 | 9740 | 4240 | 2299 | 1296 | 18281 | 16077 | 13873 | 11669 | 53.2794 | 26.3731 | 16.5718 | 11.1064 | 0.8501 | 18281 | 21250 | 0.4572 | 0.2629 | 0.4411 | 0.4412 | 0.0476 | 19.1704 | 13.6475 | 0.4492 |
|
118 |
+
| 0.7589 | 16.99 | 618 | 1.1497 | 9663 | 4140 | 2214 | 1232 | 18412 | 16208 | 14004 | 11800 | 52.4821 | 25.5429 | 15.8098 | 10.4407 | 0.8572 | 18412 | 21250 | 0.4515 | 0.2561 | 0.4359 | 0.4358 | 0.044 | 18.5906 | 13.7926 | 0.4432 |
|
119 |
+
| 0.724 | 17.98 | 654 | 1.1680 | 9743 | 4246 | 2316 | 1300 | 18402 | 16198 | 13994 | 11790 | 52.9453 | 26.2131 | 16.5499 | 11.0263 | 0.8566 | 18402 | 21250 | 0.4562 | 0.2625 | 0.4408 | 0.441 | 0.0472 | 19.2167 | 13.7214 | 0.4474 |
|
120 |
+
| 0.6755 | 18.99 | 691 | 1.1874 | 9722 | 4266 | 2351 | 1341 | 18272 | 16068 | 13864 | 11660 | 53.2071 | 26.5497 | 16.9576 | 11.5009 | 0.8496 | 18272 | 21250 | 0.4559 | 0.2639 | 0.4417 | 0.4413 | 0.0495 | 19.4647 | 13.6071 | 0.4469 |
|
121 |
+
| 0.657 | 19.79 | 720 | 1.1845 | 9920 | 4361 | 2402 | 1373 | 18884 | 16680 | 14476 | 12272 | 52.5312 | 26.1451 | 16.593 | 11.1881 | 0.8822 | 18884 | 21250 | 0.4594 | 0.2647 | 0.4423 | 0.4421 | 0.0467 | 19.8248 | 14.2001 | 0.4508 |
|
122 |
+
|
123 |
+
|
124 |
+
### Framework versions
|
125 |
+
|
126 |
+
- Transformers 4.32.1
|
127 |
+
- Pytorch 2.1.0
|
128 |
+
- Datasets 2.12.0
|
129 |
+
- Tokenizers 0.13.3
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<hl>": 250100
|
3 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 19.79,
|
3 |
+
"eval_bleu": 19.8248,
|
4 |
+
"eval_bp": 0.8822,
|
5 |
+
"eval_counts_1": 9920,
|
6 |
+
"eval_counts_2": 4361,
|
7 |
+
"eval_counts_3": 2402,
|
8 |
+
"eval_counts_4": 1373,
|
9 |
+
"eval_exact_match": 0.0467,
|
10 |
+
"eval_f1": 0.4508,
|
11 |
+
"eval_gen_len": 14.2001,
|
12 |
+
"eval_loss": 1.1845453977584839,
|
13 |
+
"eval_precisions_1": 52.5312,
|
14 |
+
"eval_precisions_2": 26.1451,
|
15 |
+
"eval_precisions_3": 16.593,
|
16 |
+
"eval_precisions_4": 11.1881,
|
17 |
+
"eval_ref_len": 21250,
|
18 |
+
"eval_rouge1": 0.4594,
|
19 |
+
"eval_rouge2": 0.2647,
|
20 |
+
"eval_rougeL": 0.4423,
|
21 |
+
"eval_rougeLsum": 0.4421,
|
22 |
+
"eval_runtime": 2997.7936,
|
23 |
+
"eval_samples": 2204,
|
24 |
+
"eval_samples_per_second": 0.735,
|
25 |
+
"eval_steps_per_second": 0.735,
|
26 |
+
"eval_sys_len": 18884,
|
27 |
+
"eval_totals_1": 18884,
|
28 |
+
"eval_totals_2": 16680,
|
29 |
+
"eval_totals_3": 14476,
|
30 |
+
"eval_totals_4": 12272,
|
31 |
+
"predict_bleu": 15.9031,
|
32 |
+
"predict_bp": 0.9242,
|
33 |
+
"predict_counts_1": 9231,
|
34 |
+
"predict_counts_2": 3627,
|
35 |
+
"predict_counts_3": 1778,
|
36 |
+
"predict_counts_4": 912,
|
37 |
+
"predict_exact_match": 0.0304,
|
38 |
+
"predict_f1": 0.4153,
|
39 |
+
"predict_gen_len": 14.6175,
|
40 |
+
"predict_loss": 1.4399399757385254,
|
41 |
+
"predict_precisions_1": 47.896,
|
42 |
+
"predict_precisions_2": 21.249,
|
43 |
+
"predict_precisions_3": 11.961,
|
44 |
+
"predict_precisions_4": 7.2032,
|
45 |
+
"predict_ref_len": 20793,
|
46 |
+
"predict_rouge1": 0.4255,
|
47 |
+
"predict_rouge2": 0.2307,
|
48 |
+
"predict_rougeL": 0.4079,
|
49 |
+
"predict_rougeLsum": 0.408,
|
50 |
+
"predict_runtime": 2027.9694,
|
51 |
+
"predict_samples": 2204,
|
52 |
+
"predict_samples_per_second": 1.087,
|
53 |
+
"predict_steps_per_second": 1.087,
|
54 |
+
"predict_sys_len": 19273,
|
55 |
+
"predict_totals_1": 19273,
|
56 |
+
"predict_totals_2": 17069,
|
57 |
+
"predict_totals_3": 14865,
|
58 |
+
"predict_totals_4": 12661,
|
59 |
+
"train_loss": 1.3412119759453667,
|
60 |
+
"train_runtime": 128063.7495,
|
61 |
+
"train_samples": 9314,
|
62 |
+
"train_samples_per_second": 1.455,
|
63 |
+
"train_steps_per_second": 0.006
|
64 |
+
}
