init project
Browse files- .gitattributes +1 -0
- README.md +127 -0
- all_results.json +28 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- rust_model.ot +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +1108 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- summarization
|
4 |
+
- mT5
|
5 |
+
language:
|
6 |
+
- zh
|
7 |
+
widget:
|
8 |
+
- text: "專家稱維康桑格研究所(Wellcome Sanger Institute)的上述研究發現「令人震驚」而且「發人深省」。基因變異指關於我們身體成長和管理的相關指令,也就是DNA當中發生的變化。長期以來,變異一直被當作癌症的根源,但是數十年來關於變異是否對衰老有重要影響一直存在爭論。桑格研究所的研究人員說他們得到了「第一個試驗性證據」,證明了兩者的關係。他們分析了預期壽命各異的物種基因變異的不同速度。研究人員分析了貓、黑白疣猴、狗、雪貂、長頸鹿、馬、人、獅子、裸鼴鼠、兔子、老鼠、環尾狐猴和老虎等十幾種動物的DNA。發表在《自然》雜誌上的研究顯示,老鼠在短暫的生命當中每年經歷了將近800次變異,老鼠的壽命一般不到4年。"
|
9 |
+
|
10 |
+
---
|
11 |
+
|
12 |
+
---
|
13 |
+
license: apache-2.0
|
14 |
+
tags:
|
15 |
+
- Summarization
|
16 |
+
metrics:
|
17 |
+
- rouge
|
18 |
+
model-index:
|
19 |
+
- name: best_model_test_0423_small
|
20 |
+
results: []
|
21 |
+
|
22 |
+
---
|
23 |
+
# best_model_test_0423_small
|
24 |
+
|
25 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
26 |
+
It achieves the following results on the evaluation set:
|
27 |
+
- Loss: 2.6341
|
28 |
+
- Rouge1: 18.7681
|
29 |
+
- Rouge2: 6.3762
|
30 |
+
- Rougel: 18.6081
|
31 |
+
- Rougelsum: 18.6173
|
32 |
+
- Gen Len: 22.1086
|
33 |
+
|
34 |
+
## Model description
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Intended uses & limitations
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training and evaluation data
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training procedure
|
47 |
+
|
48 |
+
### Training hyperparameters
|
49 |
+
|
50 |
+
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 0.0001
|
52 |
+
- train_batch_size: 2
|
53 |
+
- eval_batch_size: 2
|
54 |
+
- seed: 42
|
55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
+
- lr_scheduler_type: linear
|
57 |
+
- num_epochs: 3
|
58 |
+
|
59 |
+
### Training results
|
60 |
+
|
61 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
62 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
|
63 |
+
| 5.8165 | 0.05 | 1000 | 3.6541 | 11.6734 | 3.9865 | 11.5734 | 11.5375 | 18.0056 |
|
64 |
+
| 4.306 | 0.1 | 2000 | 3.4291 | 12.0417 | 3.8419 | 11.9231 | 11.9223 | 16.8948 |
|
65 |
+
| 4.1091 | 0.16 | 3000 | 3.3643 | 13.661 | 4.5171 | 13.5123 | 13.5076 | 19.4016 |
|
66 |
+
| 3.9637 | 0.21 | 4000 | 3.2574 | 13.8443 | 4.1761 | 13.689 | 13.6927 | 18.4288 |
|
67 |
+
| 3.8205 | 0.26 | 5000 | 3.2434 | 13.5371 | 4.3639 | 13.3551 | 13.3552 | 21.5776 |
|
68 |
+
| 3.7262 | 0.31 | 6000 | 3.1690 | 14.3668 | 4.8048 | 14.2191 | 14.1906 | 21.5548 |
|
69 |
+
| 3.6887 | 0.36 | 7000 | 3.0657 | 14.3265 | 4.436 | 14.212 | 14.205 | 20.89 |
|
70 |
+
| 3.6337 | 0.42 | 8000 | 3.0318 | 14.6809 | 4.8345 | 14.5378 | 14.5331 | 20.3651 |
|
71 |
+
| 3.5443 | 0.47 | 9000 | 3.0554 | 15.3372 | 4.9163 | 15.1794 | 15.1781 | 21.7742 |
|
72 |
+
| 3.5203 | 0.52 | 10000 | 2.9793 | 14.9278 | 4.9656 | 14.7491 | 14.743 | 20.8113 |
|
73 |
+
| 3.4936 | 0.57 | 11000 | 3.0079 | 15.7705 | 5.1453 | 15.5582 | 15.5756 | 23.4274 |
|
74 |
+
| 3.4592 | 0.62 | 12000 | 2.9721 | 15.0201 | 5.1612 | 14.8508 | 14.8198 | 22.7007 |
|
75 |
+
| 3.377 | 0.67 | 13000 | 3.0112 | 15.9595 | 5.1133 | 15.78 | 15.7774 | 23.4427 |
|
76 |
+
| 3.4158 | 0.73 | 14000 | 2.9239 | 14.7984 | 5.051 | 14.6943 | 14.6581 | 21.6009 |
|
77 |
+
| 3.378 | 0.78 | 15000 | 2.8897 | 16.5128 | 5.1923 | 16.3523 | 16.3265 | 22.0828 |
|
78 |
+
| 3.3231 | 0.83 | 16000 | 2.9347 | 16.9997 | 5.5524 | 16.8534 | 16.8737 | 22.5807 |
|
79 |
+
| 3.3268 | 0.88 | 17000 | 2.9116 | 16.0261 | 5.4226 | 15.9234 | 15.914 | 23.6988 |
|
80 |
+
| 3.3127 | 0.93 | 18000 | 2.8610 | 16.6255 | 5.3554 | 16.4729 | 16.4569 | 22.9481 |
|
81 |
+
| 3.2664 | 0.99 | 19000 | 2.8606 | 17.7703 | 5.9475 | 17.6229 | 17.6259 | 23.4423 |
|
82 |
+
| 3.1718 | 1.04 | 20000 | 2.8764 | 17.301 | 5.6262 | 17.122 | 17.1104 | 23.0093 |
|
83 |
+
| 3.0987 | 1.09 | 21000 | 2.8282 | 16.4718 | 5.2077 | 16.3394 | 16.3401 | 20.9697 |
|
84 |
+
| 3.1486 | 1.14 | 22000 | 2.8235 | 18.5594 | 5.9469 | 18.3882 | 18.3799 | 22.7291 |
|
85 |
+
| 3.1435 | 1.19 | 23000 | 2.8261 | 18.111 | 6.0309 | 17.9593 | 17.9613 | 22.9612 |
|
86 |
+
| 3.1049 | 1.25 | 24000 | 2.8068 | 17.124 | 5.5675 | 16.9714 | 16.9876 | 22.5558 |
|
87 |
+
| 3.1357 | 1.3 | 25000 | 2.8014 | 17.3916 | 5.8671 | 17.2148 | 17.2502 | 23.0075 |
|
88 |
+
| 3.0904 | 1.35 | 26000 | 2.7790 | 17.419 | 5.6689 | 17.3125 | 17.3058 | 22.1492 |
|
89 |
+
| 3.0877 | 1.4 | 27000 | 2.7462 | 17.0605 | 5.4735 | 16.9414 | 16.9378 | 21.7522 |
|
90 |
+
| 3.0694 | 1.45 | 28000 | 2.7563 | 17.752 | 5.8889 | 17.5967 | 17.619 | 23.2005 |
|
91 |
+
| 3.0498 | 1.51 | 29000 | 2.7521 | 17.9056 | 5.7754 | 17.7624 | 17.7836 | 21.9369 |
|
92 |
+
| 3.0566 | 1.56 | 30000 | 2.7468 | 18.6531 | 6.0538 | 18.5397 | 18.5038 | 22.2358 |
|
93 |
+
| 3.0489 | 1.61 | 31000 | 2.7450 | 18.4869 | 5.9297 | 18.3139 | 18.3169 | 22.0108 |
|
94 |
+
| 3.0247 | 1.66 | 32000 | 2.7449 | 18.5192 | 5.9966 | 18.3721 | 18.3569 | 22.2071 |
|
95 |
+
| 2.9877 | 1.71 | 33000 | 2.7160 | 18.1655 | 5.9294 | 18.0304 | 18.0836 | 21.4595 |
|
96 |
+
| 3.0383 | 1.76 | 34000 | 2.7202 | 18.4959 | 6.2413 | 18.3363 | 18.3431 | 22.9732 |
|
97 |
+
| 3.041 | 1.82 | 35000 | 2.6948 | 17.5306 | 5.8119 | 17.4011 | 17.4149 | 21.9435 |
|
98 |
+
| 2.9285 | 1.87 | 36000 | 2.6957 | 18.6418 | 6.1394 | 18.514 | 18.4823 | 22.5174 |
|
99 |
+
| 3.0556 | 1.92 | 37000 | 2.7000 | 18.7387 | 6.0585 | 18.5761 | 18.574 | 22.9315 |
|
100 |
+
