Marvin
commited on
Commit
•
8f02e9b
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
- runs/Oct21_13-27-58_MARVIN-PC/events.out.tfevents.1697887732.MARVIN-PC.18012.0 +3 -0
- runs/Oct21_16-57-04_MARVIN-PC/events.out.tfevents.1697900288.MARVIN-PC.9500.0 +3 -0
- runs/Oct21_16-57-04_MARVIN-PC/events.out.tfevents.1698012826.MARVIN-PC.9500.1 +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
|
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: 15.09
|
30 |
+
- name: F1
|
31 |
+
type: f1
|
32 |
+
value: 40.69
|
33 |
+
- name: ROUGE-1
|
34 |
+
type: rouge1
|
35 |
+
value: 41.68
|
36 |
+
- name: ROUGE-2
|
37 |
+
type: rouge2
|
38 |
+
value: 22.07
|
39 |
+
- name: ROUGE-L
|
40 |
+
type: rougel
|
41 |
+
value: 40.20
|
42 |
+
- name: ROUGE-Lsum
|
43 |
+
type: rougelsum
|
44 |
+
value: 40.19
|
45 |
+
- name: Exact Match
|
46 |
+
type: exact_match
|
47 |
+
value: 2.77
|
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-1k-64-constant
|
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: 1.8162
|
58 |
+
- Brevity Penalty: 0.9152
|
59 |
+
- System Length: 19102
|
60 |
+
- Reference Length: 20793
|
61 |
+
- ROUGE-1: 41.68
|
62 |
+
- ROUGE-2: 22.07
|
63 |
+
- ROUGE-L: 40.20
|
64 |
+
- ROUGE-Lsum: 40.19
|
65 |
+
- Exact Match: 2.77
|
66 |
+
- BLEU: 15.09
|
67 |
+
- F1: 40.69
|
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: 64
|
93 |
+
- total_train_batch_size: 64
|
94 |
+
- optimizer: Adafactor
|
95 |
+
- lr_scheduler_type: constant
|
96 |
+
- num_epochs: 20
|
97 |
+
|
98 |
+
### Training results
|
99 |
+
|
100 |
+
| Training Loss | Epoch | Step | BLEU | Brevity Penalty | Counts 1 | Counts 2 | Counts 3 | Counts 4 | Exact Match | F1 | Mean Generated Length | Validation Loss | Precisions 1 | Precisions 2 | Precisions 3 | Precisions 4 | Reference Length | ROUGE-1 | ROUGE-2 | ROUGE-L | ROUGE-Lsum | System Length | Totals 1 | Totals 2 | Totals 3 | Totals 4 |
|
101 |
+
|:-------------:|:-----:|:----:|:-------:|:---------------:|:--------:|:--------:|:--------:|:--------:|:-----------:|:------:|:---------------------:|:---------------:|:------------:|:------------:|:------------:|:------------:|:----------------:|:-------:|:-------:|:-------:|:----------:|:-------------:|:--------:|:--------:|:--------:|:--------:|
|
102 |
+
| 2.732 | 1.0 | 145 | 12.4473 | 0.7805 | 7779 | 2893 | 1393 | 685 | 0.0168 | 0.3393 | 12.2523 | 1.2989 | 45.6809 | 19.5143 | 11.0372 | 6.5758 | 21250 | 0.3487 | 0.1796 | 0.3329 | 0.3327 | 17029 | 17029 | 14825 | 12621 | 10417 |
|
103 |
+
| 1.5514 | 2.0 | 291 | 14.7663 | 0.7871 | 8297 | 3336 | 1711 | 899 | 0.025 | 0.3743 | 12.441 | 1.2100 | 48.3931 | 22.3278 | 13.4333 | 8.5351 | 21250 | 0.3839 | 0.2089 | 0.3688 | 0.369 | 17145 | 17145 | 14941 | 12737 | 10533 |
|
104 |
+
| 1.3546 | 3.0 | 435 | 1.1428 | 8930 | 3713 | 1905 | 1022 | 17018 | 14814 | 12610 | 10406 | 52.4739 | 25.0641 | 15.1071 | 9.8213 | 0.7798 | 17018 | 21250 | 0.4225 | 0.2345 | 0.4075 | 0.4074 | 0.034 | 16.3903 | 12.6021 | 0.4155 |
|
105 |
+
| 1.1969 | 4.0 | 581 | 1.1113 | 9456 | 3994 | 2096 | 1157 | 18171 | 15967 | 13763 | 11559 | 52.039 | 25.0141 | 15.2292 | 10.0095 | 0.8441 | 18171 | 21250 | 0.4409 | 0.246 | 0.4251 | 0.4251 | 0.0386 | 17.8161 | 13.4061 | 0.4334 |
|
106 |
+
| 1.0876 | 5.0 | 726 | 1.1032 | 9606 | 4162 | 2233 | 1243 | 18179 | 15975 | 13771 | 11567 | 52.8412 | 26.0532 | 16.2152 | 10.7461 | 0.8446 | 18179 | 21250 | 0.4504 | 0.2571 | 0.4356 | 0.4357 | 0.0377 | 18.6911 | 13.5599 | 0.443 |
|
107 |
+
| 0.9881 | 6.0 | 872 | 1.1119 | 9608 | 4167 | 2235 | 1246 | 18245 | 16041 | 13837 | 11633 | 52.661 | 25.9772 | 16.1523 | 10.7109 | 0.8481 | 18245 | 21250 | 0.4505 | 0.2567 | 0.4348 | 0.4349 | 0.044 | 18.7071 | 13.6978 | 0.4429 |
|
108 |
+
| 0.9142 | 7.0 | 1017 | 1.1106 | 9757 | 4285 | 2311 | 1310 | 18291 | 16087 | 13883 | 11679 | 53.3432 | 26.6364 | 16.6463 | 11.2167 | 0.8506 | 18291 | 21250 | 0.4587 | 0.2641 | 0.4427 | 0.443 | 0.0495 | 19.3053 | 13.5826 | 0.451 |
|
109 |
+
| 0.8323 | 8.0 | 1163 | 1.1327 | 9757 | 4300 | 2341 | 1317 | 18293 | 16089 | 13885 | 11681 | 53.3373 | 26.7263 | 16.8599 | 11.2747 | 0.8507 | 18293 | 21250 | 0.4587 | 0.2662 | 0.4429 | 0.4426 | 0.0472 | 19.4102 | 13.6239 | 0.4513 |
|
110 |
+
| 0.7742 | 9.0 | 1308 | 1.1574 | 9757 | 4273 | 2324 | 1320 | 18273 | 16069 | 13865 | 11661 | 53.3957 | 26.5916 | 16.7616 | 11.3198 | 0.8497 | 18273 | 21250 | 0.4585 | 0.2653 | 0.4431 | 0.443 | 0.049 | 19.3574 | 13.5944 | 0.451 |