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mt5-large",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2816,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"length_penalty": 0.0,
|
20 |
+
"max_length": 64,
|
21 |
+
"model_type": "mt5",
|
22 |
+
"num_beams": 4,
|
23 |
+
"num_decoder_layers": 24,
|
24 |
+
"num_heads": 16,
|
25 |
+
"num_layers": 24,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"relative_attention_max_distance": 128,
|
29 |
+
"relative_attention_num_buckets": 32,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"tokenizer_class": "T5Tokenizer",
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.32.1",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 250112
|
36 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"length_penalty": 0.0,
|
5 |
+
"max_length": 64,
|
6 |
+
"num_beams": 4,
|
7 |
+
"pad_token_id": 0,
|
8 |
+
"transformers_version": "4.32.1"
|
9 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0046fba082045672b0afcf4bdb7540c6c186e9ab9136ef77b08f18b67134697b
|
3 |
+
size 4918393736
|
special_tokens_map.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<hl>"
|
4 |
+
],
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"unk_token": "<unk>"
|
8 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef4273f90fa3341fdb81c66eb7973b1651a8183e57c8ab9e9144aac61b48f9f
|
3 |
+
size 16330550
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"extra_ids": 0,
|
6 |
+
"legacy": true,
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"sp_model_kwargs": {},
|
10 |
+
"tokenizer_class": "T5Tokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,768 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 19.789564097058193,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 720,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.99,
|
13 |
+
"learning_rate": 0.0001,
|
14 |
+
"loss": 5.932,
|
15 |
+
"step": 36
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.99,
|
19 |
+
"eval_bleu": 3.7906,
|
20 |
+
"eval_bp": 1.0,
|
21 |
+
"eval_counts_1": 5614,
|
22 |
+
"eval_counts_2": 1426,
|
23 |
+
"eval_counts_3": 527,
|
24 |
+
"eval_counts_4": 204,
|
25 |
+
"eval_exact_match": 0.0,
|
26 |
+
"eval_f1": 0.2127,
|
27 |
+
"eval_gen_len": 11.4306,
|
28 |
+
"eval_loss": 2.450988292694092,
|
29 |
+
"eval_precisions_1": 19.4694,
|
30 |
+
"eval_precisions_2": 5.3547,
|
31 |
+
"eval_precisions_3": 2.1574,
|
32 |
+
"eval_precisions_4": 0.918,
|
33 |
+
"eval_ref_len": 21250,
|
34 |
+
"eval_rouge1": 0.1946,
|
35 |
+
"eval_rouge2": 0.0763,
|
36 |
+
"eval_rougeL": 0.1843,
|
37 |
+
"eval_rougeLsum": 0.1843,
|
38 |
+
"eval_runtime": 1846.0551,
|
39 |
+
"eval_samples_per_second": 1.194,
|
40 |
+
"eval_steps_per_second": 1.194,
|
41 |
+
"eval_sys_len": 28835,
|
42 |
+
"eval_totals_1": 28835,
|
43 |
+
"eval_totals_2": 26631,
|
44 |
+
"eval_totals_3": 24427,
|
45 |
+
"eval_totals_4": 22223,
|
46 |
+
"step": 36
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.98,
|
50 |
+
"learning_rate": 0.0001,
|
51 |
+
"loss": 2.3089,
|
52 |
+
"step": 72
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 1.98,
|
56 |
+
"eval_bleu": 11.3254,
|
57 |
+
"eval_bp": 0.7904,
|
58 |
+
"eval_counts_1": 7578,
|
59 |
+
"eval_counts_2": 2696,
|
60 |
+
"eval_counts_3": 1244,
|
61 |
+
"eval_counts_4": 580,
|
62 |
+
"eval_exact_match": 0.01,
|
63 |
+
"eval_f1": 0.3246,
|
64 |
+
"eval_gen_len": 12.6583,
|
65 |
+
"eval_loss": 1.3963948488235474,
|
66 |
+
"eval_precisions_1": 44.0505,
|
67 |
+
"eval_precisions_2": 17.9745,
|
68 |
+
"eval_precisions_3": 9.7225,
|
69 |
+
"eval_precisions_4": 5.4763,
|
70 |
+
"eval_ref_len": 21250,
|
71 |
+
"eval_rouge1": 0.3312,
|
72 |
+
"eval_rouge2": 0.1655,
|
73 |
+
"eval_rougeL": 0.316,
|
74 |
+
"eval_rougeLsum": 0.3162,