| 3.0033 | 1.97 | 38000 | 2.6974 | 17.9387 | 6.1387 | 17.8271 | 17.8111 | 22.4726 |
|
101 |
+
| 2.9207 | 2.02 | 39000 | 2.6998 | 18.6073 | 6.1906 | 18.3891 | 18.4103 | 23.0274 |
|
102 |
+
| 2.8922 | 2.08 | 40000 | 2.6798 | 18.4017 | 6.2244 | 18.2321 | 18.2296 | 22.0697 |
|
103 |
+
| 2.8938 | 2.13 | 41000 | 2.6666 | 18.8016 | 6.2066 | 18.6411 | 18.6353 | 21.7017 |
|
104 |
+
| 2.9124 | 2.18 | 42000 | 2.6606 | 18.7544 | 6.3533 | 18.5923 | 18.5739 | 21.4303 |
|
105 |
+
| 2.8597 | 2.23 | 43000 | 2.6947 | 18.8672 | 6.4526 | 18.7416 | 18.7482 | 22.3352 |
|
106 |
+
| 2.8435 | 2.28 | 44000 | 2.6738 | 18.9405 | 6.356 | 18.7791 | 18.7729 | 21.9081 |
|
107 |
+
| 2.8672 | 2.34 | 45000 | 2.6734 | 18.7509 | 6.3991 | 18.6175 | 18.5828 | 21.8869 |
|
108 |
+
| 2.899 | 2.39 | 46000 | 2.6575 | 18.5529 | 6.3489 | 18.4139 | 18.401 | 21.7694 |
|
109 |
+
| 2.8616 | 2.44 | 47000 | 2.6485 | 18.7563 | 6.268 | 18.6368 | 18.6253 | 21.5685 |
|
110 |
+
| 2.8937 | 2.49 | 48000 | 2.6486 | 18.6525 | 6.3426 | 18.5184 | 18.5129 | 22.3337 |
|
111 |
+
| 2.8446 | 2.54 | 49000 | 2.6572 | 18.6529 | 6.2655 | 18.4915 | 18.4764 | 22.3331 |
|
112 |
+
| 2.8676 | 2.59 | 50000 | 2.6608 | 19.0913 | 6.494 | 18.929 | 18.9233 | 22.132 |
|
113 |
+
| 2.8794 | 2.65 | 51000 | 2.6583 | 18.7648 | 6.459 | 18.6276 | 18.6125 | 22.2414 |
|
114 |
+
| 2.8836 | 2.7 | 52000 | 2.6512 | 18.7243 | 6.3865 | 18.5848 | 18.5763 | 22.2551 |
|
115 |
+
| 2.8174 | 2.75 | 53000 | 2.6409 | 18.9393 | 6.3914 | 18.7733 | 18.7715 | 22.1243 |
|
116 |
+
| 2.8494 | 2.8 | 54000 | 2.6396 | 18.6126 | 6.4389 | 18.4673 | 18.4516 | 21.7638 |
|
117 |
+
| 2.9025 | 2.85 | 55000 | 2.6341 | 18.7681 | 6.3762 | 18.6081 | 18.6173 | 22.1086 |
|
118 |
+
| 2.8754 | 2.91 | 56000 | 2.6388 | 19.0828 | 6.5203 | 18.9334 | 18.9285 | 22.3497 |
|
119 |
+
| 2.8489 | 2.96 | 57000 | 2.6375 | 18.9219 | 6.4922 | 18.763 | 18.7437 | 21.9321 |
|
120 |
+
|
121 |
+
|
122 |
+
### Framework versions
|
123 |
+
|
124 |
+
- Transformers 4.18.0
|
125 |
+
- Pytorch 1.10.1+cu113
|
126 |
+
- Datasets 2.0.0
|
127 |
+
- Tokenizers 0.11.6
|
all_results.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_gen_len": 22.1086,
|
4 |
+
"eval_loss": 2.63411021232605,
|
5 |
+
"eval_rouge1": 18.7681,
|
6 |
+
"eval_rouge2": 6.3762,
|
7 |
+
"eval_rougeL": 18.6081,
|
8 |
+
"eval_rougeLsum": 18.6173,
|
9 |
+
"eval_runtime": 868.7385,
|
10 |
+
"eval_samples": 4818,
|
11 |
+
"eval_samples_per_second": 5.546,
|
12 |
+
"eval_steps_per_second": 2.773,
|
13 |
+
"predict_gen_len": 21.9325,
|
14 |
+
"predict_loss": 2.677487373352051,
|
15 |
+
"predict_rouge1": 18.549,
|
16 |
+
"predict_rouge2": 6.1779,
|
17 |
+
"predict_rougeL": 18.4105,
|
18 |
+
"predict_rougeLsum": 18.4124,
|
19 |
+
"predict_runtime": 856.4166,
|
20 |
+
"predict_samples": 4817,
|
21 |
+
"predict_samples_per_second": 5.625,
|
22 |
+
"predict_steps_per_second": 2.813,
|
23 |
+
"train_loss": 3.210809704903007,
|
24 |
+
"train_runtime": 55943.4873,
|
25 |
+
"train_samples": 38538,
|
26 |
+
"train_samples_per_second": 2.067,
|
27 |
+
"train_steps_per_second": 1.033
|
28 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mt5-small",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 1024,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 512,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "mt5",
|
17 |
+
"num_decoder_layers": 8,
|
18 |
+
"num_heads": 6,
|
19 |
+
"num_layers": 8,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"relative_attention_max_distance": 128,
|
22 |
+
"relative_attention_num_buckets": 32,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"tokenizer_class": "T5Tokenizer",
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.18.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 250100
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62a4076a6e6d6c06a1d4cfd64afbd638faef7d7d60864bb383e87cef8d9536c9
|
3 |
+
size 1200721733
|
rust_model.ot
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3b4701a0f1b4d95b69ca800cef47576572a8b1bb7a4f18d55ab9c8e4fead4b7
|
3 |
+
size 2225128747
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
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 sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
|
3 |
+
size 16330369
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/deeprd2/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 3.210809704903007,
|
4 |
+
"train_runtime": 55943.4873,
|
5 |
+
"train_samples": 38538,
|
6 |
+
"train_samples_per_second": 2.067,
|
7 |
+
"train_steps_per_second": 1.033
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 2.63411021232605,
|
3 |
+
"best_model_checkpoint": "model/best_model_test_0423_small/checkpoint-55000",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 57807,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.05,
|
12 |
+
"learning_rate": 9.827010569654195e-05,
|
13 |
+
"loss": 5.8165,
|
14 |
+
"step": 1000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.05,
|
18 |
+
"eval_gen_len": 18.0056,
|
19 |
+
"eval_loss": 3.6540932655334473,
|
20 |
+
"eval_rouge1": 11.6734,
|
21 |
+
"eval_rouge2": 3.9865,
|
22 |
+
"eval_rougeL": 11.5734,
|
23 |
+
"eval_rougeLsum": 11.5375,
|
24 |
+
"eval_runtime": 831.6458,
|
25 |
+
"eval_samples_per_second": 5.793,
|
26 |
+
"eval_steps_per_second": 2.897,
|
27 |
+
"step": 1000
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.1,
|
31 |
+
"learning_rate": 9.654021139308389e-05,
|
32 |
+
"loss": 4.306,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.1,
|
37 |
+
"eval_gen_len": 16.8948,
|
38 |
+
