commit files to HF hub
Browse files- README.md +59 -0
- checkpoint-44157/config.json +58 -0
- checkpoint-44157/optimizer.pt +3 -0
- checkpoint-44157/pytorch_model.bin +3 -0
- checkpoint-44157/rng_state.pth +3 -0
- checkpoint-44157/scaler.pt +3 -0
- checkpoint-44157/scheduler.pt +3 -0
- checkpoint-44157/special_tokens_map.json +1 -0
- checkpoint-44157/spiece.model +3 -0
- checkpoint-44157/tokenizer.json +0 -0
- checkpoint-44157/tokenizer_config.json +1 -0
- checkpoint-44157/trainer_state.json +568 -0
- checkpoint-44157/training_args.bin +3 -0
- config.json +58 -0
- pytorch_model.bin +3 -0
- runs/Jun16_12-09-25_c34ff7159c16/1655381368.0660024/events.out.tfevents.1655381368.c34ff7159c16.10568.3 +3 -0
- runs/Jun16_12-09-25_c34ff7159c16/events.out.tfevents.1655381368.c34ff7159c16.10568.2 +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: T5-summarizer-simple-wiki-v2
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# T5-summarizer-simple-wiki-v2
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.0866
|
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: 2e-05
|
37 |
+
- train_batch_size: 16
|
38 |
+
- eval_batch_size: 16
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 3
|
43 |
+
- mixed_precision_training: Native AMP
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
+
| 2.2575 | 1.0 | 14719 | 2.1173 |
|
50 |
+
| 2.2663 | 2.0 | 29438 | 2.0926 |
|
51 |
+
| 2.2092 | 3.0 | 44157 | 2.0866 |
|
52 |
+
|
53 |
+
|
54 |
+
### Framework versions
|
55 |
+
|
56 |
+
- Transformers 4.19.4
|
57 |
+
- Pytorch 1.11.0
|
58 |
+
- Datasets 2.3.2
|
59 |
+
- Tokenizers 0.12.1
|
checkpoint-44157/config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-small",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
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": "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": 6,
|
19 |
+
"num_heads": 8,
|
20 |
+
"num_layers": 6,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_max_distance": 128,
|
24 |
+
"relative_attention_num_buckets": 32,
|
25 |
+
"task_specific_params": {
|
26 |
+
"summarization": {
|
27 |
+
"early_stopping": true,
|
28 |
+
"length_penalty": 2.0,
|
29 |
+
"max_length": 200,
|
30 |
+
"min_length": 30,
|
31 |
+
"no_repeat_ngram_size": 3,
|
32 |
+
"num_beams": 4,
|
33 |
+
"prefix": "summarize: "
|
34 |
+
},
|
35 |
+
"translation_en_to_de": {
|
36 |
+
"early_stopping": true,
|
37 |
+
"max_length": 300,
|
38 |
+
"num_beams": 4,
|
39 |
+
"prefix": "translate English to German: "
|
40 |
+
},
|
41 |
+
"translation_en_to_fr": {
|
42 |
+
"early_stopping": true,
|
43 |
+
"max_length": 300,
|
44 |
+
"num_beams": 4,
|
45 |
+
"prefix": "translate English to French: "
|
46 |
+
},
|
47 |
+
"translation_en_to_ro": {
|
48 |
+
"early_stopping": true,
|
49 |
+
"max_length": 300,
|
50 |
+
"num_beams": 4,
|
51 |
+
"prefix": "translate English to Romanian: "
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.19.4",
|
56 |
+
"use_cache": true,
|
57 |
+
"vocab_size": 32128
|
58 |
+
}
|
checkpoint-44157/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68236975bc40f15fb38db62b9605c70f244dd8379418c3a60b1abcb42334a498
|
3 |
+
size 484129461
|
checkpoint-44157/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4bef3500b6c1bc07cbe61e7ee9dcfcbfb8fafa58569407cf92d710ecd195f76
|
3 |
+
size 242070267
|
checkpoint-44157/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f962e4fa63ae56391ee77c540393187112e19b3eeba9c290efc0eccadaaa76a4
|
3 |
+
size 14503
|
checkpoint-44157/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82f5ed4bbb2b39f09f1524e3a2a42c673003ef4cc95a9994334fd5cfdc5bee26
|
3 |
+
size 559
|
checkpoint-44157/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24f2c79808aaac618cc62090db498fee204b96e3b2affe929402215c3c0a504b
|
3 |
+
size 623
|