|
75 |
+
"eval_runtime": 1912.8668,
|
76 |
+
"eval_samples_per_second": 1.152,
|
77 |
+
"eval_steps_per_second": 1.152,
|
78 |
+
"eval_sys_len": 17203,
|
79 |
+
"eval_totals_1": 17203,
|
80 |
+
"eval_totals_2": 14999,
|
81 |
+
"eval_totals_3": 12795,
|
82 |
+
"eval_totals_4": 10591,
|
83 |
+
"step": 72
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 3.0,
|
87 |
+
"learning_rate": 0.0001,
|
88 |
+
"loss": 1.6778,
|
89 |
+
"step": 109
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 3.0,
|
93 |
+
"eval_bleu": 13.128,
|
94 |
+
"eval_bp": 0.7826,
|
95 |
+
"eval_counts_1": 7961,
|
96 |
+
"eval_counts_2": 3020,
|
97 |
+
"eval_counts_3": 1480,
|
98 |
+
"eval_counts_4": 747,
|
99 |
+
"eval_exact_match": 0.0195,
|
100 |
+
"eval_f1": 0.3517,
|
101 |
+
"eval_gen_len": 12.4682,
|
102 |
+
"eval_loss": 1.2659858465194702,
|
103 |
+
"eval_precisions_1": 46.6456,
|
104 |
+
"eval_precisions_2": 20.3189,
|
105 |
+
"eval_precisions_3": 11.6913,
|
106 |
+
"eval_precisions_4": 7.1449,
|
107 |
+
"eval_ref_len": 21250,
|
108 |
+
"eval_rouge1": 0.3608,
|
109 |
+
"eval_rouge2": 0.1881,
|
110 |
+
"eval_rougeL": 0.3456,
|
111 |
+
"eval_rougeLsum": 0.3454,
|
112 |
+
"eval_runtime": 1864.6637,
|
113 |
+
"eval_samples_per_second": 1.182,
|
114 |
+
"eval_steps_per_second": 1.182,
|
115 |
+
"eval_sys_len": 17067,
|
116 |
+
"eval_totals_1": 17067,
|
117 |
+
"eval_totals_2": 14863,
|
118 |
+
"eval_totals_3": 12659,
|
119 |
+
"eval_totals_4": 10455,
|
120 |
+
"step": 109
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 3.99,
|
124 |
+
"learning_rate": 0.0001,
|
125 |
+
"loss": 1.5383,
|
126 |
+
"step": 145
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 3.99,
|
130 |
+
"eval_bleu": 13.625,
|
131 |
+
"eval_bp": 0.7612,
|
132 |
+
"eval_counts_1": 7948,
|
133 |
+
"eval_counts_2": 3121,
|
134 |
+
"eval_counts_3": 1558,
|
135 |
+
"eval_counts_4": 796,
|
136 |
+
"eval_exact_match": 0.024,
|
137 |
+
"eval_f1": 0.3554,
|
138 |
+
"eval_gen_len": 12.221,
|
139 |
+
"eval_loss": 1.2212449312210083,
|
140 |
+
"eval_precisions_1": 47.6099,
|
141 |
+
"eval_precisions_2": 21.539,
|
142 |
+
"eval_precisions_3": 12.6811,
|
143 |
+
"eval_precisions_4": 7.8953,
|
144 |
+
"eval_ref_len": 21250,
|
145 |
+
"eval_rouge1": 0.3663,
|
146 |
+
"eval_rouge2": 0.1989,
|
147 |
+
"eval_rougeL": 0.3523,
|
148 |
+
"eval_rougeLsum": 0.352,
|
149 |
+
"eval_runtime": 1862.6167,
|
150 |
+
"eval_samples_per_second": 1.183,
|
151 |
+
"eval_steps_per_second": 1.183,
|
152 |
+
"eval_sys_len": 16694,
|
153 |
+
"eval_totals_1": 16694,
|
154 |
+
"eval_totals_2": 14490,
|
155 |
+
"eval_totals_3": 12286,
|
156 |
+
"eval_totals_4": 10082,
|
157 |
+
"step": 145
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 4.97,
|
161 |
+
"learning_rate": 0.0001,
|
162 |
+
"loss": 1.423,
|
163 |
+
"step": 181
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 4.97,
|
167 |
+
"eval_bleu": 15.7567,
|
168 |
+
"eval_bp": 0.8219,
|
169 |
+
"eval_counts_1": 8746,
|
170 |
+
"eval_counts_2": 3590,
|
171 |
+
"eval_counts_3": 1840,
|
172 |
+
"eval_counts_4": 963,
|
173 |
+
"eval_exact_match": 0.0304,
|
174 |
+
"eval_f1": 0.3941,
|
175 |
+
"eval_gen_len": 13.0277,
|
176 |
+
"eval_loss": 1.1706066131591797,
|
177 |
+
"eval_precisions_1": 49.2316,
|
178 |
+
"eval_precisions_2": 23.0705,
|
179 |
+
"eval_precisions_3": 13.7755,
|
180 |
+
"eval_precisions_4": 8.6344,
|
181 |
+
"eval_ref_len": 21250,
|
182 |
+
"eval_rouge1": 0.4033,
|
183 |
+
"eval_rouge2": 0.2224,
|
184 |
+
"eval_rougeL": 0.3876,
|
185 |
+
"eval_rougeLsum": 0.3874,
|
186 |
+
"eval_runtime": 1923.5708,
|
187 |
+
"eval_samples_per_second": 1.146,
|
188 |
+
"eval_steps_per_second": 1.146,
|
189 |
+
"eval_sys_len": 17765,
|
190 |
+