"eval_loss": 3.4290754795074463,
|
39 |
+
"eval_rouge1": 12.0417,
|
40 |
+
"eval_rouge2": 3.8419,
|
41 |
+
"eval_rougeL": 11.9231,
|
42 |
+
"eval_rougeLsum": 11.9223,
|
43 |
+
"eval_runtime": 769.6461,
|
44 |
+
"eval_samples_per_second": 6.26,
|
45 |
+
"eval_steps_per_second": 3.13,
|
46 |
+
"step": 2000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.16,
|
50 |
+
"learning_rate": 9.481031708962583e-05,
|
51 |
+
"loss": 4.1091,
|
52 |
+
"step": 3000
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.16,
|
56 |
+
"eval_gen_len": 19.4016,
|
57 |
+
"eval_loss": 3.364335060119629,
|
58 |
+
"eval_rouge1": 13.661,
|
59 |
+
"eval_rouge2": 4.5171,
|
60 |
+
"eval_rougeL": 13.5123,
|
61 |
+
"eval_rougeLsum": 13.5076,
|
62 |
+
"eval_runtime": 875.4047,
|
63 |
+
"eval_samples_per_second": 5.504,
|
64 |
+
"eval_steps_per_second": 2.752,
|
65 |
+
"step": 3000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.21,
|
69 |
+
"learning_rate": 9.308042278616777e-05,
|
70 |
+
"loss": 3.9637,
|
71 |
+
"step": 4000
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.21,
|
75 |
+
"eval_gen_len": 18.4288,
|
76 |
+
"eval_loss": 3.2573604583740234,
|
77 |
+
"eval_rouge1": 13.8443,
|
78 |
+
"eval_rouge2": 4.1761,
|
79 |
+
"eval_rougeL": 13.689,
|
80 |
+
"eval_rougeLsum": 13.6927,
|
81 |
+
"eval_runtime": 771.3843,
|
82 |
+
"eval_samples_per_second": 6.246,
|
83 |
+
"eval_steps_per_second": 3.123,
|
84 |
+
"step": 4000
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.26,
|
88 |
+
"learning_rate": 9.135052848270971e-05,
|
89 |
+
"loss": 3.8205,
|
90 |
+
"step": 5000
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.26,
|
94 |
+
"eval_gen_len": 21.5776,
|
95 |
+
"eval_loss": 3.2433691024780273,
|
96 |
+
"eval_rouge1": 13.5371,
|
97 |
+
"eval_rouge2": 4.3639,
|
98 |
+
"eval_rougeL": 13.3551,
|
99 |
+
"eval_rougeLsum": 13.3552,
|
100 |
+
"eval_runtime": 903.4907,
|
101 |
+
"eval_samples_per_second": 5.333,
|
102 |
+
"eval_steps_per_second": 2.666,
|
103 |
+
"step": 5000
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 0.31,
|
107 |
+
"learning_rate": 8.962063417925165e-05,
|
108 |
+
"loss": 3.7262,
|
109 |
+
"step": 6000
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.31,
|
113 |
+
"eval_gen_len": 21.5548,
|
114 |
+
"eval_loss": 3.1689953804016113,
|
115 |
+
"eval_rouge1": 14.3668,
|
116 |
+
"eval_rouge2": 4.8048,
|
117 |
+
"eval_rougeL": 14.2191,
|
118 |
+
"eval_rougeLsum": 14.1906,
|
119 |
+
"eval_runtime": 870.3487,
|
120 |
+
"eval_samples_per_second": 5.536,
|
121 |
+
"eval_steps_per_second": 2.768,
|
122 |
+
"step": 6000
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.36,
|
126 |
+
"learning_rate": 8.78907398757936e-05,
|
127 |
+
"loss": 3.6887,
|
128 |
+
"step": 7000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.36,
|
132 |
+
"eval_gen_len": 20.89,
|
133 |
+
"eval_loss": 3.0656516551971436,
|
134 |
+
"eval_rouge1": 14.3265,
|
135 |
+
"eval_rouge2": 4.436,
|
136 |
+
"eval_rougeL": 14.212,
|
137 |
+
"eval_rougeLsum": 14.205,
|
138 |
+
"eval_runtime": 840.9965,
|
139 |
+
"eval_samples_per_second": 5.729,
|
140 |
+
"eval_steps_per_second": 2.864,
|
141 |
+
"step": 7000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.42,
|
145 |
+
"learning_rate": 8.616084557233554e-05,
|
146 |
+
"loss": 3.6337,
|
147 |
+
"step": 8000
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.42,
|
151 |
+
"eval_gen_len": 20.3651,
|
152 |
+
"eval_loss": 3.031759262084961,
|
153 |
+
"eval_rouge1": 14.6809,
|
154 |
+
"eval_rouge2": 4.8345,
|
155 |
+
"eval_rougeL": 14.5378,
|
156 |
+
"eval_rougeLsum": 14.5331,
|
157 |
+
"eval_runtime": 836.4852,
|
158 |
+
"eval_samples_per_second": 5.76,
|
159 |
+
"eval_steps_per_second": 2.88,
|
160 |
+
"step": 8000
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.47,
|
164 |
+
"learning_rate": 8.443095126887747e-05,
|
165 |
+
"loss": 3.5443,
|
166 |
+
"step": 9000
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.47,
|
170 |
+
"eval_gen_len": 21.7742,
|
171 |
+
"eval_loss": 3.0553905963897705,
|
172 |
+
"eval_rouge1": 15.3372,
|
173 |
+
"eval_rouge2": 4.9163,
|
174 |
+
"eval_rougeL": 15.1794,
|
175 |
+
"eval_rougeLsum": 15.1781,
|
176 |
+
"eval_runtime": 893.8221,
|
177 |
+
"eval_samples_per_second": 5.39,
|
178 |
+
"eval_steps_per_second": 2.695,
|
179 |
+
"step": 9000
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.52,
|
183 |
+
"learning_rate": 8.270105696541942e-05,
|
184 |
+
"loss": 3.5203,
|
185 |
+
"step": 10000
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.52,
|
189 |
+
"eval_gen_len": 20.8113,
|
190 |
+
"eval_loss": 2.9792585372924805,
|
191 |
+
"eval_rouge1": 14.9278,
|
192 |
+
"eval_rouge2": 4.9656,
|
193 |
+
"eval_rougeL": 14.7491,
|
194 |
+
"eval_rougeLsum": 14.743,
|
195 |
+
"eval_runtime": 848.3297,
|
196 |
+
"eval_samples_per_second": 5.679,
|
197 |
+
"eval_steps_per_second": 2.84,
|
198 |
+
"step": 10000
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.57,
|
202 |
+
"learning_rate": 8.097116266196136e-05,
|
203 |
+
"loss": 3.4936,
|
204 |
+
"step": 11000
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.57,
|
208 |
+
"eval_gen_len": 23.4274,
|
209 |
+
"eval_loss": 3.0078511238098145,
|
210 |
+
"eval_rouge1": 15.7705,
|
211 |
+
"eval_rouge2": 5.1453,
|
212 |
+
"eval_rougeL": 15.5582,
|
213 |
+
"eval_rougeLsum": 15.5756,
|
214 |
+
"eval_runtime": 944.685,
|
215 |
+
"eval_samples_per_second": 5.1,
|
216 |
+
"eval_steps_per_second": 2.55,
|
217 |
+
"step": 11000
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.62,