|
111 |
+
| 0.7101 | 10.0 | 1454 | 1.1674 | 9861 | 4403 | 2438 | 1416 | 18641 | 16437 | 14233 | 12029 | 52.8995 | 26.7871 | 17.1292 | 11.7716 | 0.8694 | 18641 | 21250 | 0.4594 | 0.2689 | 0.444 | 0.4435 | 0.0531 | 20.1003 | 13.9133 | 0.4525 |
|
112 |
+
| 0.6642 | 10.99 | 1599 | 1.1889 | 9868 | 4380 | 2358 | 1337 | 18386 | 16182 | 13978 | 11774 | 53.6713 | 27.0671 | 16.8694 | 11.3555 | 0.8558 | 18386 | 21250 | 0.4622 | 0.2694 | 0.4469 | 0.4466 | 0.0476 | 19.655 | 13.9142 | 0.4551 |
|
113 |
+
| 0.6067 | 12.0 | 1745 | 1.2207 | 9872 | 4384 | 2408 | 1395 | 18894 | 16690 | 14486 | 12282 | 52.2494 | 26.2672 | 16.6229 | 11.3581 | 0.8828 | 18894 | 21250 | 0.4569 | 0.2667 | 0.441 | 0.4408 | 0.0472 | 19.9169 | 14.2482 | 0.4489 |
|
114 |
+
| 0.5684 | 12.99 | 1890 | 1.2587 | 9870 | 4356 | 2360 | 1329 | 18901 | 16697 | 14493 | 12289 | 52.2195 | 26.0885 | 16.2837 | 10.8145 | 0.8831 | 18901 | 21250 | 0.4581 | 0.2651 | 0.4414 | 0.4409 | 0.0485 | 19.5451 | 14.2432 | 0.4506 |
|
115 |
+
| 0.5288 | 14.0 | 2036 | 1.2804 | 9815 | 4360 | 2389 | 1335 | 18367 | 16163 | 13959 | 11755 | 53.4382 | 26.9752 | 17.1144 | 11.3569 | 0.8547 | 18367 | 21250 | 0.4592 | 0.2671 | 0.4443 | 0.4436 | 0.0454 | 19.6648 | 13.7432 | 0.4504 |
|
116 |
+
| 0.4902 | 14.99 | 2181 | 1.3211 | 9886 | 4407 | 2398 | 1359 | 18777 | 16573 | 14369 | 12165 | 52.6495 | 26.5914 | 16.6887 | 11.1714 | 0.8766 | 18777 | 21250 | 0.4582 | 0.2674 | 0.4426 | 0.4421 | 0.0495 | 19.8138 | 14.1225 | 0.451 |
|
117 |
+
| 0.4498 | 16.0 | 2327 | 1.3621 | 10008 | 4477 | 2456 | 1381 | 19399 | 17195 | 14991 | 12787 | 51.5903 | 26.0366 | 16.3832 | 10.8 | 0.909 | 19399 | 21250 | 0.4569 | 0.2679 | 0.4415 | 0.4412 | 0.0476 | 20.0703 | 14.3725 | 0.4491 |
|
118 |
+
| 0.4216 | 16.99 | 2472 | 1.3967 | 10016 | 4483 | 2455 | 1385 | 19125 | 16921 | 14717 | 12513 | 52.3712 | 26.4937 | 16.6814 | 11.0685 | 0.8948 | 19125 | 21250 | 0.4615 | 0.2705 | 0.4457 | 0.4451 | 0.0481 | 20.1319 | 14.3008 | 0.4531 |
|
119 |
+
| 0.3829 | 18.0 | 2618 | 1.4460 | 9976 | 4407 | 2412 | 1374 | 19464 | 17260 | 15056 | 12852 | 51.2536 | 25.533 | 16.0202 | 10.6909 | 0.9123 | 19464 | 21250 | 0.4556 | 0.2627 | 0.4387 | 0.4385 | 0.0476 | 19.8508 | 14.7046 | 0.4479 |
|
120 |
+
| 0.3551 | 19.0 | 2764 | 1.4725 | 10010 | 4451 | 2438 | 1385 | 19131 | 16927 | 14723 | 12519 | 52.3235 | 26.2953 | 16.5591 | 11.0632 | 0.8952 | 19131 | 21250 | 0.4606 | 0.2672 | 0.4438 | 0.4434 | 0.0463 | 20.0572 | 14.3807 | 0.4523 |
|
121 |
+
| 0.3301 | 19.93 | 2900 | 1.5030 | 9858 | 4378 | 2406 | 1368 | 18872 | 16668 | 14464 | 12260 | 52.2361 | 26.2659 | 16.6344 | 11.1582 | 0.8816 | 18872 | 21250 | 0.4569 | 0.2644 | 0.4412 | 0.4405 | 0.0495 | 19.8047 | 14.2795 | 0.4483 |
|
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": 19.93,
|
3 |
+
"eval_bleu": 19.8047,
|
4 |
+
"eval_bp": 0.8816,
|
5 |
+
"eval_counts_1": 9858,
|
6 |
+
"eval_counts_2": 4378,
|
7 |
+
"eval_counts_3": 2406,
|
8 |
+
"eval_counts_4": 1368,
|
9 |
+
"eval_exact_match": 0.0495,
|
10 |
+
"eval_f1": 0.4483,
|
11 |
+
"eval_gen_len": 14.2795,
|
12 |
+
"eval_loss": 1.5030488967895508,
|
13 |
+
"eval_precisions_1": 52.2361,
|
14 |
+
"eval_precisions_2": 26.2659,
|
15 |
+
"eval_precisions_3": 16.6344,
|
16 |
+
"eval_precisions_4": 11.1582,
|
17 |
+
"eval_ref_len": 21250,
|
18 |
+
"eval_rouge1": 0.4569,
|
19 |
+
"eval_rouge2": 0.2644,
|
20 |
+
"eval_rougeL": 0.4412,
|
21 |
+
"eval_rougeLsum": 0.4405,
|
22 |
+
"eval_runtime": 2187.575,
|
23 |
+
"eval_samples": 2204,
|
24 |
+
"eval_samples_per_second": 1.008,
|
25 |
+
"eval_steps_per_second": 1.008,
|
26 |
+
"eval_sys_len": 18872,
|
27 |
+
"eval_totals_1": 18872,
|
28 |
+
"eval_totals_2": 16668,
|
29 |
+
"eval_totals_3": 14464,
|
30 |
+
"eval_totals_4": 12260,
|
31 |
+
"predict_bleu": 14.494,
|
32 |
+
"predict_bp": 0.9213,
|
33 |
+
"predict_counts_1": 8898,
|
34 |
+
"predict_counts_2": 3367,
|
35 |
+
"predict_counts_3": 1600,
|
36 |
+
"predict_counts_4": 780,
|
37 |
+
"predict_exact_match": 0.0268,
|
38 |
+
"predict_f1": 0.3965,
|
39 |
+
"predict_gen_len": 14.6842,
|
40 |
+
"predict_loss": 1.8663314580917358,
|
41 |
+
"predict_precisions_1": 46.3028,
|
42 |
+
"predict_precisions_2": 19.7907,
|
43 |
+
"predict_precisions_3": 10.8042,
|
44 |
+
"predict_precisions_4": 6.188,