"eval_totals_1": 17765,
|
191 |
+
"eval_totals_2": 15561,
|
192 |
+
"eval_totals_3": 13357,
|
193 |
+
"eval_totals_4": 11153,
|
194 |
+
"step": 181
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 5.99,
|
198 |
+
"learning_rate": 0.0001,
|
199 |
+
"loss": 1.2861,
|
200 |
+
"step": 218
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 5.99,
|
204 |
+
"eval_bleu": 16.123,
|
205 |
+
"eval_bp": 0.8018,
|
206 |
+
"eval_counts_1": 8885,
|
207 |
+
"eval_counts_2": 3646,
|
208 |
+
"eval_counts_3": 1864,
|
209 |
+
"eval_counts_4": 1005,
|
210 |
+
"eval_exact_match": 0.0331,
|
211 |
+
"eval_f1": 0.4092,
|
212 |
+
"eval_gen_len": 12.9142,
|
213 |
+
"eval_loss": 1.1327459812164307,
|
214 |
+
"eval_precisions_1": 51.0456,
|
215 |
+
"eval_precisions_2": 23.9837,
|
216 |
+
"eval_precisions_3": 14.3407,
|
217 |
+
"eval_precisions_4": 9.3107,
|
218 |
+
"eval_ref_len": 21250,
|
219 |
+
"eval_rouge1": 0.4181,
|
220 |
+
"eval_rouge2": 0.2295,
|
221 |
+
"eval_rougeL": 0.4022,
|
222 |
+
"eval_rougeLsum": 0.402,
|
223 |
+
"eval_runtime": 2271.0986,
|
224 |
+
"eval_samples_per_second": 0.97,
|
225 |
+
"eval_steps_per_second": 0.97,
|
226 |
+
"eval_sys_len": 17406,
|
227 |
+
"eval_totals_1": 17406,
|
228 |
+
"eval_totals_2": 15202,
|
229 |
+
"eval_totals_3": 12998,
|
230 |
+
"eval_totals_4": 10794,
|
231 |
+
"step": 218
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 6.98,
|
235 |
+
"learning_rate": 0.0001,
|
236 |
+
"loss": 1.2372,
|
237 |
+
"step": 254
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 6.98,
|
241 |
+
"eval_bleu": 17.0334,
|
242 |
+
"eval_bp": 0.7964,
|
243 |
+
"eval_counts_1": 9122,
|
244 |
+
"eval_counts_2": 3824,
|
245 |
+
"eval_counts_3": 1997,
|
246 |
+
"eval_counts_4": 1084,
|
247 |
+
"eval_exact_match": 0.0358,
|
248 |
+
"eval_f1": 0.4236,
|
249 |
+
"eval_gen_len": 12.8412,
|
250 |
+
"eval_loss": 1.1248232126235962,
|
251 |
+
"eval_precisions_1": 52.6979,
|
252 |
+
"eval_precisions_2": 25.3144,
|
253 |
+
"eval_precisions_3": 15.4782,
|
254 |
+
"eval_precisions_4": 10.1327,
|
255 |
+
"eval_ref_len": 21250,
|
256 |
+
"eval_rouge1": 0.4313,
|
257 |
+
"eval_rouge2": 0.239,
|
258 |
+
"eval_rougeL": 0.4175,
|
259 |
+
"eval_rougeLsum": 0.4172,
|
260 |
+
"eval_runtime": 2069.7482,
|
261 |
+
"eval_samples_per_second": 1.065,
|
262 |
+
"eval_steps_per_second": 1.065,
|
263 |
+
"eval_sys_len": 17310,
|
264 |
+
"eval_totals_1": 17310,
|
265 |
+
"eval_totals_2": 15106,
|
266 |
+
"eval_totals_3": 12902,
|
267 |
+
"eval_totals_4": 10698,
|
268 |
+
"step": 254
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 8.0,
|
272 |
+
"learning_rate": 0.0001,
|
273 |
+
"loss": 1.1307,
|
274 |
+
"step": 291
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 8.0,
|
278 |
+
"eval_bleu": 18.0474,
|
279 |
+
"eval_bp": 0.8389,
|
280 |
+
"eval_counts_1": 9423,
|
281 |
+
"eval_counts_2": 4019,
|
282 |
+
"eval_counts_3": 2136,
|
283 |
+
"eval_counts_4": 1190,
|
284 |
+
"eval_exact_match": 0.0404,
|
285 |
+
"eval_f1": 0.4327,
|
286 |
+
"eval_gen_len": 13.4138,
|
287 |
+
"eval_loss": 1.0998262166976929,
|
288 |
+
"eval_precisions_1": 52.1357,
|
289 |
+
"eval_precisions_2": 25.3245,
|
290 |
+
"eval_precisions_3": 15.63,
|
291 |
+
"eval_precisions_4": 10.3821,
|
292 |
+
"eval_ref_len": 21250,
|
293 |
+
"eval_rouge1": 0.441,
|
294 |
+
"eval_rouge2": 0.249,
|
295 |
+
"eval_rougeL": 0.4255,
|
296 |
+
"eval_rougeLsum": 0.4252,
|
297 |
+
"eval_runtime": 2305.9504,
|
298 |
+
"eval_samples_per_second": 0.956,
|
299 |
+
"eval_steps_per_second": 0.956,
|
300 |
+
"eval_sys_len": 18074,
|
301 |
+
"eval_totals_1": 18074,
|
302 |
+
"eval_totals_2": 15870,
|
303 |
+
"eval_totals_3": 13666,
|
304 |
+
"eval_totals_4": 11462,
|
305 |
+
"step": 291
