Initial commit
Browse files- README.md +55 -0
- added_tokens.json +1 -0
- all_results.json +15 -0
- checkpoint-500/added_tokens.json +1 -0
- checkpoint-500/config.json +62 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/special_tokens_map.json +1 -0
- checkpoint-500/spiece.model +3 -0
- checkpoint-500/tokenizer.json +0 -0
- checkpoint-500/tokenizer_config.json +1 -0
- checkpoint-500/trainer_state.json +46 -0
- checkpoint-500/training_args.bin +3 -0
- config.json +62 -0
- generated_predictions.txt +0 -0
- labels.txt +0 -0
- predictions.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jan19_12-53-00_7cf8fe6c7293/1642596802.460296/events.out.tfevents.1642596802.7cf8fe6c7293.668.1 +3 -0
- runs/Jan19_12-53-00_7cf8fe6c7293/events.out.tfevents.1642596802.7cf8fe6c7293.668.0 +3 -0
- runs/Jan19_12-54-25_7cf8fe6c7293/1642596880.8129342/events.out.tfevents.1642596880.7cf8fe6c7293.718.1 +3 -0
- runs/Jan19_12-54-25_7cf8fe6c7293/events.out.tfevents.1642596880.7cf8fe6c7293.718.0 +3 -0
- runs/Jan19_12-55-27_7cf8fe6c7293/1642596942.3387752/events.out.tfevents.1642596942.7cf8fe6c7293.750.1 +3 -0
- runs/Jan19_12-55-27_7cf8fe6c7293/events.out.tfevents.1642596942.7cf8fe6c7293.750.0 +3 -0
- runs/Jan19_13-17-49_7cf8fe6c7293/1642598288.1092122/events.out.tfevents.1642598288.7cf8fe6c7293.913.1 +3 -0
- runs/Jan19_13-17-49_7cf8fe6c7293/events.out.tfevents.1642598288.7cf8fe6c7293.913.0 +3 -0
- runs/Jan19_14-10-20_7cf8fe6c7293/1642601438.4479742/events.out.tfevents.1642601438.7cf8fe6c7293.1429.1 +3 -0
- runs/Jan19_14-10-20_7cf8fe6c7293/events.out.tfevents.1642601438.7cf8fe6c7293.1429.0 +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- test_results.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +67 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- data
|
7 |
+
model-index:
|
8 |
+
- name: german-qg-t5-e2e-quad
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# german-qg-t5-e2e-quad
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [valhalla/t5-base-e2e-qg](https://huggingface.co/valhalla/t5-base-e2e-qg) on the data dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0001
|
37 |
+
- train_batch_size: 4
|
38 |
+
- eval_batch_size: 4
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 8
|
41 |
+
- total_train_batch_size: 32
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 10.0
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.16.0.dev0
|
53 |
+
- Pytorch 1.10.0+cu111
|
54 |
+
- Datasets 1.16.1
|
55 |
+
- Tokenizers 0.10.3
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<sep>": 32100, "<hl>": 32101}
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"predict_bleu": 15.0146,
|
4 |
+
"predict_gen_len": 123.8797,
|
5 |
+
"predict_loss": 1.5464541912078857,
|
6 |
+
"predict_runtime": 1193.4414,
|
7 |
+
"predict_samples": 474,
|
8 |
+
"predict_samples_per_second": 0.397,
|
9 |
+
"predict_steps_per_second": 0.1,
|
10 |
+
"train_loss": 1.4465530395507813,
|
11 |
+
"train_runtime": 7665.0914,
|
12 |
+
"train_samples": 2540,
|
13 |
+
"train_samples_per_second": 3.314,
|
14 |
+
"train_steps_per_second": 0.103
|
15 |
+
}
|
checkpoint-500/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<sep>": 32100, "<hl>": 32101}
|
checkpoint-500/config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "valhalla/t5-base-e2e-qg",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 3072,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"n_positions": 512,
|
18 |
+
"num_decoder_layers": 12,
|
19 |
+
"num_heads": 12,
|
20 |
+
"num_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"task_specific_params": {
|
25 |
+
"summarization": {
|
26 |
+
"early_stopping": true,
|
27 |
+
"length_penalty": 1.5,
|
28 |
+
"max_length": 256,
|
29 |
+
"no_repeat_ngram_size": 3,
|
30 |
+
"num_beams": 4,
|
31 |
+
"prefix": "generate questions: "
|
32 |
+
},
|
33 |
+
"translation_en_to_de": {
|
34 |
+
"early_stopping": true,
|
35 |
+
"length_penalty": 1.5,
|
36 |
+
"max_length": 256,
|
37 |
+
"no_repeat_ngram_size": 3,
|
38 |
+
"num_beams": 4,
|
39 |
+
"prefix": "generate questions: "
|
40 |
+
},
|
41 |
+
"translation_en_to_fr": {
|
42 |
+
"early_stopping": true,
|
43 |
+
"length_penalty": 1.5,
|
44 |
+
"max_length": 256,
|
45 |
+
"no_repeat_ngram_size": 3,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "generate questions: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"length_penalty": 1.5,