|
45 |
+
"predict_ref_len": 20793,
|
46 |
+
"predict_rouge1": 0.4064,
|
47 |
+
"predict_rouge2": 0.2138,
|
48 |
+
"predict_rougeL": 0.3919,
|
49 |
+
"predict_rougeLsum": 0.3914,
|
50 |
+
"predict_runtime": 2245.7822,
|
51 |
+
"predict_samples": 2204,
|
52 |
+
"predict_samples_per_second": 0.981,
|
53 |
+
"predict_steps_per_second": 0.981,
|
54 |
+
"predict_sys_len": 19217,
|
55 |
+
"predict_totals_1": 19217,
|
56 |
+
"predict_totals_2": 17013,
|
57 |
+
"predict_totals_3": 14809,
|
58 |
+
"predict_totals_4": 12605,
|
59 |
+
"train_loss": 0.6333936349276839,
|
60 |
+
"train_runtime": 110329.1002,
|
61 |
+
"train_samples": 9314,
|
62 |
+
"train_samples_per_second": 1.688,
|
63 |
+
"train_steps_per_second": 0.026
|
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 sha256:1d4911da46fd490fd525410a130c54ae158cf2bcef89fa6e7ef555fd40801997
|
3 |
+
size 4918393736
|
runs/Oct21_13-27-58_MARVIN-PC/events.out.tfevents.1697887732.MARVIN-PC.18012.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0847a597cdc4989ca81f25e62905cdf4eda01996fb998004123627107836cfa9
|
3 |
+
size 7812
|
runs/Oct21_16-57-04_MARVIN-PC/events.out.tfevents.1697900288.MARVIN-PC.9500.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67b320f494619d940760bfbc53359b96650beb2f1ef4979dc24e5494b23e1d81
|
3 |
+
size 34070
|
runs/Oct21_16-57-04_MARVIN-PC/events.out.tfevents.1698012826.MARVIN-PC.9500.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d529b50ea1f1561f84443e763b918fe190a4b5c7f385c50217f60ab99b16f839
|
3 |
+
size 1550
|
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": 19.934292462958986,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2900,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"learning_rate": 0.0001,
|
14 |
+
"loss": 2.732,
|
15 |
+
"step": 145
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_bleu": 12.4473,
|
20 |
+
"eval_bp": 0.7805,
|
21 |
+
"eval_counts_1": 7779,
|
22 |
+
"eval_counts_2": 2893,
|
23 |
+
"eval_counts_3": 1393,
|
24 |
+
"eval_counts_4": 685,
|
25 |
+
"eval_exact_match": 0.0168,
|
26 |
+
"eval_f1": 0.3393,
|
27 |
+
"eval_gen_len": 12.2523,
|
28 |
+
"eval_loss": 1.2989141941070557,
|
29 |
+
"eval_precisions_1": 45.6809,
|
30 |
+
"eval_precisions_2": 19.5143,
|
31 |
+
"eval_precisions_3": 11.0372,
|
32 |
+
"eval_precisions_4": 6.5758,
|
33 |
+
"eval_ref_len": 21250,
|
34 |
+
"eval_rouge1": 0.3487,
|
35 |
+
"eval_rouge2": 0.1796,
|
36 |
+
"eval_rougeL": 0.3329,
|
37 |
+
"eval_rougeLsum": 0.3327,
|
38 |
+
"eval_runtime": 2048.1193,
|
39 |
+
"eval_samples_per_second": 1.076,
|
40 |
+
"eval_steps_per_second": 1.076,
|
41 |
+
"eval_sys_len": 17029,
|
42 |
+
"eval_totals_1": 17029,
|
43 |
+
"eval_totals_2": 14825,
|
44 |
+
"eval_totals_3": 12621,
|
45 |
+
"eval_totals_4": 10417,
|
46 |
+
"step": 145
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 2.0,
|
50 |
+
"learning_rate": 0.0001,
|
51 |
+
"loss": 1.5514,
|
52 |
+
"step": 291
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 2.0,
|
56 |
+
"eval_bleu": 14.7663,
|
57 |
+
"eval_bp": 0.7871,
|
58 |
+
"eval_counts_1": 8297,
|
59 |
+
"eval_counts_2": 3336,
|
60 |
+
"eval_counts_3": 1711,
|
61 |
+
"eval_counts_4": 899,
|
62 |
+
"eval_exact_match": 0.025,
|
63 |
+
"eval_f1": 0.3743,
|
64 |
+
"eval_gen_len": 12.441,
|
65 |
+
"eval_loss": 1.20997154712677,
|
66 |
+
"eval_precisions_1": 48.3931,
|
67 |
+
"eval_precisions_2": 22.3278,
|
68 |
+
"eval_precisions_3": 13.4333,
|
69 |
+
"eval_precisions_4": 8.5351,
|
70 |
+
"eval_ref_len": 21250,
|
71 |
+
"eval_rouge1": 0.3839,
|
72 |
+
"eval_rouge2": 0.2089,
|
73 |
+
"eval_rougeL": 0.3688,
|
74 |
+
"eval_rougeLsum": 0.369,
|
75 |
+
"eval_runtime": 2570.171,
|
76 |
+
"eval_samples_per_second": 0.858,
|
77 |
+
"eval_steps_per_second": 0.858,
|
78 |
+
"eval_sys_len": 17145,
|
79 |
+
"eval_totals_1": 17145,
|
80 |
+
"eval_totals_2": 14941,
|
81 |
+
"eval_totals_3": 12737,
|
82 |
+
"eval_totals_4": 10533,
|
83 |
+
"step": 291
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 3.0,
|
87 |
+
"learning_rate": 0.0001,
|
88 |
+
"loss": 1.3546,
|
89 |
+
"step": 435
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 3.0,
|
93 |
+
"eval_bleu": 16.3903,
|
94 |
+
"eval_bp": 0.7798,
|
95 |
+
"eval_counts_1": 8930,
|
96 |
+
"eval_counts_2": 3713,
|
97 |
+
"eval_counts_3": 1905,
|
98 |
+
"eval_counts_4": 1022,
|
99 |