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 8.99,
|
309 |
+
"learning_rate": 0.0001,
|
310 |
+
"loss": 1.0982,
|
311 |
+
"step": 327
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 8.99,
|
315 |
+
"eval_bleu": 18.0367,
|
316 |
+
"eval_bp": 0.8427,
|
317 |
+
"eval_counts_1": 9450,
|
318 |
+
"eval_counts_2": 4003,
|
319 |
+
"eval_counts_3": 2147,
|
320 |
+
"eval_counts_4": 1184,
|
321 |
+
"eval_exact_match": 0.0426,
|
322 |
+
"eval_f1": 0.4344,
|
323 |
+
"eval_gen_len": 13.4465,
|
324 |
+
"eval_loss": 1.1051570177078247,
|
325 |
+
"eval_precisions_1": 52.0805,
|
326 |
+
"eval_precisions_2": 25.1113,
|
327 |
+
"eval_precisions_3": 15.6293,
|
328 |
+
"eval_precisions_4": 10.2662,
|
329 |
+
"eval_ref_len": 21250,
|
330 |
+
"eval_rouge1": 0.4427,
|
331 |
+
"eval_rouge2": 0.2492,
|
332 |
+
"eval_rougeL": 0.4266,
|
333 |
+
"eval_rougeLsum": 0.4261,
|
334 |
+
"eval_runtime": 2511.4033,
|
335 |
+
"eval_samples_per_second": 0.878,
|
336 |
+
"eval_steps_per_second": 0.878,
|
337 |
+
"eval_sys_len": 18145,
|
338 |
+
"eval_totals_1": 18145,
|
339 |
+
"eval_totals_2": 15941,
|
340 |
+
"eval_totals_3": 13737,
|
341 |
+
"eval_totals_4": 11533,
|
342 |
+
"step": 327
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 9.98,
|
346 |
+
"learning_rate": 0.0001,
|
347 |
+
"loss": 1.0449,
|
348 |
+
"step": 363
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 9.98,
|
352 |
+
"eval_bleu": 18.0793,
|
353 |
+
"eval_bp": 0.8385,
|
354 |
+
"eval_counts_1": 9471,
|
355 |
+
"eval_counts_2": 4036,
|
356 |
+
"eval_counts_3": 2149,
|
357 |
+
"eval_counts_4": 1180,
|
358 |
+
"eval_exact_match": 0.0404,
|
359 |
+
"eval_f1": 0.4341,
|
360 |
+
"eval_gen_len": 13.333,
|
361 |
+
"eval_loss": 1.0995820760726929,
|
362 |
+
"eval_precisions_1": 52.4215,
|
363 |
+
"eval_precisions_2": 25.4429,
|
364 |
+
"eval_precisions_3": 15.7332,
|
365 |
+
"eval_precisions_4": 10.3012,
|
366 |
+
"eval_ref_len": 21250,
|
367 |
+
"eval_rouge1": 0.4422,
|
368 |
+
"eval_rouge2": 0.2477,
|
369 |
+
"eval_rougeL": 0.4261,
|
370 |
+
"eval_rougeLsum": 0.4257,
|
371 |
+
"eval_runtime": 1973.5312,
|
372 |
+
"eval_samples_per_second": 1.117,
|
373 |
+
"eval_steps_per_second": 1.117,
|
374 |
+
"eval_sys_len": 18067,
|
375 |
+
"eval_totals_1": 18067,
|
376 |
+
"eval_totals_2": 15863,
|
377 |
+
"eval_totals_3": 13659,
|
378 |
+
"eval_totals_4": 11455,
|
379 |
+
"step": 363
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 10.99,
|
383 |
+
"learning_rate": 0.0001,
|
384 |
+
"loss": 0.9686,
|
385 |
+
"step": 400
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 10.99,
|
389 |
+
"eval_bleu": 18.6914,
|
390 |
+
"eval_bp": 0.8339,
|
391 |
+
"eval_counts_1": 9612,
|
392 |
+
"eval_counts_2": 4165,
|
393 |
+
"eval_counts_3": 2240,
|
394 |
+
"eval_counts_4": 1233,
|
395 |
+
"eval_exact_match": 0.0449,
|
396 |
+
"eval_f1": 0.4458,
|
397 |
+
"eval_gen_len": 13.3534,
|
398 |
+
"eval_loss": 1.1012390851974487,
|
399 |
+
"eval_precisions_1": 53.4505,
|
400 |
+
"eval_precisions_2": 26.3958,
|
401 |
+
"eval_precisions_3": 16.5009,
|
402 |
+
"eval_precisions_4": 10.8434,
|
403 |
+
"eval_ref_len": 21250,
|
404 |
+
"eval_rouge1": 0.4534,
|
405 |
+
"eval_rouge2": 0.2591,
|
406 |
+
"eval_rougeL": 0.4381,
|
407 |
+
"eval_rougeLsum": 0.4378,
|
408 |
+
"eval_runtime": 2028.4468,
|
409 |
+
"eval_samples_per_second": 1.087,
|
410 |
+
"eval_steps_per_second": 1.087,
|
411 |
+
"eval_sys_len": 17983,
|
412 |
+
"eval_totals_1": 17983,
|
413 |
+
"eval_totals_2": 15779,
|
414 |
+
"eval_totals_3": 13575,
|
415 |
+
"eval_totals_4": 11371,
|
416 |
+
"step": 400
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 11.98,
|
420 |
+
"learning_rate": 0.0001,
|
421 |
+
"loss": 0.9465,
|
422 |
+
"step": 436
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 11.98,