checkpoint-44157/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-44157/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-44157/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-44157/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": null, "name_or_path": "t5-small", "tokenizer_class": "T5Tokenizer"}
|
checkpoint-44157/trainer_state.json
ADDED
@@ -0,0 +1,568 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 44157,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"learning_rate": 1.9774441198450984e-05,
|
13 |
+
"loss": 2.4542,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.07,
|
18 |
+
"learning_rate": 1.9547976538261206e-05,
|
19 |
+
"loss": 2.4106,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.1,
|
24 |
+
"learning_rate": 1.9321511878071427e-05,
|
25 |
+
"loss": 2.4207,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.14,
|
30 |
+
"learning_rate": 1.909595307652241e-05,
|
31 |
+
"loss": 2.3664,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.17,
|
36 |
+
"learning_rate": 1.8869488416332635e-05,
|
37 |
+
"loss": 2.3553,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.2,
|
42 |
+
"learning_rate": 1.8643023756142857e-05,
|
43 |
+
"loss": 2.3541,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24,
|
48 |
+
"learning_rate": 1.841655909595308e-05,
|
49 |
+
"loss": 2.3494,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.27,
|
54 |
+
"learning_rate": 1.81900944357633e-05,
|
55 |
+
"loss": 2.3592,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.31,
|
60 |
+
"learning_rate": 1.7963629775573522e-05,
|
61 |
+
"loss": 2.3452,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.34,
|
66 |
+
"learning_rate": 1.7737165115383744e-05,
|
67 |
+
"loss": 2.32,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.37,
|
72 |
+
"learning_rate": 1.7510700455193966e-05,
|
73 |
+
"loss": 2.2992,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.41,
|
78 |
+
"learning_rate": 1.728423579500419e-05,
|
79 |
+
"loss": 2.3109,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.44,
|
84 |
+
"learning_rate": 1.7057771134814413e-05,
|
85 |
+
"loss": 2.3008,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.48,
|
90 |
+
"learning_rate": 1.6831306474624635e-05,
|
91 |
+
"loss": 2.3091,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.51,
|
96 |
+
"learning_rate": 1.6604841814434857e-05,
|
97 |
+
"loss": 2.3252,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.54,
|
102 |
+
"learning_rate": 1.6378377154245082e-05,
|
103 |
+
"loss": 2.2909,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.58,
|
108 |
+
"learning_rate": 1.6151912494055304e-05,
|
109 |
+
"loss": 2.3015,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.61,
|
114 |
+
"learning_rate": 1.5925900763185907e-05,
|
115 |
+
"loss": 2.2997,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.65,
|
120 |
+
"learning_rate": 1.569943610299613e-05,
|
121 |
+
"loss": 2.283,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.68,
|
126 |
+
"learning_rate": 1.547297144280635e-05,
|
127 |
+
"loss": 2.2826,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.71,
|
132 |
+
"learning_rate": 1.5246506782616575e-05,
|
133 |
+
"loss": 2.2771,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.75,
|
138 |
+
"learning_rate": 1.5020042122426796e-05,
|
139 |
+
"loss": 2.2991,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.78,
|
144 |
+
"learning_rate": 1.4794030391557398e-05,
|
145 |
+
"loss": 2.3035,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.82,
|
150 |
+
"learning_rate": 1.456756573136762e-05,
|
151 |
+
"loss": 2.2715,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.85,
|
156 |
+
"learning_rate": 1.4341101071177844e-05,
|
157 |
+
"loss": 2.2736,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.88,
|
162 |
+
"learning_rate": 1.4114636410988067e-05,
|
163 |
+
"loss": 2.2883,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.92,
|
168 |
+
"learning_rate": 1.388862468011867e-05,