+
"eval_exact_match": 0.034,
|
100 |
+
"eval_f1": 0.4155,
|
101 |
+
"eval_gen_len": 12.6021,
|
102 |
+
"eval_loss": 1.142831563949585,
|
103 |
+
"eval_precisions_1": 52.4739,
|
104 |
+
"eval_precisions_2": 25.0641,
|
105 |
+
"eval_precisions_3": 15.1071,
|
106 |
+
"eval_precisions_4": 9.8213,
|
107 |
+
"eval_ref_len": 21250,
|
108 |
+
"eval_rouge1": 0.4225,
|
109 |
+
"eval_rouge2": 0.2345,
|
110 |
+
"eval_rougeL": 0.4075,
|
111 |
+
"eval_rougeLsum": 0.4074,
|
112 |
+
"eval_runtime": 2923.7087,
|
113 |
+
"eval_samples_per_second": 0.754,
|
114 |
+
"eval_steps_per_second": 0.754,
|
115 |
+
"eval_sys_len": 17018,
|
116 |
+
"eval_totals_1": 17018,
|
117 |
+
"eval_totals_2": 14814,
|
118 |
+
"eval_totals_3": 12610,
|
119 |
+
"eval_totals_4": 10406,
|
120 |
+
"step": 435
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 4.0,
|
124 |
+
"learning_rate": 0.0001,
|
125 |
+
"loss": 1.1969,
|
126 |
+
"step": 581
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 4.0,
|
130 |
+
"eval_bleu": 17.8161,
|
131 |
+
"eval_bp": 0.8441,
|
132 |
+
"eval_counts_1": 9456,
|
133 |
+
"eval_counts_2": 3994,
|
134 |
+
"eval_counts_3": 2096,
|
135 |
+
"eval_counts_4": 1157,
|
136 |
+
"eval_exact_match": 0.0386,
|
137 |
+
"eval_f1": 0.4334,
|
138 |
+
"eval_gen_len": 13.4061,
|
139 |
+
"eval_loss": 1.1113450527191162,
|
140 |
+
"eval_precisions_1": 52.039,
|
141 |
+
"eval_precisions_2": 25.0141,
|
142 |
+
"eval_precisions_3": 15.2292,
|
143 |
+
"eval_precisions_4": 10.0095,
|
144 |
+
"eval_ref_len": 21250,
|
145 |
+
"eval_rouge1": 0.4409,
|
146 |
+
"eval_rouge2": 0.246,
|
147 |
+
"eval_rougeL": 0.4251,
|
148 |
+
"eval_rougeLsum": 0.4251,
|
149 |
+
"eval_runtime": 2741.9646,
|
150 |
+
"eval_samples_per_second": 0.804,
|
151 |
+
"eval_steps_per_second": 0.804,
|
152 |
+
"eval_sys_len": 18171,
|
153 |
+
"eval_totals_1": 18171,
|
154 |
+
"eval_totals_2": 15967,
|
155 |
+
"eval_totals_3": 13763,
|
156 |
+
"eval_totals_4": 11559,
|
157 |
+
"step": 581
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 5.0,
|
161 |
+
"learning_rate": 0.0001,
|
162 |
+
"loss": 1.0876,
|
163 |
+
"step": 726
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 5.0,
|
167 |
+
"eval_bleu": 18.6911,
|
168 |
+
"eval_bp": 0.8446,
|
169 |
+
"eval_counts_1": 9606,
|
170 |
+
"eval_counts_2": 4162,
|
171 |
+
"eval_counts_3": 2233,
|
172 |
+
"eval_counts_4": 1243,
|
173 |
+
"eval_exact_match": 0.0377,
|
174 |
+
"eval_f1": 0.443,
|
175 |
+
"eval_gen_len": 13.5599,
|
176 |
+
"eval_loss": 1.1031831502914429,
|
177 |
+
"eval_precisions_1": 52.8412,
|
178 |
+
"eval_precisions_2": 26.0532,
|
179 |
+
"eval_precisions_3": 16.2152,
|
180 |
+
"eval_precisions_4": 10.7461,
|
181 |
+
"eval_ref_len": 21250,
|
182 |
+
"eval_rouge1": 0.4504,
|
183 |
+
"eval_rouge2": 0.2571,
|
184 |
+
"eval_rougeL": 0.4356,
|
185 |
+
"eval_rougeLsum": 0.4357,
|
186 |
+
"eval_runtime": 3812.6899,
|
187 |
+
"eval_samples_per_second": 0.578,
|
188 |
+
"eval_steps_per_second": 0.578,
|
189 |
+
"eval_sys_len": 18179,
|
190 |
+
"eval_totals_1": 18179,
|
191 |
+
"eval_totals_2": 15975,
|
192 |
+
"eval_totals_3": 13771,
|
193 |
+
"eval_totals_4": 11567,
|
194 |
+
"step": 726
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 6.0,
|
198 |
+
"learning_rate": 0.0001,
|
199 |
+
"loss": 0.9881,
|
200 |
+
"step": 872
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 6.0,
|
204 |
+
"eval_bleu": 18.7071,
|
205 |
+
"eval_bp": 0.8481,
|
206 |
+
"eval_counts_1": 9608,
|
207 |
+
"eval_counts_2": 4167,
|
208 |
+
"eval_counts_3": 2235,
|
209 |
+
"eval_counts_4": 1246,
|
210 |
+
"eval_exact_match": 0.044,
|
211 |
+
"eval_f1": 0.4429,
|
212 |
+
"eval_gen_len": 13.6978,
|
213 |
+
"eval_loss": 1.1118519306182861,
|
214 |
+
"eval_precisions_1": 52.661,
|
215 |
+
"eval_precisions_2": 25.9772,
|
216 |
+
"eval_precisions_3": 16.1523,
|
217 |
+
"eval_precisions_4": 10.7109,
|
218 |
+
"eval_ref_len": 21250,
|
219 |
+
"eval_rouge1": 0.4505,
|
220 |
+
"eval_rouge2": 0.2567,
|
221 |
+
"eval_rougeL": 0.4348,
|
222 |
+
"eval_rougeLsum": 0.4349,
|
223 |
+
"eval_runtime": 2020.0708,
|
224 |
+
"eval_samples_per_second": 1.091,
|
225 |
+
"eval_steps_per_second": 1.091,
|
226 |
+
"eval_sys_len": 18245,
|
227 |
+
"eval_totals_1": 18245,
|
228 |
+
"eval_totals_2": 16041,
|
229 |
+
"eval_totals_3": 13837,
|
230 |
+
"eval_totals_4": 11633,
|
231 |
+