|
221 |
+
"learning_rate": 7.92412683585033e-05,
|
222 |
+
"loss": 3.4592,
|
223 |
+
"step": 12000
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 0.62,
|
227 |
+
"eval_gen_len": 22.7007,
|
228 |
+
"eval_loss": 2.972140312194824,
|
229 |
+
"eval_rouge1": 15.0201,
|
230 |
+
"eval_rouge2": 5.1612,
|
231 |
+
"eval_rougeL": 14.8508,
|
232 |
+
"eval_rougeLsum": 14.8198,
|
233 |
+
"eval_runtime": 914.5833,
|
234 |
+
"eval_samples_per_second": 5.268,
|
235 |
+
"eval_steps_per_second": 2.634,
|
236 |
+
"step": 12000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.67,
|
240 |
+
"learning_rate": 7.751137405504524e-05,
|
241 |
+
"loss": 3.377,
|
242 |
+
"step": 13000
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.67,
|
246 |
+
"eval_gen_len": 23.4427,
|
247 |
+
"eval_loss": 3.01123309135437,
|
248 |
+
"eval_rouge1": 15.9595,
|
249 |
+
"eval_rouge2": 5.1133,
|
250 |
+
"eval_rougeL": 15.78,
|
251 |
+
"eval_rougeLsum": 15.7774,
|
252 |
+
"eval_runtime": 950.6422,
|
253 |
+
"eval_samples_per_second": 5.068,
|
254 |
+
"eval_steps_per_second": 2.534,
|
255 |
+
"step": 13000
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.73,
|
259 |
+
"learning_rate": 7.578147975158718e-05,
|
260 |
+
"loss": 3.4158,
|
261 |
+
"step": 14000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.73,
|
265 |
+
"eval_gen_len": 21.6009,
|
266 |
+
"eval_loss": 2.9238853454589844,
|
267 |
+
"eval_rouge1": 14.7984,
|
268 |
+
"eval_rouge2": 5.051,
|
269 |
+
"eval_rougeL": 14.6943,
|
270 |
+
"eval_rougeLsum": 14.6581,
|
271 |
+
"eval_runtime": 878.6968,
|
272 |
+
"eval_samples_per_second": 5.483,
|
273 |
+
"eval_steps_per_second": 2.742,
|
274 |
+
"step": 14000
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 0.78,
|
278 |
+
"learning_rate": 7.405158544812913e-05,
|
279 |
+
"loss": 3.378,
|
280 |
+
"step": 15000
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 0.78,
|
284 |
+
"eval_gen_len": 22.0828,
|
285 |
+
"eval_loss": 2.889694929122925,
|
286 |
+
"eval_rouge1": 16.5128,
|
287 |
+
"eval_rouge2": 5.1923,
|
288 |
+
"eval_rougeL": 16.3523,
|
289 |
+
"eval_rougeLsum": 16.3265,
|
290 |
+
"eval_runtime": 902.1756,
|
291 |
+
"eval_samples_per_second": 5.34,
|
292 |
+
"eval_steps_per_second": 2.67,
|
293 |
+
"step": 15000
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 0.83,
|
297 |
+
"learning_rate": 7.232169114467106e-05,
|
298 |
+
"loss": 3.3231,
|
299 |
+
"step": 16000
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.83,
|
303 |
+
"eval_gen_len": 22.5807,
|
304 |
+
"eval_loss": 2.9346752166748047,
|
305 |
+
"eval_rouge1": 16.9997,
|
306 |
+
"eval_rouge2": 5.5524,
|
307 |
+
"eval_rougeL": 16.8534,
|
308 |
+
"eval_rougeLsum": 16.8737,
|
309 |
+
"eval_runtime": 895.2014,
|
310 |
+
"eval_samples_per_second": 5.382,
|
311 |
+
"eval_steps_per_second": 2.691,
|
312 |
+
"step": 16000
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.88,
|
316 |
+
"learning_rate": 7.059179684121301e-05,
|
317 |
+
"loss": 3.3268,
|
318 |
+
"step": 17000
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.88,
|
322 |
+
"eval_gen_len": 23.6988,
|
323 |
+
"eval_loss": 2.911571741104126,
|
324 |
+
"eval_rouge1": 16.0261,
|
325 |
+
"eval_rouge2": 5.4226,
|
326 |
+
"eval_rougeL": 15.9234,
|
327 |
+
"eval_rougeLsum": 15.914,
|
328 |
+
"eval_runtime": 962.7416,
|
329 |
+
"eval_samples_per_second": 5.004,
|
330 |
+
"eval_steps_per_second": 2.502,
|
331 |
+
"step": 17000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.93,
|
335 |
+
"learning_rate": 6.886190253775494e-05,
|
336 |
+
"loss": 3.3127,
|
337 |
+
"step": 18000
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.93,
|
341 |
+
"eval_gen_len": 22.9481,
|
342 |
+
"eval_loss": 2.861004590988159,
|
343 |
+
"eval_rouge1": 16.6255,
|
344 |
+
"eval_rouge2": 5.3554,
|
345 |
+
"eval_rougeL": 16.4729,
|
346 |
+
"eval_rougeLsum": 16.4569,
|
347 |
+
"eval_runtime": 922.0145,
|
348 |
+
"eval_samples_per_second": 5.226,
|
349 |
+
"eval_steps_per_second": 2.613,
|
350 |
+
"step": 18000
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.99,
|
354 |
+
"learning_rate": 6.713200823429688e-05,
|
355 |
+
"loss": 3.2664,
|
356 |
+
"step": 19000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.99,
|
360 |
+
"eval_gen_len": 23.4423,
|
361 |
+
"eval_loss": 2.860574722290039,
|
362 |
+
"eval_rouge1": 17.7703,
|
363 |
+
"eval_rouge2": 5.9475,
|
364 |
+
"eval_rougeL": 17.6229,
|
365 |
+
"eval_rougeLsum": 17.6259,
|
366 |
+
"eval_runtime": 936.5594,
|
367 |
+
"eval_samples_per_second": 5.144,
|
368 |
+
"eval_steps_per_second": 2.572,
|
369 |
+
"step": 19000
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 1.04,
|
373 |
+
"learning_rate": 6.540211393083882e-05,
|
374 |
+
"loss": 3.1718,
|
375 |
+
"step": 20000
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 1.04,
|
379 |
+
"eval_gen_len": 23.0093,
|
380 |
+
"eval_loss": 2.8764114379882812,
|
381 |
+
"eval_rouge1": 17.301,
|
382 |
+
"eval_rouge2": 5.6262,
|
383 |
+
"eval_rougeL": 17.122,
|
384 |
+
"eval_rougeLsum": 17.1104,
|
385 |
+
"eval_runtime": 908.2265,
|
386 |
+
"eval_samples_per_second": 5.305,
|
387 |
+
"eval_steps_per_second": 2.652,
|
388 |
+
"step": 20000
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.09,
|
392 |
+
"learning_rate": 6.367221962738077e-05,
|
393 |
+
"loss": 3.0987,
|
394 |
+
"step": 21000
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.09,
|
398 |
+
"eval_gen_len": 20.9697,
|
399 |
+
"eval_loss": 2.82820200920105,
|
400 |
+