|
169 |
+
"loss": 2.2545,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.95,
|
174 |
+
"learning_rate": 1.3662160019928891e-05,
|
175 |
+
"loss": 2.2956,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.99,
|
180 |
+
"learning_rate": 1.3435695359739113e-05,
|
181 |
+
"loss": 2.2575,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.0,
|
186 |
+
"eval_loss": 2.1173367500305176,
|
187 |
+
"eval_runtime": 371.7904,
|
188 |
+
"eval_samples_per_second": 158.353,
|
189 |
+
"eval_steps_per_second": 9.898,
|
190 |
+
"step": 14719
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 1.02,
|
194 |
+
"learning_rate": 1.3209230699549337e-05,
|
195 |
+
"loss": 2.2485,
|
196 |
+
"step": 15000
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 1.05,
|
200 |
+
"learning_rate": 1.298276603935956e-05,
|
201 |
+
"loss": 2.2548,
|
202 |
+
"step": 15500
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.09,
|
206 |
+
"learning_rate": 1.2756301379169782e-05,
|
207 |
+
"loss": 2.242,
|
208 |
+
"step": 16000
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 1.12,
|
212 |
+
"learning_rate": 1.2529836718980004e-05,
|
213 |
+
"loss": 2.2797,
|
214 |
+
"step": 16500
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 1.15,
|
218 |
+
"learning_rate": 1.2303824988110606e-05,
|
219 |
+
"loss": 2.264,
|
220 |
+
"step": 17000
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 1.19,
|
224 |
+
"learning_rate": 1.207781325724121e-05,
|
225 |
+
"loss": 2.2747,
|
226 |
+
"step": 17500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.22,
|
230 |
+
"learning_rate": 1.1851348597051431e-05,
|
231 |
+
"loss": 2.2776,
|
232 |
+
"step": 18000
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 1.26,
|
236 |
+
"learning_rate": 1.1624883936861653e-05,
|
237 |
+
"loss": 2.2696,
|
238 |
+
"step": 18500
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 1.29,
|
242 |
+
"learning_rate": 1.1398419276671877e-05,
|
243 |
+
"loss": 2.2436,
|
244 |
+
"step": 19000
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.32,
|
248 |
+
"learning_rate": 1.1171954616482099e-05,
|
249 |
+
"loss": 2.2563,
|
250 |
+
"step": 19500
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 1.36,
|
254 |
+
"learning_rate": 1.094548995629232e-05,
|
255 |
+
"loss": 2.266,
|
256 |
+
"step": 20000
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 1.39,
|
260 |
+
"learning_rate": 1.0719478225422924e-05,
|
261 |
+
"loss": 2.2696,
|
262 |
+
"step": 20500
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 1.43,
|
266 |
+
"learning_rate": 1.0493013565233146e-05,
|
267 |
+
"loss": 2.2423,
|
268 |
+
"step": 21000
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.46,
|
272 |
+
"learning_rate": 1.026654890504337e-05,
|
273 |
+
"loss": 2.2411,
|
274 |
+
"step": 21500
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 1.49,
|
278 |
+
"learning_rate": 1.0040084244853591e-05,
|
279 |
+
"loss": 2.2564,
|
280 |
+
"step": 22000
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 1.53,
|
284 |
+
"learning_rate": 9.813619584663813e-06,
|
285 |
+
"loss": 2.2632,
|
286 |
+
"step": 22500
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.56,
|
290 |
+
"learning_rate": 9.587154924474037e-06,
|
291 |
+
"loss": 2.2656,
|
292 |
+
"step": 23000
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 1.6,
|
296 |
+
"learning_rate": 9.360690264284259e-06,
|
297 |
+
"loss": 2.2667,
|
298 |
+
"step": 23500
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 1.63,
|
302 |
+
"learning_rate": 9.134225604094482e-06,
|
303 |
+
"loss": 2.2622,
|
304 |
+
"step": 24000
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 1.66,
|
308 |
+
"learning_rate": 8.907760943904704e-06,
|
309 |
+
"loss": 2.2398,
|
310 |
+
"step": 24500
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.7,
|
314 |
+
"learning_rate": 8.681296283714928e-06,
|
315 |
+
"loss": 2.2477,