"step": 872
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 7.0,
|
235 |
+
"learning_rate": 0.0001,
|
236 |
+
"loss": 0.9142,
|
237 |
+
"step": 1017
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 7.0,
|
241 |
+
"eval_bleu": 19.3053,
|
242 |
+
"eval_bp": 0.8506,
|
243 |
+
"eval_counts_1": 9757,
|
244 |
+
"eval_counts_2": 4285,
|
245 |
+
"eval_counts_3": 2311,
|
246 |
+
"eval_counts_4": 1310,
|
247 |
+
"eval_exact_match": 0.0495,
|
248 |
+
"eval_f1": 0.451,
|
249 |
+
"eval_gen_len": 13.5826,
|
250 |
+
"eval_loss": 1.1105936765670776,
|
251 |
+
"eval_precisions_1": 53.3432,
|
252 |
+
"eval_precisions_2": 26.6364,
|
253 |
+
"eval_precisions_3": 16.6463,
|
254 |
+
"eval_precisions_4": 11.2167,
|
255 |
+
"eval_ref_len": 21250,
|
256 |
+
"eval_rouge1": 0.4587,
|
257 |
+
"eval_rouge2": 0.2641,
|
258 |
+
"eval_rougeL": 0.4427,
|
259 |
+
"eval_rougeLsum": 0.443,
|
260 |
+
"eval_runtime": 1991.0459,
|
261 |
+
"eval_samples_per_second": 1.107,
|
262 |
+
"eval_steps_per_second": 1.107,
|
263 |
+
"eval_sys_len": 18291,
|
264 |
+
"eval_totals_1": 18291,
|
265 |
+
"eval_totals_2": 16087,
|
266 |
+
"eval_totals_3": 13883,
|
267 |
+
"eval_totals_4": 11679,
|
268 |
+
"step": 1017
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 8.0,
|
272 |
+
"learning_rate": 0.0001,
|
273 |
+
"loss": 0.8323,
|
274 |
+
"step": 1163
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 8.0,
|
278 |
+
"eval_bleu": 19.4102,
|
279 |
+
"eval_bp": 0.8507,
|
280 |
+
"eval_counts_1": 9757,
|
281 |
+
"eval_counts_2": 4300,
|
282 |
+
"eval_counts_3": 2341,
|
283 |
+
"eval_counts_4": 1317,
|
284 |
+
"eval_exact_match": 0.0472,
|
285 |
+
"eval_f1": 0.4513,
|
286 |
+
"eval_gen_len": 13.6239,
|
287 |
+
"eval_loss": 1.1327157020568848,
|
288 |
+
"eval_precisions_1": 53.3373,
|
289 |
+
"eval_precisions_2": 26.7263,
|
290 |
+
"eval_precisions_3": 16.8599,
|
291 |
+
"eval_precisions_4": 11.2747,
|
292 |
+
"eval_ref_len": 21250,
|
293 |
+
"eval_rouge1": 0.4587,
|
294 |
+
"eval_rouge2": 0.2662,
|
295 |
+
"eval_rougeL": 0.4429,
|
296 |
+
"eval_rougeLsum": 0.4426,
|
297 |
+
"eval_runtime": 1972.0648,
|
298 |
+
"eval_samples_per_second": 1.118,
|
299 |
+
"eval_steps_per_second": 1.118,
|
300 |
+
"eval_sys_len": 18293,
|
301 |
+
"eval_totals_1": 18293,
|
302 |
+
"eval_totals_2": 16089,
|
303 |
+
"eval_totals_3": 13885,
|
304 |
+
"eval_totals_4": 11681,
|
305 |
+
"step": 1163
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 9.0,
|
309 |
+
"learning_rate": 0.0001,
|
310 |
+
"loss": 0.7742,
|
311 |
+
"step": 1308
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 9.0,
|
315 |
+
"eval_bleu": 19.3574,
|
316 |
+
"eval_bp": 0.8497,
|
317 |
+
"eval_counts_1": 9757,
|
318 |
+
"eval_counts_2": 4273,
|
319 |
+
"eval_counts_3": 2324,
|
320 |
+
"eval_counts_4": 1320,
|
321 |
+
"eval_exact_match": 0.049,
|
322 |
+
"eval_f1": 0.451,
|
323 |
+
"eval_gen_len": 13.5944,
|
324 |
+
"eval_loss": 1.1574428081512451,
|
325 |
+
"eval_precisions_1": 53.3957,
|
326 |
+
"eval_precisions_2": 26.5916,
|
327 |
+
"eval_precisions_3": 16.7616,
|
328 |
+
"eval_precisions_4": 11.3198,
|
329 |
+
"eval_ref_len": 21250,
|
330 |
+
"eval_rouge1": 0.4585,
|
331 |
+
"eval_rouge2": 0.2653,
|
332 |
+
"eval_rougeL": 0.4431,
|
333 |
+
"eval_rougeLsum": 0.443,
|
334 |
+
"eval_runtime": 1991.8737,
|
335 |
+
"eval_samples_per_second": 1.106,
|
336 |
+
"eval_steps_per_second": 1.106,
|
337 |
+
"eval_sys_len": 18273,
|
338 |
+
"eval_totals_1": 18273,
|
339 |
+
"eval_totals_2": 16069,
|
340 |
+
"eval_totals_3": 13865,
|
341 |
+
"eval_totals_4": 11661,
|
342 |
+
"step": 1308
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 10.0,
|
346 |
+
"learning_rate": 0.0001,
|
347 |
+
"loss": 0.7101,
|
348 |
+
"step": 1454
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 10.0,
|
352 |
+
"eval_bleu": 20.1003,
|
353 |
+
"eval_bp": 0.8694,
|
354 |
+
"eval_counts_1": 9861,
|
355 |
+
"eval_counts_2": 4403,
|
356 |
+
"eval_counts_3": 2438,
|
357 |
+
"eval_counts_4": 1416,
|
358 |
+
"eval_exact_match": 0.0531,
|
359 |
+
"eval_f1": 0.4525,
|
360 |
+
"eval_gen_len": 13.9133,
|
361 |
+
"eval_loss": 1.167409896850586,
|
362 |
+
"eval_precisions_1": 52.8995,
|
363 |
+
"eval_precisions_2": 26.7871,
|
364 |
+
"eval_precisions_3": 17.1292,
|
365 |
+
"eval_precisions_4": 11.7716,
|
366 |
+
"eval_ref_len": 21250,
|
367 |
+