|
426 |
+
"eval_bleu": 18.6863,
|
427 |
+
"eval_bp": 0.8466,
|
428 |
+
"eval_counts_1": 9670,
|
429 |
+
"eval_counts_2": 4154,
|
430 |
+
"eval_counts_3": 2229,
|
431 |
+
"eval_counts_4": 1239,
|
432 |
+
"eval_exact_match": 0.0445,
|
433 |
+
"eval_f1": 0.4452,
|
434 |
+
"eval_gen_len": 13.5912,
|
435 |
+
"eval_loss": 1.1026833057403564,
|
436 |
+
"eval_precisions_1": 53.0823,
|
437 |
+
"eval_precisions_2": 25.9414,
|
438 |
+
"eval_precisions_3": 16.1416,
|
439 |
+
"eval_precisions_4": 10.6764,
|
440 |
+
"eval_ref_len": 21250,
|
441 |
+
"eval_rouge1": 0.4531,
|
442 |
+
"eval_rouge2": 0.258,
|
443 |
+
"eval_rougeL": 0.4377,
|
444 |
+
"eval_rougeLsum": 0.4374,
|
445 |
+
"eval_runtime": 4413.1713,
|
446 |
+
"eval_samples_per_second": 0.499,
|
447 |
+
"eval_steps_per_second": 0.499,
|
448 |
+
"eval_sys_len": 18217,
|
449 |
+
"eval_totals_1": 18217,
|
450 |
+
"eval_totals_2": 16013,
|
451 |
+
"eval_totals_3": 13809,
|
452 |
+
"eval_totals_4": 11605,
|
453 |
+
"step": 436
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 12.97,
|
457 |
+
"learning_rate": 0.0001,
|
458 |
+
"loss": 0.9025,
|
459 |
+
"step": 472
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 12.97,
|
463 |
+
"eval_bleu": 18.7344,
|
464 |
+
"eval_bp": 0.839,
|
465 |
+
"eval_counts_1": 9627,
|
466 |
+
"eval_counts_2": 4155,
|
467 |
+
"eval_counts_3": 2241,
|
468 |
+
"eval_counts_4": 1247,
|
469 |
+
"eval_exact_match": 0.0436,
|
470 |
+
"eval_f1": 0.4452,
|
471 |
+
"eval_gen_len": 13.5259,
|
472 |
+
"eval_loss": 1.11244535446167,
|
473 |
+
"eval_precisions_1": 53.2585,
|
474 |
+
"eval_precisions_2": 26.1782,
|
475 |
+
"eval_precisions_3": 16.396,
|
476 |
+
"eval_precisions_4": 10.8775,
|
477 |
+
"eval_ref_len": 21250,
|
478 |
+
"eval_rouge1": 0.4531,
|
479 |
+
"eval_rouge2": 0.2583,
|
480 |
+
"eval_rougeL": 0.4386,
|
481 |
+
"eval_rougeLsum": 0.4382,
|
482 |
+
"eval_runtime": 3852.502,
|
483 |
+
"eval_samples_per_second": 0.572,
|
484 |
+
"eval_steps_per_second": 0.572,
|
485 |
+
"eval_sys_len": 18076,
|
486 |
+
"eval_totals_1": 18076,
|
487 |
+
"eval_totals_2": 15872,
|
488 |
+
"eval_totals_3": 13668,
|
489 |
+
"eval_totals_4": 11464,
|
490 |
+
"step": 472
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 13.99,
|
494 |
+
"learning_rate": 0.0001,
|
495 |
+
"loss": 0.8402,
|
496 |
+
"step": 509
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 13.99,
|
500 |
+
"eval_bleu": 18.3062,
|
501 |
+
"eval_bp": 0.7981,
|
502 |
+
"eval_counts_1": 9425,
|
503 |
+
"eval_counts_2": 4071,
|
504 |
+
"eval_counts_3": 2176,
|
505 |
+
"eval_counts_4": 1207,
|
506 |
+
"eval_exact_match": 0.0445,
|
507 |
+
"eval_f1": 0.4417,
|
508 |
+
"eval_gen_len": 12.9129,
|
509 |
+
"eval_loss": 1.139233946800232,
|
510 |
+
"eval_precisions_1": 54.3572,
|
511 |
+
"eval_precisions_2": 26.8979,
|
512 |
+
"eval_precisions_3": 16.8278,
|
513 |
+
"eval_precisions_4": 11.252,
|
514 |
+
"eval_ref_len": 21250,
|
515 |
+
"eval_rouge1": 0.4495,
|
516 |
+
"eval_rouge2": 0.2568,
|
517 |
+
"eval_rougeL": 0.4365,
|
518 |
+
"eval_rougeLsum": 0.4358,
|
519 |
+
"eval_runtime": 3679.9149,
|
520 |
+
"eval_samples_per_second": 0.599,
|
521 |
+
"eval_steps_per_second": 0.599,
|
522 |
+
"eval_sys_len": 17339,
|
523 |
+
"eval_totals_1": 17339,
|
524 |
+
"eval_totals_2": 15135,
|
525 |
+
"eval_totals_3": 12931,
|
526 |
+
"eval_totals_4": 10727,
|
527 |
+
"step": 509
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 14.98,
|
531 |
+
"learning_rate": 0.0001,
|
532 |
+
"loss": 0.8282,
|
533 |
+
"step": 545
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 14.98,
|
537 |
+
"eval_bleu": 19.2695,
|
538 |
+
"eval_bp": 0.87,
|
539 |
+
"eval_counts_1": 9803,
|
540 |
+
"eval_counts_2": 4274,