"eval_rouge1": 16.4718,
|
401 |
+
"eval_rouge2": 5.2077,
|
402 |
+
"eval_rougeL": 16.3394,
|
403 |
+
"eval_rougeLsum": 16.3401,
|
404 |
+
"eval_runtime": 831.2333,
|
405 |
+
"eval_samples_per_second": 5.796,
|
406 |
+
"eval_steps_per_second": 2.898,
|
407 |
+
"step": 21000
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 1.14,
|
411 |
+
"learning_rate": 6.19423253239227e-05,
|
412 |
+
"loss": 3.1486,
|
413 |
+
"step": 22000
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 1.14,
|
417 |
+
"eval_gen_len": 22.7291,
|
418 |
+
"eval_loss": 2.823465347290039,
|
419 |
+
"eval_rouge1": 18.5594,
|
420 |
+
"eval_rouge2": 5.9469,
|
421 |
+
"eval_rougeL": 18.3882,
|
422 |
+
"eval_rougeLsum": 18.3799,
|
423 |
+
"eval_runtime": 901.4834,
|
424 |
+
"eval_samples_per_second": 5.345,
|
425 |
+
"eval_steps_per_second": 2.672,
|
426 |
+
"step": 22000
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 1.19,
|
430 |
+
"learning_rate": 6.021243102046465e-05,
|
431 |
+
"loss": 3.1435,
|
432 |
+
"step": 23000
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 1.19,
|
436 |
+
"eval_gen_len": 22.9612,
|
437 |
+
"eval_loss": 2.826120615005493,
|
438 |
+
"eval_rouge1": 18.111,
|
439 |
+
"eval_rouge2": 6.0309,
|
440 |
+
"eval_rougeL": 17.9593,
|
441 |
+
"eval_rougeLsum": 17.9613,
|
442 |
+
"eval_runtime": 912.4414,
|
443 |
+
"eval_samples_per_second": 5.28,
|
444 |
+
"eval_steps_per_second": 2.64,
|
445 |
+
"step": 23000
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 1.25,
|
449 |
+
"learning_rate": 5.84825367170066e-05,
|
450 |
+
"loss": 3.1049,
|
451 |
+
"step": 24000
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.25,
|
455 |
+
"eval_gen_len": 22.5558,
|
456 |
+
"eval_loss": 2.8067939281463623,
|
457 |
+
"eval_rouge1": 17.124,
|
458 |
+
"eval_rouge2": 5.5675,
|
459 |
+
"eval_rougeL": 16.9714,
|
460 |
+
"eval_rougeLsum": 16.9876,
|
461 |
+
"eval_runtime": 903.448,
|
462 |
+
"eval_samples_per_second": 5.333,
|
463 |
+
"eval_steps_per_second": 2.666,
|
464 |
+
"step": 24000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.3,
|
468 |
+
"learning_rate": 5.675264241354854e-05,
|
469 |
+
"loss": 3.1357,
|
470 |
+
"step": 25000
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 1.3,
|
474 |
+
"eval_gen_len": 23.0075,
|
475 |
+
"eval_loss": 2.801447629928589,
|
476 |
+
"eval_rouge1": 17.3916,
|
477 |
+
"eval_rouge2": 5.8671,
|
478 |
+
"eval_rougeL": 17.2148,
|
479 |
+
"eval_rougeLsum": 17.2502,
|
480 |
+
"eval_runtime": 917.374,
|
481 |
+
"eval_samples_per_second": 5.252,
|
482 |
+
"eval_steps_per_second": 2.626,
|
483 |
+
"step": 25000
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 1.35,
|
487 |
+
"learning_rate": 5.5022748110090474e-05,
|
488 |
+
"loss": 3.0904,
|
489 |
+
"step": 26000
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.35,
|
493 |
+
"eval_gen_len": 22.1492,
|
494 |
+
"eval_loss": 2.7790260314941406,
|
495 |
+
"eval_rouge1": 17.419,
|
496 |
+
"eval_rouge2": 5.6689,
|
497 |
+
"eval_rougeL": 17.3125,
|
498 |
+
"eval_rougeLsum": 17.3058,
|
499 |
+
"eval_runtime": 879.4764,
|
500 |
+
"eval_samples_per_second": 5.478,
|
501 |
+
"eval_steps_per_second": 2.739,
|
502 |
+
"step": 26000
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 1.4,
|
506 |
+
"learning_rate": 5.3292853806632414e-05,
|
507 |
+
"loss": 3.0877,
|
508 |
+
"step": 27000
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 1.4,
|
512 |
+
"eval_gen_len": 21.7522,
|
513 |
+
"eval_loss": 2.7462034225463867,
|
514 |
+
"eval_rouge1": 17.0605,
|
515 |
+
"eval_rouge2": 5.4735,
|
516 |
+
"eval_rougeL": 16.9414,
|
517 |
+
"eval_rougeLsum": 16.9378,
|
518 |
+
"eval_runtime": 878.5335,
|
519 |
+
"eval_samples_per_second": 5.484,
|
520 |
+
"eval_steps_per_second": 2.742,
|
521 |
+
"step": 27000
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.45,
|
525 |
+
"learning_rate": 5.1562959503174354e-05,
|
526 |
+
"loss": 3.0694,
|
527 |
+
"step": 28000
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 1.45,
|
531 |
+
"eval_gen_len": 23.2005,
|
532 |
+
"eval_loss": 2.75631046295166,
|
533 |
+
"eval_rouge1": 17.752,
|
534 |
+
"eval_rouge2": 5.8889,
|
535 |
+
"eval_rougeL": 17.5967,
|
536 |
+
"eval_rougeLsum": 17.619,
|
537 |
+
"eval_runtime": 928.0873,
|
538 |
+
"eval_samples_per_second": 5.191,
|
539 |
+
"eval_steps_per_second": 2.596,
|
540 |
+
"step": 28000
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 1.51,
|
544 |
+
"learning_rate": 4.98330651997163e-05,
|
545 |
+
"loss": 3.0498,
|
546 |
+
"step": 29000
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 1.51,
|
550 |
+
"eval_gen_len": 21.9369,
|
551 |
+
"eval_loss": 2.752108335494995,
|
552 |
+
"eval_rouge1": 17.9056,
|
553 |
+
"eval_rouge2": 5.7754,
|
554 |
+
"eval_rougeL": 17.7624,
|
555 |
+
"eval_rougeLsum": 17.7836,
|
556 |
+
"eval_runtime": 872.1773,
|
557 |
+
"eval_samples_per_second": 5.524,
|
558 |
+
"eval_steps_per_second": 2.762,
|
559 |
+
"step": 29000
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 1.56,
|
563 |
+
"learning_rate": 4.810317089625824e-05,
|
564 |
+
"loss": 3.0566,
|
565 |
+
"step": 30000
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 1.56,
|
569 |
+
"eval_gen_len": 22.2358,
|
570 |
+
"eval_loss": 2.7468161582946777,
|
571 |
+
"eval_rouge1": 18.6531,
|
572 |
+
"eval_rouge2": 6.0538,
|
573 |
+
"eval_rougeL": 18.5397,
|
574 |
+
"eval_rougeLsum": 18.5038,
|
575 |
+
"eval_runtime": 878.1686,
|
576 |
+
"eval_samples_per_second": 5.486,
|
577 |
+
"eval_steps_per_second": 2.743,
|
578 |
+