"eval_rouge1": 0.4594,
|
368 |
+
"eval_rouge2": 0.2689,
|
369 |
+
"eval_rougeL": 0.444,
|
370 |
+
"eval_rougeLsum": 0.4435,
|
371 |
+
"eval_runtime": 2025.3437,
|
372 |
+
"eval_samples_per_second": 1.088,
|
373 |
+
"eval_steps_per_second": 1.088,
|
374 |
+
"eval_sys_len": 18641,
|
375 |
+
"eval_totals_1": 18641,
|
376 |
+
"eval_totals_2": 16437,
|
377 |
+
"eval_totals_3": 14233,
|
378 |
+
"eval_totals_4": 12029,
|
379 |
+
"step": 1454
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 10.99,
|
383 |
+
"learning_rate": 0.0001,
|
384 |
+
"loss": 0.6642,
|
385 |
+
"step": 1599
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 10.99,
|
389 |
+
"eval_bleu": 19.655,
|
390 |
+
"eval_bp": 0.8558,
|
391 |
+
"eval_counts_1": 9868,
|
392 |
+
"eval_counts_2": 4380,
|
393 |
+
"eval_counts_3": 2358,
|
394 |
+
"eval_counts_4": 1337,
|
395 |
+
"eval_exact_match": 0.0476,
|
396 |
+
"eval_f1": 0.4551,
|
397 |
+
"eval_gen_len": 13.9142,
|
398 |
+
"eval_loss": 1.1888612508773804,
|
399 |
+
"eval_precisions_1": 53.6713,
|
400 |
+
"eval_precisions_2": 27.0671,
|
401 |
+
"eval_precisions_3": 16.8694,
|
402 |
+
"eval_precisions_4": 11.3555,
|
403 |
+
"eval_ref_len": 21250,
|
404 |
+
"eval_rouge1": 0.4622,
|
405 |
+
"eval_rouge2": 0.2694,
|
406 |
+
"eval_rougeL": 0.4469,
|
407 |
+
"eval_rougeLsum": 0.4466,
|
408 |
+
"eval_runtime": 2020.9205,
|
409 |
+
"eval_samples_per_second": 1.091,
|
410 |
+
"eval_steps_per_second": 1.091,
|
411 |
+
"eval_sys_len": 18386,
|
412 |
+
"eval_totals_1": 18386,
|
413 |
+
"eval_totals_2": 16182,
|
414 |
+
"eval_totals_3": 13978,
|
415 |
+
"eval_totals_4": 11774,
|
416 |
+
"step": 1599
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 12.0,
|
420 |
+
"learning_rate": 0.0001,
|
421 |
+
"loss": 0.6067,
|
422 |
+
"step": 1745
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 12.0,
|
426 |
+
"eval_bleu": 19.9169,
|
427 |
+
"eval_bp": 0.8828,
|
428 |
+
"eval_counts_1": 9872,
|
429 |
+
"eval_counts_2": 4384,
|
430 |
+
"eval_counts_3": 2408,
|
431 |
+
"eval_counts_4": 1395,
|
432 |
+
"eval_exact_match": 0.0472,
|
433 |
+
"eval_f1": 0.4489,
|
434 |
+
"eval_gen_len": 14.2482,
|
435 |
+
"eval_loss": 1.2207266092300415,
|
436 |
+
"eval_precisions_1": 52.2494,
|
437 |
+
"eval_precisions_2": 26.2672,
|
438 |
+
"eval_precisions_3": 16.6229,
|
439 |
+
"eval_precisions_4": 11.3581,
|
440 |
+
"eval_ref_len": 21250,
|
441 |
+
"eval_rouge1": 0.4569,
|
442 |
+
"eval_rouge2": 0.2667,
|
443 |
+
"eval_rougeL": 0.441,
|
444 |
+
"eval_rougeLsum": 0.4408,
|
445 |
+
"eval_runtime": 2047.2616,
|
446 |
+
"eval_samples_per_second": 1.077,
|
447 |
+
"eval_steps_per_second": 1.077,
|
448 |
+
"eval_sys_len": 18894,
|
449 |
+
"eval_totals_1": 18894,
|
450 |
+
"eval_totals_2": 16690,
|
451 |
+
"eval_totals_3": 14486,
|
452 |
+
"eval_totals_4": 12282,
|
453 |
+
"step": 1745
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 12.99,
|
457 |
+
"learning_rate": 0.0001,
|
458 |
+
"loss": 0.5684,
|
459 |
+
"step": 1890
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 12.99,
|
463 |
+
"eval_bleu": 19.5451,
|
464 |
+
"eval_bp": 0.8831,
|
465 |
+
"eval_counts_1": 9870,
|
466 |
+
"eval_counts_2": 4356,
|
467 |
+
"eval_counts_3": 2360,
|
468 |
+
"eval_counts_4": 1329,
|
469 |
+
"eval_exact_match": 0.0485,
|
470 |
+
"eval_f1": 0.4506,
|
471 |
+
"eval_gen_len": 14.2432,
|
472 |
+
"eval_loss": 1.2586854696273804,
|
473 |
+
"eval_precisions_1": 52.2195,
|
474 |
+
"eval_precisions_2": 26.0885,
|
475 |
+
"eval_precisions_3": 16.2837,
|
476 |
+
"eval_precisions_4": 10.8145,
|
477 |
+
"eval_ref_len": 21250,
|
478 |
+
"eval_rouge1": 0.4581,
|
479 |
+
"eval_rouge2": 0.2651,
|
480 |
+
"eval_rougeL": 0.4414,
|
481 |
+
"eval_rougeLsum": 0.4409,
|
482 |
+
"eval_runtime": 2126.3316,
|
483 |
+
"eval_samples_per_second": 1.037,
|
484 |
+
"eval_steps_per_second": 1.037,
|
485 |
+
"eval_sys_len": 18901,
|
486 |
+
"eval_totals_1": 18901,
|
487 |
+
"eval_totals_2": 16697,
|
488 |
+
"eval_totals_3": 14493,
|
489 |
+
"eval_totals_4": 12289,
|
490 |
+
"step": 1890
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 14.0,
|
494 |
+
"learning_rate": 0.0001,
|
495 |
+
"loss": 0.5288,
|
496 |
+
"step": 2036
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 14.0,
|
500 |
+
"eval_bleu": 19.6648,
|
501 |
+
"eval_bp": 0.8547,
|
502 |
+
"eval_counts_1": 9815,
|
503 |
+