|
541 |
+
"eval_counts_3": 2316,
|
542 |
+
"eval_counts_4": 1305,
|
543 |
+
"eval_exact_match": 0.0463,
|
544 |
+
"eval_f1": 0.4496,
|
545 |
+
"eval_gen_len": 14.0104,
|
546 |
+
"eval_loss": 1.1227205991744995,
|
547 |
+
"eval_precisions_1": 52.5574,
|
548 |
+
"eval_precisions_2": 25.9849,
|
549 |
+
"eval_precisions_3": 16.2595,
|
550 |
+
"eval_precisions_4": 10.8389,
|
551 |
+
"eval_ref_len": 21250,
|
552 |
+
"eval_rouge1": 0.4573,
|
553 |
+
"eval_rouge2": 0.2627,
|
554 |
+
"eval_rougeL": 0.4418,
|
555 |
+
"eval_rougeLsum": 0.4414,
|
556 |
+
"eval_runtime": 3897.0455,
|
557 |
+
"eval_samples_per_second": 0.566,
|
558 |
+
"eval_steps_per_second": 0.566,
|
559 |
+
"eval_sys_len": 18652,
|
560 |
+
"eval_totals_1": 18652,
|
561 |
+
"eval_totals_2": 16448,
|
562 |
+
"eval_totals_3": 14244,
|
563 |
+
"eval_totals_4": 12040,
|
564 |
+
"step": 545
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 16.0,
|
568 |
+
"learning_rate": 0.0001,
|
569 |
+
"loss": 0.7694,
|
570 |
+
"step": 582
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 16.0,
|
574 |
+
"eval_bleu": 19.1704,
|
575 |
+
"eval_bp": 0.8501,
|
576 |
+
"eval_counts_1": 9740,
|
577 |
+
"eval_counts_2": 4240,
|
578 |
+
"eval_counts_3": 2299,
|
579 |
+
"eval_counts_4": 1296,
|
580 |
+
"eval_exact_match": 0.0476,
|
581 |
+
"eval_f1": 0.4492,
|
582 |
+
"eval_gen_len": 13.6475,
|
583 |
+
"eval_loss": 1.139431357383728,
|
584 |
+
"eval_precisions_1": 53.2794,
|
585 |
+
"eval_precisions_2": 26.3731,
|
586 |
+
"eval_precisions_3": 16.5718,
|
587 |
+
"eval_precisions_4": 11.1064,
|
588 |
+
"eval_ref_len": 21250,
|
589 |
+
"eval_rouge1": 0.4572,
|
590 |
+
"eval_rouge2": 0.2629,
|
591 |
+
"eval_rougeL": 0.4411,
|
592 |
+
"eval_rougeLsum": 0.4412,
|
593 |
+
"eval_runtime": 3879.8331,
|
594 |
+
"eval_samples_per_second": 0.568,
|
595 |
+
"eval_steps_per_second": 0.568,
|
596 |
+
"eval_sys_len": 18281,
|
597 |
+
"eval_totals_1": 18281,
|
598 |
+
"eval_totals_2": 16077,
|
599 |
+
"eval_totals_3": 13873,
|
600 |
+
"eval_totals_4": 11669,
|
601 |
+
"step": 582
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 16.99,
|
605 |
+
"learning_rate": 0.0001,
|
606 |
+
"loss": 0.7589,
|
607 |
+
"step": 618
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 16.99,
|
611 |
+
"eval_bleu": 18.5906,
|
612 |
+
"eval_bp": 0.8572,
|
613 |
+
"eval_counts_1": 9663,
|
614 |
+
"eval_counts_2": 4140,
|
615 |
+
"eval_counts_3": 2214,
|
616 |
+
"eval_counts_4": 1232,
|
617 |
+
"eval_exact_match": 0.044,
|
618 |
+
"eval_f1": 0.4432,
|
619 |
+
"eval_gen_len": 13.7926,
|
620 |
+
"eval_loss": 1.1496515274047852,
|
621 |
+
"eval_precisions_1": 52.4821,
|
622 |
+
"eval_precisions_2": 25.5429,
|
623 |
+
"eval_precisions_3": 15.8098,
|
624 |
+
"eval_precisions_4": 10.4407,
|
625 |
+
"eval_ref_len": 21250,
|
626 |
+
"eval_rouge1": 0.4515,
|
627 |
+
"eval_rouge2": 0.2561,
|
628 |
+
"eval_rougeL": 0.4359,
|
629 |
+
"eval_rougeLsum": 0.4358,
|
630 |
+
"eval_runtime": 3896.3752,
|
631 |
+
"eval_samples_per_second": 0.566,
|
632 |
+
"eval_steps_per_second": 0.566,
|
633 |
+
"eval_sys_len": 18412,
|
634 |
+
"eval_totals_1": 18412,
|
635 |
+
"eval_totals_2": 16208,
|
636 |
+
"eval_totals_3": 14004,
|
637 |
+
"eval_totals_4": 11800,
|
638 |
+
"step": 618
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 17.98,
|
642 |
+
"learning_rate": 0.0001,
|
643 |
+
"loss": 0.724,
|
644 |
+
"step": 654
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 17.98,
|
648 |
+
"eval_bleu": 19.2167,
|
649 |
+
"eval_bp": 0.8566,
|
650 |
+
"eval_counts_1": 9743,
|
651 |
+
"eval_counts_2": 4246,
|
652 |
+
"eval_counts_3": 2316,
|
653 |
+
"eval_counts_4": 1300,
|
654 |
+
"eval_exact_match": 0.0472,
|
655 |
+
"eval_f1": 0.4474,
|
656 |
+