|
316 |
+
"step": 25000
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.73,
|
320 |
+
"learning_rate": 8.45528455284553e-06,
|
321 |
+
"loss": 2.2248,
|
322 |
+
"step": 25500
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 1.77,
|
326 |
+
"learning_rate": 8.228819892655751e-06,
|
327 |
+
"loss": 2.2286,
|
328 |
+
"step": 26000
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.8,
|
332 |
+
"learning_rate": 8.002355232465975e-06,
|
333 |
+
"loss": 2.2268,
|
334 |
+
"step": 26500
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 1.83,
|
338 |
+
"learning_rate": 7.775890572276197e-06,
|
339 |
+
"loss": 2.239,
|
340 |
+
"step": 27000
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 1.87,
|
344 |
+
"learning_rate": 7.5498788414067996e-06,
|
345 |
+
"loss": 2.2238,
|
346 |
+
"step": 27500
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.9,
|
350 |
+
"learning_rate": 7.323414181217021e-06,
|
351 |
+
"loss": 2.2225,
|
352 |
+
"step": 28000
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.94,
|
356 |
+
"learning_rate": 7.096949521027244e-06,
|
357 |
+
"loss": 2.2272,
|
358 |
+
"step": 28500
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 1.97,
|
362 |
+
"learning_rate": 6.870484860837466e-06,
|
363 |
+
"loss": 2.2663,
|
364 |
+
"step": 29000
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 2.0,
|
368 |
+
"eval_loss": 2.092595100402832,
|
369 |
+
"eval_runtime": 372.6322,
|
370 |
+
"eval_samples_per_second": 157.995,
|
371 |
+
"eval_steps_per_second": 9.876,
|
372 |
+
"step": 29438
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 2.0,
|
376 |
+
"learning_rate": 6.644473129968069e-06,
|
377 |
+
"loss": 2.2417,
|
378 |
+
"step": 29500
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 2.04,
|
382 |
+
"learning_rate": 6.4180084697782915e-06,
|
383 |
+
"loss": 2.2355,
|
384 |
+
"step": 30000
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 2.07,
|
388 |
+
"learning_rate": 6.191543809588514e-06,
|
389 |
+
"loss": 2.2285,
|
390 |
+
"step": 30500
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 2.11,
|
394 |
+
"learning_rate": 5.965079149398737e-06,
|
395 |
+
"loss": 2.2392,
|
396 |
+
"step": 31000
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 2.14,
|
400 |
+
"learning_rate": 5.738614489208959e-06,
|
401 |
+
"loss": 2.23,
|
402 |
+
"step": 31500
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.17,
|
406 |
+
"learning_rate": 5.512149829019182e-06,
|
407 |
+
"loss": 2.2399,
|
408 |
+
"step": 32000
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 2.21,
|
412 |
+
"learning_rate": 5.286138098149784e-06,
|
413 |
+
"loss": 2.2363,
|
414 |
+
"step": 32500
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 2.24,
|
418 |
+
"learning_rate": 5.059673437960007e-06,
|
419 |
+
"loss": 2.2392,
|
420 |
+
"step": 33000
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 2.28,
|
424 |
+
"learning_rate": 4.833208777770229e-06,
|
425 |
+
"loss": 2.2302,
|
426 |
+
"step": 33500
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 2.31,
|
430 |
+
"learning_rate": 4.6067441175804515e-06,
|
431 |
+
"loss": 2.2257,
|
432 |
+
"step": 34000
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 2.34,
|
436 |
+
"learning_rate": 4.380732386711054e-06,
|
437 |
+
"loss": 2.2527,
|
438 |
+
"step": 34500
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 2.38,
|
442 |
+
"learning_rate": 4.154267726521277e-06,
|
443 |
+
"loss": 2.2505,
|
444 |
+
"step": 35000
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 2.41,
|
448 |
+
"learning_rate": 3.927803066331499e-06,
|
449 |
+
"loss": 2.2063,
|
450 |
+
"step": 35500
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.45,
|
454 |
+
"learning_rate": 3.701338406141722e-06,
|
455 |
+
"loss": 2.2317,
|
456 |
+
"step": 36000
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 2.48,
|
460 |
+