"eval_counts_2": 4360,
|
504 |
+
"eval_counts_3": 2389,
|
505 |
+
"eval_counts_4": 1335,
|
506 |
+
"eval_exact_match": 0.0454,
|
507 |
+
"eval_f1": 0.4504,
|
508 |
+
"eval_gen_len": 13.7432,
|
509 |
+
"eval_loss": 1.2803738117218018,
|
510 |
+
"eval_precisions_1": 53.4382,
|
511 |
+
"eval_precisions_2": 26.9752,
|
512 |
+
"eval_precisions_3": 17.1144,
|
513 |
+
"eval_precisions_4": 11.3569,
|
514 |
+
"eval_ref_len": 21250,
|
515 |
+
"eval_rouge1": 0.4592,
|
516 |
+
"eval_rouge2": 0.2671,
|
517 |
+
"eval_rougeL": 0.4443,
|
518 |
+
"eval_rougeLsum": 0.4436,
|
519 |
+
"eval_runtime": 3989.4275,
|
520 |
+
"eval_samples_per_second": 0.552,
|
521 |
+
"eval_steps_per_second": 0.552,
|
522 |
+
"eval_sys_len": 18367,
|
523 |
+
"eval_totals_1": 18367,
|
524 |
+
"eval_totals_2": 16163,
|
525 |
+
"eval_totals_3": 13959,
|
526 |
+
"eval_totals_4": 11755,
|
527 |
+
"step": 2036
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 14.99,
|
531 |
+
"learning_rate": 0.0001,
|
532 |
+
"loss": 0.4902,
|
533 |
+
"step": 2181
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 14.99,
|
537 |
+
"eval_bleu": 19.8138,
|
538 |
+
"eval_bp": 0.8766,
|
539 |
+
"eval_counts_1": 9886,
|
540 |
+
"eval_counts_2": 4407,
|
541 |
+
"eval_counts_3": 2398,
|
542 |
+
"eval_counts_4": 1359,
|
543 |
+
"eval_exact_match": 0.0495,
|
544 |
+
"eval_f1": 0.451,
|
545 |
+
"eval_gen_len": 14.1225,
|
546 |
+
"eval_loss": 1.321104884147644,
|
547 |
+
"eval_precisions_1": 52.6495,
|
548 |
+
"eval_precisions_2": 26.5914,
|
549 |
+
"eval_precisions_3": 16.6887,
|
550 |
+
"eval_precisions_4": 11.1714,
|
551 |
+
"eval_ref_len": 21250,
|
552 |
+
"eval_rouge1": 0.4582,
|
553 |
+
"eval_rouge2": 0.2674,
|
554 |
+
"eval_rougeL": 0.4426,
|
555 |
+
"eval_rougeLsum": 0.4421,
|
556 |
+
"eval_runtime": 2190.6068,
|
557 |
+
"eval_samples_per_second": 1.006,
|
558 |
+
"eval_steps_per_second": 1.006,
|
559 |
+
"eval_sys_len": 18777,
|
560 |
+
"eval_totals_1": 18777,
|
561 |
+
"eval_totals_2": 16573,
|
562 |
+
"eval_totals_3": 14369,
|
563 |
+
"eval_totals_4": 12165,
|
564 |
+
"step": 2181
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 16.0,
|
568 |
+
"learning_rate": 0.0001,
|
569 |
+
"loss": 0.4498,
|
570 |
+
"step": 2327
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 16.0,
|
574 |
+
"eval_bleu": 20.0703,
|
575 |
+
"eval_bp": 0.909,
|
576 |
+
"eval_counts_1": 10008,
|
577 |
+
"eval_counts_2": 4477,
|
578 |
+
"eval_counts_3": 2456,
|
579 |
+
"eval_counts_4": 1381,
|
580 |
+
"eval_exact_match": 0.0476,
|
581 |
+
"eval_f1": 0.4491,
|
582 |
+
"eval_gen_len": 14.3725,
|
583 |
+
"eval_loss": 1.3620938062667847,
|
584 |
+
"eval_precisions_1": 51.5903,
|
585 |
+
"eval_precisions_2": 26.0366,
|
586 |
+
"eval_precisions_3": 16.3832,
|
587 |
+
"eval_precisions_4": 10.8,
|
588 |
+
"eval_ref_len": 21250,
|
589 |
+
"eval_rouge1": 0.4569,
|
590 |
+
"eval_rouge2": 0.2679,
|
591 |
+
"eval_rougeL": 0.4415,
|
592 |
+
"eval_rougeLsum": 0.4412,
|
593 |
+
"eval_runtime": 4080.8757,
|
594 |
+
"eval_samples_per_second": 0.54,
|
595 |
+
"eval_steps_per_second": 0.54,
|
596 |
+
"eval_sys_len": 19399,
|
597 |
+
"eval_totals_1": 19399,
|
598 |
+
"eval_totals_2": 17195,
|
599 |
+
"eval_totals_3": 14991,
|
600 |
+
"eval_totals_4": 12787,
|
601 |
+
"step": 2327
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 16.99,
|
605 |
+
"learning_rate": 0.0001,
|
606 |
+
"loss": 0.4216,
|
607 |
+
"step": 2472
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 16.99,
|
611 |
+
"eval_bleu": 20.1319,
|
612 |
+
"eval_bp": 0.8948,
|
613 |
+
"eval_counts_1": 10016,
|
614 |
+
"eval_counts_2": 4483,
|
615 |
+
"eval_counts_3": 2455,
|
616 |
+
"eval_counts_4": 1385,
|
617 |
+
"eval_exact_match": 0.0481,
|
618 |
+
"eval_f1": 0.4531,
|
619 |
+
"eval_gen_len": 14.3008,
|
620 |
+
"eval_loss": 1.3966974020004272,
|
621 |
+
"eval_precisions_1": 52.3712,
|
622 |
+
"eval_precisions_2": 26.4937,
|
623 |
+
"eval_precisions_3": 16.6814,
|
624 |
+
"eval_precisions_4": 11.0685,
|
625 |
+
"eval_ref_len": 21250,
|
626 |
+
"eval_rouge1": 0.4615,
|
627 |
+
"eval_rouge2": 0.2705,
|
628 |
+
"eval_rougeL": 0.4457,
|
629 |
+
"eval_rougeLsum": 0.4451,
|
630 |
+
"eval_runtime": 3311.0939,
|
631 |
+
"eval_samples_per_second": 0.666,
|
632 |
+
"eval_steps_per_second": 0.666,
|
633 |
+
"eval_sys_len": 19125,
|
634 |
+
"eval_totals_1": 19125,
|
635 |
+