"step": 30000
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 1.61,
|
582 |
+
"learning_rate": 4.637327659280018e-05,
|
583 |
+
"loss": 3.0489,
|
584 |
+
"step": 31000
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.61,
|
588 |
+
"eval_gen_len": 22.0108,
|
589 |
+
"eval_loss": 2.7450203895568848,
|
590 |
+
"eval_rouge1": 18.4869,
|
591 |
+
"eval_rouge2": 5.9297,
|
592 |
+
"eval_rougeL": 18.3139,
|
593 |
+
"eval_rougeLsum": 18.3169,
|
594 |
+
"eval_runtime": 856.3376,
|
595 |
+
"eval_samples_per_second": 5.626,
|
596 |
+
"eval_steps_per_second": 2.813,
|
597 |
+
"step": 31000
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 1.66,
|
601 |
+
"learning_rate": 4.464338228934212e-05,
|
602 |
+
"loss": 3.0247,
|
603 |
+
"step": 32000
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 1.66,
|
607 |
+
"eval_gen_len": 22.2071,
|
608 |
+
"eval_loss": 2.744947671890259,
|
609 |
+
"eval_rouge1": 18.5192,
|
610 |
+
"eval_rouge2": 5.9966,
|
611 |
+
"eval_rougeL": 18.3721,
|
612 |
+
"eval_rougeLsum": 18.3569,
|
613 |
+
"eval_runtime": 887.9355,
|
614 |
+
"eval_samples_per_second": 5.426,
|
615 |
+
"eval_steps_per_second": 2.713,
|
616 |
+
"step": 32000
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 1.71,
|
620 |
+
"learning_rate": 4.291348798588406e-05,
|
621 |
+
"loss": 2.9877,
|
622 |
+
"step": 33000
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 1.71,
|
626 |
+
"eval_gen_len": 21.4595,
|
627 |
+
"eval_loss": 2.7159626483917236,
|
628 |
+
"eval_rouge1": 18.1655,
|
629 |
+
"eval_rouge2": 5.9294,
|
630 |
+
"eval_rougeL": 18.0304,
|
631 |
+
"eval_rougeLsum": 18.0836,
|
632 |
+
"eval_runtime": 847.8313,
|
633 |
+
"eval_samples_per_second": 5.683,
|
634 |
+
"eval_steps_per_second": 2.841,
|
635 |
+
"step": 33000
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 1.76,
|
639 |
+
"learning_rate": 4.118359368242601e-05,
|
640 |
+
"loss": 3.0383,
|
641 |
+
"step": 34000
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 1.76,
|
645 |
+
"eval_gen_len": 22.9732,
|
646 |
+
"eval_loss": 2.720228433609009,
|
647 |
+
"eval_rouge1": 18.4959,
|
648 |
+
"eval_rouge2": 6.2413,
|
649 |
+
"eval_rougeL": 18.3363,
|
650 |
+
"eval_rougeLsum": 18.3431,
|
651 |
+
"eval_runtime": 911.6184,
|
652 |
+
"eval_samples_per_second": 5.285,
|
653 |
+
"eval_steps_per_second": 2.643,
|
654 |
+
"step": 34000
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 1.82,
|
658 |
+
"learning_rate": 3.945369937896794e-05,
|
659 |
+
"loss": 3.041,
|
660 |
+
"step": 35000
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 1.82,
|
664 |
+
"eval_gen_len": 21.9435,
|
665 |
+
"eval_loss": 2.6947648525238037,
|
666 |
+
"eval_rouge1": 17.5306,
|
667 |
+
"eval_rouge2": 5.8119,
|
668 |
+
"eval_rougeL": 17.4011,
|
669 |
+
"eval_rougeLsum": 17.4149,
|
670 |
+
"eval_runtime": 881.522,
|
671 |
+
"eval_samples_per_second": 5.466,
|
672 |
+
"eval_steps_per_second": 2.733,
|
673 |
+
"step": 35000
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 1.87,
|
677 |
+
"learning_rate": 3.772380507550989e-05,
|
678 |
+
"loss": 2.9285,
|
679 |
+
"step": 36000
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 1.87,
|
683 |
+
"eval_gen_len": 22.5174,
|
684 |
+
"eval_loss": 2.6956820487976074,
|
685 |
+
"eval_rouge1": 18.6418,
|
686 |
+
"eval_rouge2": 6.1394,
|
687 |
+
"eval_rougeL": 18.514,
|
688 |
+
"eval_rougeLsum": 18.4823,
|
689 |
+
"eval_runtime": 891.2207,
|
690 |
+
"eval_samples_per_second": 5.406,
|
691 |
+
"eval_steps_per_second": 2.703,
|
692 |
+
"step": 36000
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 1.92,
|
696 |
+
"learning_rate": 3.599391077205183e-05,
|
697 |
+
"loss": 3.0556,
|
698 |
+
"step": 37000
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 1.92,
|
702 |
+
"eval_gen_len": 22.9315,
|
703 |
+
"eval_loss": 2.7000110149383545,
|
704 |
+
"eval_rouge1": 18.7387,
|
705 |
+
"eval_rouge2": 6.0585,
|
706 |
+
"eval_rougeL": 18.5761,
|
707 |
+
"eval_rougeLsum": 18.574,
|
708 |
+
"eval_runtime": 896.5509,
|
709 |
+
"eval_samples_per_second": 5.374,
|
710 |
+
"eval_steps_per_second": 2.687,
|
711 |
+
"step": 37000
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 1.97,
|
715 |
+
"learning_rate": 3.426401646859377e-05,
|
716 |
+
"loss": 3.0033,
|
717 |
+
"step": 38000
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 1.97,
|
721 |
+
"eval_gen_len": 22.4726,
|
722 |
+
"eval_loss": 2.697437047958374,
|
723 |
+
"eval_rouge1": 17.9387,
|
724 |
+
"eval_rouge2": 6.1387,
|
725 |
+
"eval_rougeL": 17.8271,
|
726 |
+
"eval_rougeLsum": 17.8111,
|
727 |
+
"eval_runtime": 892.312,
|
728 |
+
"eval_samples_per_second": 5.399,
|
729 |
+
"eval_steps_per_second": 2.7,
|
730 |
+
"step": 38000
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 2.02,
|
734 |
+
"learning_rate": 3.253412216513571e-05,
|
735 |
+
"loss": 2.9207,
|
736 |
+
"step": 39000
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 2.02,
|
740 |
+
"eval_gen_len": 23.0274,
|
741 |
+
"eval_loss": 2.699842929840088,
|
742 |
+
"eval_rouge1": 18.6073,
|
743 |
+
"eval_rouge2": 6.1906,
|
744 |
+
"eval_rougeL": 18.3891,
|
745 |
+
"eval_rougeLsum": 18.4103,
|
746 |
+
"eval_runtime": 911.8188,
|
747 |
+
"eval_samples_per_second": 5.284,
|
748 |
+
"eval_steps_per_second": 2.642,
|
749 |
+
"step": 39000
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 2.08,
|
753 |
+
"learning_rate": 3.080422786167765e-05,
|
754 |
+
"loss": 2.8922,
|
755 |
+
"step": 40000
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 2.08,
|
759 |
+