|
52 |
+
"max_length": 256,
|
53 |
+
"no_repeat_ngram_size": 3,
|
54 |
+
"num_beams": 4,
|
55 |
+
"prefix": "generate questions: "
|
56 |
+
}
|
57 |
+
},
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.16.0.dev0",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 32102
|
62 |
+
}
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:948525b0aa8dc1fc5763e169cd1aca753b177263baa1b7f5be4e5c3f0bfb1d8e
|
3 |
+
size 1783219389
|
checkpoint-500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71039639b1987ded849bbb4aaa9eb183f9af155539af60cf216148569570cb3e
|
3 |
+
size 891651007
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bba26607dfe634191d975f09a73dfacf9effdfcc778854798f84b699099bed9d
|
3 |
+
size 14503
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26eab845218018d9515ebdee68340a063bea33586c5b2d308186c022fcd2f104
|
3 |
+
size 623
|
checkpoint-500/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
checkpoint-500/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-500/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": "models/t5-base-e2e-qg/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "valhalla/t5-base-e2e-qg", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.32755905511811,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.26,
|
12 |
+
"learning_rate": 8.734177215189874e-05,
|
13 |
+
"loss": 1.9271,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.53,
|
18 |
+
"learning_rate": 7.468354430379747e-05,
|
19 |
+
"loss": 1.5723,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 3.79,
|
24 |
+
"learning_rate": 6.20253164556962e-05,
|
25 |
+
"loss": 1.4655,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 5.06,
|
30 |
+
"learning_rate": 4.936708860759494e-05,
|
31 |
+
"loss": 1.4053,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 6.33,
|
36 |
+
"learning_rate": 3.670886075949367e-05,
|
37 |
+
"loss": 1.3442,
|
38 |
+
"step": 500
|
39 |
+
}
|
40 |
+
],
|
41 |
+
"max_steps": 790,
|
42 |
+
"num_train_epochs": 10,
|
43 |
+
"total_flos": 8796387214172160.0,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": null
|
46 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7d1c7ee3fc7ca3fc54caa0619765badf40de2954147f4239ab1ad292322a6a7
|
3 |
+
size 3119
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "valhalla/t5-base-e2e-qg",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 3072,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"n_positions": 512,
|
18 |
+
"num_decoder_layers": 12,
|
19 |
+
"num_heads": 12,
|
20 |
+
"num_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"task_specific_params": {
|
25 |
+
"summarization": {
|
26 |
+
"early_stopping": true,
|
27 |
+
"length_penalty": 1.5,
|
28 |
+
"max_length": 256,
|
29 |
+
"no_repeat_ngram_size": 3,
|
30 |
+
"num_beams": 4,
|
31 |
+
"prefix": "generate questions: "
|
32 |
+
},
|
33 |
+
"translation_en_to_de": {
|
34 |
+
"early_stopping": true,
|
35 |
+
"length_penalty": 1.5,
|
36 |
+
"max_length": 256,
|
37 |
+
"no_repeat_ngram_size": 3,
|
38 |
+
"num_beams": 4,
|
39 |
+
"prefix": "generate questions: "
|
40 |
+
},
|
41 |
+
"translation_en_to_fr": {
|
42 |
+
"early_stopping": true,
|
43 |
+
"length_penalty": 1.5,
|
44 |
+
"max_length": 256,
|
45 |
+
"no_repeat_ngram_size": 3,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "generate questions: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"length_penalty": 1.5,
|
52 |
+
"max_length": 256,
|
53 |
+
"no_repeat_ngram_size": 3,
|
54 |
+
"num_beams": 4,
|
55 |
+
"prefix": "generate questions: "
|
56 |
+
}
|
57 |
+
},
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.16.0.dev0",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 32102
|
62 |
+
}
|
generated_predictions.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
labels.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
predictions.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d1f16bf160477b1ace9d387905ae3df6b6af1bda43e0671b371638099829dc8
|
3 |
+
size 891651007
|
runs/Jan19_12-53-00_7cf8fe6c7293/1642596802.460296/events.out.tfevents.1642596802.7cf8fe6c7293.668.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e001bada56838c177417a5614ee99d5df375c1d8e3a7501490ed991c252ef6d2
|
3 |
+
size 5001
|
runs/Jan19_12-53-00_7cf8fe6c7293/events.out.tfevents.1642596802.7cf8fe6c7293.668.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73dd19024d01a4843c7c7e94fa8554b247d1193c6f236bd08f3fb9a9049ba424