"eval_gen_len": 13.7214,
|
657 |
+
"eval_loss": 1.1680002212524414,
|
658 |
+
"eval_precisions_1": 52.9453,
|
659 |
+
"eval_precisions_2": 26.2131,
|
660 |
+
"eval_precisions_3": 16.5499,
|
661 |
+
"eval_precisions_4": 11.0263,
|
662 |
+
"eval_ref_len": 21250,
|
663 |
+
"eval_rouge1": 0.4562,
|
664 |
+
"eval_rouge2": 0.2625,
|
665 |
+
"eval_rougeL": 0.4408,
|
666 |
+
"eval_rougeLsum": 0.441,
|
667 |
+
"eval_runtime": 3957.7799,
|
668 |
+
"eval_samples_per_second": 0.557,
|
669 |
+
"eval_steps_per_second": 0.557,
|
670 |
+
"eval_sys_len": 18402,
|
671 |
+
"eval_totals_1": 18402,
|
672 |
+
"eval_totals_2": 16198,
|
673 |
+
"eval_totals_3": 13994,
|
674 |
+
"eval_totals_4": 11790,
|
675 |
+
"step": 654
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 18.99,
|
679 |
+
"learning_rate": 0.0001,
|
680 |
+
"loss": 0.6755,
|
681 |
+
"step": 691
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 18.99,
|
685 |
+
"eval_bleu": 19.4647,
|
686 |
+
"eval_bp": 0.8496,
|
687 |
+
"eval_counts_1": 9722,
|
688 |
+
"eval_counts_2": 4266,
|
689 |
+
"eval_counts_3": 2351,
|
690 |
+
"eval_counts_4": 1341,
|
691 |
+
"eval_exact_match": 0.0495,
|
692 |
+
"eval_f1": 0.4469,
|
693 |
+
"eval_gen_len": 13.6071,
|
694 |
+
"eval_loss": 1.1873786449432373,
|
695 |
+
"eval_precisions_1": 53.2071,
|
696 |
+
"eval_precisions_2": 26.5497,
|
697 |
+
"eval_precisions_3": 16.9576,
|
698 |
+
"eval_precisions_4": 11.5009,
|
699 |
+
"eval_ref_len": 21250,
|
700 |
+
"eval_rouge1": 0.4559,
|
701 |
+
"eval_rouge2": 0.2639,
|
702 |
+
"eval_rougeL": 0.4417,
|
703 |
+
"eval_rougeLsum": 0.4413,
|
704 |
+
"eval_runtime": 3873.6961,
|
705 |
+
"eval_samples_per_second": 0.569,
|
706 |
+
"eval_steps_per_second": 0.569,
|
707 |
+
"eval_sys_len": 18272,
|
708 |
+
"eval_totals_1": 18272,
|
709 |
+
"eval_totals_2": 16068,
|
710 |
+
"eval_totals_3": 13864,
|
711 |
+
"eval_totals_4": 11660,
|
712 |
+
"step": 691
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 19.79,
|
716 |
+
"learning_rate": 0.0001,
|
717 |
+
"loss": 0.657,
|
718 |
+
"step": 720
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 19.79,
|
722 |
+
"eval_bleu": 19.8248,
|
723 |
+
"eval_bp": 0.8822,
|
724 |
+
"eval_counts_1": 9920,
|
725 |
+
"eval_counts_2": 4361,
|
726 |
+
"eval_counts_3": 2402,
|
727 |
+
"eval_counts_4": 1373,
|
728 |
+
"eval_exact_match": 0.0467,
|
729 |
+
"eval_f1": 0.4508,
|
730 |
+
"eval_gen_len": 14.2001,
|
731 |
+
"eval_loss": 1.1845453977584839,
|
732 |
+
"eval_precisions_1": 52.5312,
|
733 |
+
"eval_precisions_2": 26.1451,
|
734 |
+
"eval_precisions_3": 16.593,
|
735 |
+
"eval_precisions_4": 11.1881,
|
736 |
+
"eval_ref_len": 21250,
|
737 |
+
"eval_rouge1": 0.4594,
|
738 |
+
"eval_rouge2": 0.2647,
|
739 |
+
"eval_rougeL": 0.4423,
|
740 |
+
"eval_rougeLsum": 0.4421,
|
741 |
+
"eval_runtime": 3958.6673,
|
742 |
+
"eval_samples_per_second": 0.557,
|
743 |
+
"eval_steps_per_second": 0.557,
|
744 |
+
"eval_sys_len": 18884,
|
745 |
+
"eval_totals_1": 18884,
|
746 |
+
"eval_totals_2": 16680,
|
747 |
+
"eval_totals_3": 14476,
|
748 |
+
"eval_totals_4": 12272,
|
749 |
+
"step": 720
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 19.79,
|
753 |
+
"step": 720,
|
754 |
+
"total_flos": 1.102412878184448e+18,
|
755 |
+
"train_loss": 1.3412119759453667,
|
756 |
+
"train_runtime": 128063.7495,
|
757 |
+
"train_samples_per_second": 1.455,
|
758 |
+
"train_steps_per_second": 0.006
|
759 |
+
}
|
760 |
+
],
|
761 |
+
"logging_steps": 500,
|
762 |
+
"max_steps": 720,
|
763 |
+
"num_train_epochs": 20,
|
764 |
+
"save_steps": 500,
|
765 |
+
"total_flos": 1.102412878184448e+18,
|
766 |
+
"trial_name": null,
|
767 |
+
"trial_params": null
|
768 |
+
}
|
training_args.bin
ADDED
Binary file (4.66 kB). View file
|
|