"eval_gen_len": 22.0697,
|
760 |
+
"eval_loss": 2.67978572845459,
|
761 |
+
"eval_rouge1": 18.4017,
|
762 |
+
"eval_rouge2": 6.2244,
|
763 |
+
"eval_rougeL": 18.2321,
|
764 |
+
"eval_rougeLsum": 18.2296,
|
765 |
+
"eval_runtime": 869.5208,
|
766 |
+
"eval_samples_per_second": 5.541,
|
767 |
+
"eval_steps_per_second": 2.77,
|
768 |
+
"step": 40000
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 2.13,
|
772 |
+
"learning_rate": 2.9074333558219595e-05,
|
773 |
+
"loss": 2.8938,
|
774 |
+
"step": 41000
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 2.13,
|
778 |
+
"eval_gen_len": 21.7017,
|
779 |
+
"eval_loss": 2.666600227355957,
|
780 |
+
"eval_rouge1": 18.8016,
|
781 |
+
"eval_rouge2": 6.2066,
|
782 |
+
"eval_rougeL": 18.6411,
|
783 |
+
"eval_rougeLsum": 18.6353,
|
784 |
+
"eval_runtime": 845.165,
|
785 |
+
"eval_samples_per_second": 5.701,
|
786 |
+
"eval_steps_per_second": 2.85,
|
787 |
+
"step": 41000
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 2.18,
|
791 |
+
"learning_rate": 2.7344439254761532e-05,
|
792 |
+
"loss": 2.9124,
|
793 |
+
"step": 42000
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 2.18,
|
797 |
+
"eval_gen_len": 21.4303,
|
798 |
+
"eval_loss": 2.6605563163757324,
|
799 |
+
"eval_rouge1": 18.7544,
|
800 |
+
"eval_rouge2": 6.3533,
|
801 |
+
"eval_rougeL": 18.5923,
|
802 |
+
"eval_rougeLsum": 18.5739,
|
803 |
+
"eval_runtime": 843.6756,
|
804 |
+
"eval_samples_per_second": 5.711,
|
805 |
+
"eval_steps_per_second": 2.855,
|
806 |
+
"step": 42000
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 2.23,
|
810 |
+
"learning_rate": 2.5614544951303476e-05,
|
811 |
+
"loss": 2.8597,
|
812 |
+
"step": 43000
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 2.23,
|
816 |
+
"eval_gen_len": 22.3352,
|
817 |
+
"eval_loss": 2.694676399230957,
|
818 |
+
"eval_rouge1": 18.8672,
|
819 |
+
"eval_rouge2": 6.4526,
|
820 |
+
"eval_rougeL": 18.7416,
|
821 |
+
"eval_rougeLsum": 18.7482,
|
822 |
+
"eval_runtime": 884.9439,
|
823 |
+
"eval_samples_per_second": 5.444,
|
824 |
+
"eval_steps_per_second": 2.722,
|
825 |
+
"step": 43000
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 2.28,
|
829 |
+
"learning_rate": 2.388465064784542e-05,
|
830 |
+
"loss": 2.8435,
|
831 |
+
"step": 44000
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 2.28,
|
835 |
+
"eval_gen_len": 21.9081,
|
836 |
+
"eval_loss": 2.6738336086273193,
|
837 |
+
"eval_rouge1": 18.9405,
|
838 |
+
"eval_rouge2": 6.356,
|
839 |
+
"eval_rougeL": 18.7791,
|
840 |
+
"eval_rougeLsum": 18.7729,
|
841 |
+
"eval_runtime": 862.6512,
|
842 |
+
"eval_samples_per_second": 5.585,
|
843 |
+
"eval_steps_per_second": 2.793,
|
844 |
+
"step": 44000
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 2.34,
|
848 |
+
"learning_rate": 2.215475634438736e-05,
|
849 |
+
"loss": 2.8672,
|
850 |
+
"step": 45000
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 2.34,
|
854 |
+
"eval_gen_len": 21.8869,
|
855 |
+
"eval_loss": 2.6733603477478027,
|
856 |
+
"eval_rouge1": 18.7509,
|
857 |
+
"eval_rouge2": 6.3991,
|
858 |
+
"eval_rougeL": 18.6175,
|
859 |
+
"eval_rougeLsum": 18.5828,
|
860 |
+
"eval_runtime": 863.0328,
|
861 |
+
"eval_samples_per_second": 5.583,
|
862 |
+
"eval_steps_per_second": 2.791,
|
863 |
+
"step": 45000
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 2.39,
|
867 |
+
"learning_rate": 2.04248620409293e-05,
|
868 |
+
"loss": 2.899,
|
869 |
+
"step": 46000
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 2.39,
|
873 |
+
"eval_gen_len": 21.7694,
|
874 |
+
"eval_loss": 2.6575164794921875,
|
875 |
+
"eval_rouge1": 18.5529,
|
876 |
+
"eval_rouge2": 6.3489,
|
877 |
+
"eval_rougeL": 18.4139,
|
878 |
+
"eval_rougeLsum": 18.401,
|
879 |
+
"eval_runtime": 860.1836,
|
880 |
+
"eval_samples_per_second": 5.601,
|
881 |
+
"eval_steps_per_second": 2.801,
|
882 |
+
"step": 46000
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 2.44,
|
886 |
+
"learning_rate": 1.869496773747124e-05,
|
887 |
+
"loss": 2.8616,
|
888 |
+
"step": 47000
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 2.44,
|
892 |
+
"eval_gen_len": 21.5685,
|
893 |
+
"eval_loss": 2.6484768390655518,
|
894 |
+
"eval_rouge1": 18.7563,
|
895 |
+
"eval_rouge2": 6.268,
|
896 |
+
"eval_rougeL": 18.6368,
|
897 |
+
"eval_rougeLsum": 18.6253,
|
898 |
+
"eval_runtime": 854.7636,
|
899 |
+
"eval_samples_per_second": 5.637,
|
900 |
+
"eval_steps_per_second": 2.818,
|
901 |
+
"step": 47000
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 2.49,
|
905 |
+
"learning_rate": 1.696507343401318e-05,
|
906 |
+
"loss": 2.8937,
|
907 |
+
"step": 48000
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 2.49,
|
911 |
+
"eval_gen_len": 22.3337,
|
912 |
+
"eval_loss": 2.648592472076416,
|
913 |
+
"eval_rouge1": 18.6525,
|
914 |
+
"eval_rouge2": 6.3426,
|
915 |
+
"eval_rougeL": 18.5184,
|
916 |
+
"eval_rougeLsum": 18.5129,
|
917 |
+
"eval_runtime": 882.9047,
|
918 |
+
"eval_samples_per_second": 5.457,
|
919 |
+
"eval_steps_per_second": 2.728,
|
920 |
+
"step": 48000
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 2.54,
|
924 |
+
"learning_rate": 1.5235179130555125e-05,
|
925 |
+
"loss": 2.8446,
|
926 |
+
"step": 49000
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 2.54,
|
930 |
+
"eval_gen_len": 22.3331,
|
931 |
+
"eval_loss": 2.657186508178711,
|
932 |
+
"eval_rouge1": 18.6529,
|
933 |
+
"eval_rouge2": 6.2655,
|
934 |
+
"eval_rougeL": 18.4915,
|
935 |
+
"eval_rougeLsum": 18.4764,
|
936 |
+
"eval_runtime": 873.4651,