|
3 |
+
size 4312
|
runs/Jan19_12-54-25_7cf8fe6c7293/1642596880.8129342/events.out.tfevents.1642596880.7cf8fe6c7293.718.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16dfbc09c61c77ad339d08546a966ea5470a57af135909dac4afe7e2d27e9329
|
3 |
+
size 5001
|
runs/Jan19_12-54-25_7cf8fe6c7293/events.out.tfevents.1642596880.7cf8fe6c7293.718.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e374266569198366455a077948d407161898b09f240ff45c21f9ce028ccd290
|
3 |
+
size 4309
|
runs/Jan19_12-55-27_7cf8fe6c7293/1642596942.3387752/events.out.tfevents.1642596942.7cf8fe6c7293.750.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cc56e439959733451c2e457260f1dc6a8784d76a1488a06ca6eb59584d6035c
|
3 |
+
size 5001
|
runs/Jan19_12-55-27_7cf8fe6c7293/events.out.tfevents.1642596942.7cf8fe6c7293.750.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae84792071dd515410e7b940933836a749d415a6c35f0f62bde6b995b91f908b
|
3 |
+
size 4657
|
runs/Jan19_13-17-49_7cf8fe6c7293/1642598288.1092122/events.out.tfevents.1642598288.7cf8fe6c7293.913.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db7a976a18082bb064aba3cda058fceab9fab780628d66363f9a85b6e8f2a852
|
3 |
+
size 5001
|
runs/Jan19_13-17-49_7cf8fe6c7293/events.out.tfevents.1642598288.7cf8fe6c7293.913.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ace15da7a997f88138522a29bf0fb4e0f45faef7f0ee9badf3fc784eebf155bc
|
3 |
+
size 4657
|
runs/Jan19_14-10-20_7cf8fe6c7293/1642601438.4479742/events.out.tfevents.1642601438.7cf8fe6c7293.1429.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0781904291da3e1b02fd31fce0c32a8bbfebad0af0df50ff2a07a10fa9be71f4
|
3 |
+
size 5001
|
runs/Jan19_14-10-20_7cf8fe6c7293/events.out.tfevents.1642601438.7cf8fe6c7293.1429.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa37bac9d1a3b865d86dbc09415f03a8d4f8bfcefd9a8dff7bf6f1edab523f38
|
3 |
+
size 5760
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
test_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"predict_bleu": 15.0146,
|
3 |
+
"predict_gen_len": 123.8797,
|
4 |
+
"predict_loss": 1.5464541912078857,
|
5 |
+
"predict_runtime": 1193.4414,
|
6 |
+
"predict_samples": 474,
|
7 |
+
"predict_samples_per_second": 0.397,
|
8 |
+
"predict_steps_per_second": 0.1
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": "models/t5-base-e2e-qg/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "valhalla/t5-base-e2e-qg", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 1.4465530395507813,
|
4 |
+
"train_runtime": 7665.0914,
|
5 |
+
"train_samples": 2540,
|
6 |
+
"train_samples_per_second": 3.314,
|
7 |
+
"train_steps_per_second": 0.103
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.99527559055118,
|
5 |
+
"global_step": 790,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.26,
|
12 |
+
"learning_rate": 8.734177215189874e-05,
|
13 |
+
"loss": 1.9271,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.53,
|
18 |
+
"learning_rate": 7.468354430379747e-05,
|
19 |
+
"loss": 1.5723,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 3.79,
|
24 |
+
"learning_rate": 6.20253164556962e-05,
|
25 |
+
"loss": 1.4655,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 5.06,
|
30 |
+
"learning_rate": 4.936708860759494e-05,
|
31 |
+
"loss": 1.4053,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 6.33,
|
36 |
+
"learning_rate": 3.670886075949367e-05,
|
37 |
+
"loss": 1.3442,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 7.59,
|
42 |
+
"learning_rate": 2.4050632911392405e-05,
|
43 |
+
"loss": 1.2954,
|
44 |
+
"step": 600
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 8.86,
|
48 |
+
"learning_rate": 1.139240506329114e-05,
|
49 |
+
"loss": 1.28,
|
50 |
+
"step": 700
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 10.0,
|
54 |
+
"step": 790,
|
55 |
+
"total_flos": 1.388887369371648e+16,
|
56 |
+
"train_loss": 1.4465530395507813,
|
57 |
+
"train_runtime": 7665.0914,
|
58 |
+
"train_samples_per_second": 3.314,
|
59 |
+
"train_steps_per_second": 0.103
|
60 |
+
}
|
61 |
+
],
|
62 |
+
"max_steps": 790,
|
63 |
+
"num_train_epochs": 10,
|
64 |
+
"total_flos": 1.388887369371648e+16,
|
65 |
+
"trial_name": null,
|
66 |
+
"trial_params": null
|
67 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7d1c7ee3fc7ca3fc54caa0619765badf40de2954147f4239ab1ad292322a6a7
|
3 |
+
size 3119
|