"eval_totals_2": 16921,
|
636 |
+
"eval_totals_3": 14717,
|
637 |
+
"eval_totals_4": 12513,
|
638 |
+
"step": 2472
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 18.0,
|
642 |
+
"learning_rate": 0.0001,
|
643 |
+
"loss": 0.3829,
|
644 |
+
"step": 2618
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 18.0,
|
648 |
+
"eval_bleu": 19.8508,
|
649 |
+
"eval_bp": 0.9123,
|
650 |
+
"eval_counts_1": 9976,
|
651 |
+
"eval_counts_2": 4407,
|
652 |
+
"eval_counts_3": 2412,
|
653 |
+
"eval_counts_4": 1374,
|
654 |
+
"eval_exact_match": 0.0476,
|
655 |
+
"eval_f1": 0.4479,
|
656 |
+
"eval_gen_len": 14.7046,
|
657 |
+
"eval_loss": 1.4460452795028687,
|
658 |
+
"eval_precisions_1": 51.2536,
|
659 |
+
"eval_precisions_2": 25.533,
|
660 |
+
"eval_precisions_3": 16.0202,
|
661 |
+
"eval_precisions_4": 10.6909,
|
662 |
+
"eval_ref_len": 21250,
|
663 |
+
"eval_rouge1": 0.4556,
|
664 |
+
"eval_rouge2": 0.2627,
|
665 |
+
"eval_rougeL": 0.4387,
|
666 |
+
"eval_rougeLsum": 0.4385,
|
667 |
+
"eval_runtime": 3748.4463,
|
668 |
+
"eval_samples_per_second": 0.588,
|
669 |
+
"eval_steps_per_second": 0.588,
|
670 |
+
"eval_sys_len": 19464,
|
671 |
+
"eval_totals_1": 19464,
|
672 |
+
"eval_totals_2": 17260,
|
673 |
+
"eval_totals_3": 15056,
|
674 |
+
"eval_totals_4": 12852,
|
675 |
+
"step": 2618
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 19.0,
|
679 |
+
"learning_rate": 0.0001,
|
680 |
+
"loss": 0.3551,
|
681 |
+
"step": 2764
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 19.0,
|
685 |
+
"eval_bleu": 20.0572,
|
686 |
+
"eval_bp": 0.8952,
|
687 |
+
"eval_counts_1": 10010,
|
688 |
+
"eval_counts_2": 4451,
|
689 |
+
"eval_counts_3": 2438,
|
690 |
+
"eval_counts_4": 1385,
|
691 |
+
"eval_exact_match": 0.0463,
|
692 |
+
"eval_f1": 0.4523,
|
693 |
+
"eval_gen_len": 14.3807,
|
694 |
+
"eval_loss": 1.4725110530853271,
|
695 |
+
"eval_precisions_1": 52.3235,
|
696 |
+
"eval_precisions_2": 26.2953,
|
697 |
+
"eval_precisions_3": 16.5591,
|
698 |
+
"eval_precisions_4": 11.0632,
|
699 |
+
"eval_ref_len": 21250,
|
700 |
+
"eval_rouge1": 0.4606,
|
701 |
+
"eval_rouge2": 0.2672,
|
702 |
+
"eval_rougeL": 0.4438,
|
703 |
+
"eval_rougeLsum": 0.4434,
|
704 |
+
"eval_runtime": 2215.2029,
|
705 |
+
"eval_samples_per_second": 0.995,
|
706 |
+
"eval_steps_per_second": 0.995,
|
707 |
+
"eval_sys_len": 19131,
|
708 |
+
"eval_totals_1": 19131,
|
709 |
+
"eval_totals_2": 16927,
|
710 |
+
"eval_totals_3": 14723,
|
711 |
+
"eval_totals_4": 12519,
|
712 |
+
"step": 2764
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 19.93,
|
716 |
+
"learning_rate": 0.0001,
|
717 |
+
"loss": 0.3301,
|
718 |
+
"step": 2900
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 19.93,
|
722 |
+
"eval_bleu": 19.8047,
|
723 |
+
"eval_bp": 0.8816,
|
724 |
+
"eval_counts_1": 9858,
|
725 |
+
"eval_counts_2": 4378,
|
726 |
+
"eval_counts_3": 2406,
|
727 |
+
"eval_counts_4": 1368,
|
728 |
+
"eval_exact_match": 0.0495,
|
729 |
+
"eval_f1": 0.4483,
|
730 |
+
"eval_gen_len": 14.2795,
|
731 |
+
"eval_loss": 1.5030488967895508,
|
732 |
+
"eval_precisions_1": 52.2361,
|
733 |
+
"eval_precisions_2": 26.2659,
|
734 |
+
"eval_precisions_3": 16.6344,
|
735 |
+
"eval_precisions_4": 11.1582,
|
736 |
+
"eval_ref_len": 21250,
|
737 |
+
"eval_rouge1": 0.4569,
|
738 |
+
"eval_rouge2": 0.2644,
|
739 |
+
"eval_rougeL": 0.4412,
|
740 |
+
"eval_rougeLsum": 0.4405,
|
741 |
+
"eval_runtime": 2181.7432,
|
742 |
+
"eval_samples_per_second": 1.01,
|
743 |
+
"eval_steps_per_second": 1.01,
|
744 |
+
"eval_sys_len": 18872,
|
745 |
+
"eval_totals_1": 18872,
|
746 |
+
"eval_totals_2": 16668,
|
747 |
+
"eval_totals_3": 14464,
|
748 |
+
"eval_totals_4": 12260,
|
749 |
+
"step": 2900
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 19.93,
|
753 |
+
"step": 2900,
|
754 |
+
"total_flos": 1.1100924470624256e+18,
|
755 |
+
"train_loss": 0.6333936349276839,
|
756 |
+
"train_runtime": 110329.1002,
|
757 |
+
"train_samples_per_second": 1.688,
|
758 |
+
"train_steps_per_second": 0.026
|
759 |
+
}
|
760 |
+
],
|
761 |
+
"logging_steps": 500,
|
762 |
+
"max_steps": 2900,
|
763 |
+
"num_train_epochs": 20,
|
764 |
+
"save_steps": 500,
|
765 |
+
"total_flos": 1.1100924470624256e+18,
|
766 |
+
"trial_name": null,
|
767 |
+
"trial_params": null
|
768 |
+
}
|
training_args.bin
ADDED
Binary file (4.66 kB). View file
|
|