|
937 |
+
"eval_samples_per_second": 5.516,
|
938 |
+
"eval_steps_per_second": 2.758,
|
939 |
+
"step": 49000
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 2.59,
|
943 |
+
"learning_rate": 1.3505284827097065e-05,
|
944 |
+
"loss": 2.8676,
|
945 |
+
"step": 50000
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 2.59,
|
949 |
+
"eval_gen_len": 22.132,
|
950 |
+
"eval_loss": 2.6608123779296875,
|
951 |
+
"eval_rouge1": 19.0913,
|
952 |
+
"eval_rouge2": 6.494,
|
953 |
+
"eval_rougeL": 18.929,
|
954 |
+
"eval_rougeLsum": 18.9233,
|
955 |
+
"eval_runtime": 867.8739,
|
956 |
+
"eval_samples_per_second": 5.551,
|
957 |
+
"eval_steps_per_second": 2.776,
|
958 |
+
"step": 50000
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 2.65,
|
962 |
+
"learning_rate": 1.1775390523639005e-05,
|
963 |
+
"loss": 2.8794,
|
964 |
+
"step": 51000
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 2.65,
|
968 |
+
"eval_gen_len": 22.2414,
|
969 |
+
"eval_loss": 2.6582980155944824,
|
970 |
+
"eval_rouge1": 18.7648,
|
971 |
+
"eval_rouge2": 6.459,
|
972 |
+
"eval_rougeL": 18.6276,
|
973 |
+
"eval_rougeLsum": 18.6125,
|
974 |
+
"eval_runtime": 877.0489,
|
975 |
+
"eval_samples_per_second": 5.493,
|
976 |
+
"eval_steps_per_second": 2.747,
|
977 |
+
"step": 51000
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 2.7,
|
981 |
+
"learning_rate": 1.0045496220180947e-05,
|
982 |
+
"loss": 2.8836,
|
983 |
+
"step": 52000
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 2.7,
|
987 |
+
"eval_gen_len": 22.2551,
|
988 |
+
"eval_loss": 2.6512138843536377,
|
989 |
+
"eval_rouge1": 18.7243,
|
990 |
+
"eval_rouge2": 6.3865,
|
991 |
+
"eval_rougeL": 18.5848,
|
992 |
+
"eval_rougeLsum": 18.5763,
|
993 |
+
"eval_runtime": 879.8072,
|
994 |
+
"eval_samples_per_second": 5.476,
|
995 |
+
"eval_steps_per_second": 2.738,
|
996 |
+
"step": 52000
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 2.75,
|
1000 |
+
"learning_rate": 8.315601916722888e-06,
|
1001 |
+
"loss": 2.8174,
|
1002 |
+
"step": 53000
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 2.75,
|
1006 |
+
"eval_gen_len": 22.1243,
|
1007 |
+
"eval_loss": 2.640946865081787,
|
1008 |
+
"eval_rouge1": 18.9393,
|
1009 |
+
"eval_rouge2": 6.3914,
|
1010 |
+
"eval_rougeL": 18.7733,
|
1011 |
+
"eval_rougeLsum": 18.7715,
|
1012 |
+
"eval_runtime": 881.5366,
|
1013 |
+
"eval_samples_per_second": 5.465,
|
1014 |
+
"eval_steps_per_second": 2.733,
|
1015 |
+
"step": 53000
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 2.8,
|
1019 |
+
"learning_rate": 6.58570761326483e-06,
|
1020 |
+
"loss": 2.8494,
|
1021 |
+
"step": 54000
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 2.8,
|
1025 |
+
"eval_gen_len": 21.7638,
|
1026 |
+
"eval_loss": 2.639634132385254,
|
1027 |
+
"eval_rouge1": 18.6126,
|
1028 |
+
"eval_rouge2": 6.4389,
|
1029 |
+
"eval_rougeL": 18.4673,
|
1030 |
+
"eval_rougeLsum": 18.4516,
|
1031 |
+
"eval_runtime": 860.8517,
|
1032 |
+
"eval_samples_per_second": 5.597,
|
1033 |
+
"eval_steps_per_second": 2.798,
|
1034 |
+
"step": 54000
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 2.85,
|
1038 |
+
"learning_rate": 4.855813309806771e-06,
|
1039 |
+
"loss": 2.9025,
|
1040 |
+
"step": 55000
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 2.85,
|
1044 |
+
"eval_gen_len": 22.1086,
|
1045 |
+
"eval_loss": 2.63411021232605,
|
1046 |
+
"eval_rouge1": 18.7681,
|
1047 |
+
"eval_rouge2": 6.3762,
|
1048 |
+
"eval_rougeL": 18.6081,
|
1049 |
+
"eval_rougeLsum": 18.6173,
|
1050 |
+
"eval_runtime": 872.623,
|
1051 |
+
"eval_samples_per_second": 5.521,
|
1052 |
+
"eval_steps_per_second": 2.761,
|
1053 |
+
"step": 55000
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 2.91,
|
1057 |
+
"learning_rate": 3.1259190063487117e-06,
|
1058 |
+
"loss": 2.8754,
|
1059 |
+
"step": 56000
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 2.91,
|
1063 |
+
"eval_gen_len": 22.3497,
|
1064 |
+
"eval_loss": 2.638812780380249,
|
1065 |
+
"eval_rouge1": 19.0828,
|
1066 |
+
"eval_rouge2": 6.5203,
|
1067 |
+
"eval_rougeL": 18.9334,
|
1068 |
+
"eval_rougeLsum": 18.9285,
|
1069 |
+
"eval_runtime": 879.763,
|
1070 |
+
"eval_samples_per_second": 5.476,
|
1071 |
+
"eval_steps_per_second": 2.738,
|
1072 |
+
"step": 56000
|
1073 |
+
},
|
1074 |
+
{
|
1075 |
+
"epoch": 2.96,
|
1076 |
+
"learning_rate": 1.3960247028906535e-06,
|
1077 |
+
"loss": 2.8489,
|
1078 |
+
"step": 57000
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 2.96,
|
1082 |
+
"eval_gen_len": 21.9321,
|
1083 |
+
"eval_loss": 2.637495756149292,
|
1084 |
+
"eval_rouge1": 18.9219,
|
1085 |
+
"eval_rouge2": 6.4922,
|
1086 |
+
"eval_rougeL": 18.763,
|
1087 |
+
"eval_rougeLsum": 18.7437,
|
1088 |
+
"eval_runtime": 865.2523,
|
1089 |
+
"eval_samples_per_second": 5.568,
|
1090 |
+
"eval_steps_per_second": 2.784,
|
1091 |
+
"step": 57000
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 3.0,
|
1095 |
+
"step": 57807,
|
1096 |
+
"total_flos": 8.129568206380646e+16,
|
1097 |
+
"train_loss": 3.210809704903007,
|
1098 |
+
"train_runtime": 55943.4873,
|
1099 |
+
"train_samples_per_second": 2.067,
|
1100 |
+
"train_steps_per_second": 1.033
|
1101 |
+
}
|
1102 |
+
],
|
1103 |
+
"max_steps": 57807,
|
1104 |
+
"num_train_epochs": 3,
|
1105 |
+
"total_flos": 8.129568206380646e+16,
|
1106 |
+
"trial_name": null,
|
1107 |
+
"trial_params": null
|
1108 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa4a51ab894986324056067d4cff910564c0db59adfa272698be297ac1831722
|
3 |
+
size 3183
|