"learning_rate": 3.4748737459519442e-06,
|
461 |
+
"loss": 2.2432,
|
462 |
+
"step": 36500
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 2.51,
|
466 |
+
"learning_rate": 3.248409085762167e-06,
|
467 |
+
"loss": 2.2414,
|
468 |
+
"step": 37000
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 2.55,
|
472 |
+
"learning_rate": 3.0219444255723896e-06,
|
473 |
+
"loss": 2.2523,
|
474 |
+
"step": 37500
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 2.58,
|
478 |
+
"learning_rate": 2.795479765382612e-06,
|
479 |
+
"loss": 2.2264,
|
480 |
+
"step": 38000
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 2.62,
|
484 |
+
"learning_rate": 2.5690151051928346e-06,
|
485 |
+
"loss": 2.229,
|
486 |
+
"step": 38500
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 2.65,
|
490 |
+
"learning_rate": 2.343003374323437e-06,
|
491 |
+
"loss": 2.2231,
|
492 |
+
"step": 39000
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.68,
|
496 |
+
"learning_rate": 2.1165387141336597e-06,
|
497 |
+
"loss": 2.2375,
|
498 |
+
"step": 39500
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 2.72,
|
502 |
+
"learning_rate": 1.8900740539438822e-06,
|
503 |
+
"loss": 2.235,
|
504 |
+
"step": 40000
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 2.75,
|
508 |
+
"learning_rate": 1.6636093937541049e-06,
|
509 |
+
"loss": 2.2294,
|
510 |
+
"step": 40500
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 2.79,
|
514 |
+
"learning_rate": 1.4371447335643274e-06,
|
515 |
+
"loss": 2.2244,
|
516 |
+
"step": 41000
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 2.82,
|
520 |
+
"learning_rate": 1.2106800733745499e-06,
|
521 |
+
"loss": 2.2468,
|
522 |
+
"step": 41500
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 2.85,
|
526 |
+
"learning_rate": 9.842154131847726e-07,
|
527 |
+
"loss": 2.2278,
|
528 |
+
"step": 42000
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 2.89,
|
532 |
+
"learning_rate": 7.577507529949953e-07,
|
533 |
+
"loss": 2.222,
|
534 |
+
"step": 42500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 2.92,
|
538 |
+
"learning_rate": 5.317390221255973e-07,
|
539 |
+
"loss": 2.2208,
|
540 |
+
"step": 43000
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 2.96,
|
544 |
+
"learning_rate": 3.057272912561995e-07,
|
545 |
+
"loss": 2.211,
|
546 |
+
"step": 43500
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 2.99,
|
550 |
+
"learning_rate": 7.926263106642208e-08,
|
551 |
+
"loss": 2.2092,
|
552 |
+
"step": 44000
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 3.0,
|
556 |
+
"eval_loss": 2.086573362350464,
|
557 |
+
"eval_runtime": 371.7326,
|
558 |
+
"eval_samples_per_second": 158.377,
|
559 |
+
"eval_steps_per_second": 9.9,
|
560 |
+
"step": 44157
|
561 |
+
}
|
562 |
+
],
|
563 |
+
"max_steps": 44157,
|
564 |
+
"num_train_epochs": 3,
|
565 |
+
"total_flos": 6.916093810478285e+16,
|
566 |
+
"trial_name": null,
|
567 |
+
"trial_params": null
|
568 |
+
}
|
checkpoint-44157/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:877743c33e306d19c3f70b013b001c6a7976c99a695b0ebd0072e22d2b6381b9
|
3 |
+
size 3375
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-small",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
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": "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": 6,
|
19 |
+
"num_heads": 8,
|
20 |
+
"num_layers": 6,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_max_distance": 128,
|
24 |
+
"relative_attention_num_buckets": 32,
|
25 |
+
"task_specific_params": {
|
26 |
+
"summarization": {
|
27 |
+
"early_stopping": true,
|
28 |
+
"length_penalty": 2.0,
|
29 |
+
"max_length": 200,
|
30 |
+
"min_length": 30,
|
31 |
+
"no_repeat_ngram_size": 3,
|
32 |
+
"num_beams": 4,
|
33 |
+
"prefix": "summarize: "
|
34 |
+
},
|
35 |
+
"translation_en_to_de": {
|
36 |
+
"early_stopping": true,
|
37 |
+
"max_length": 300,
|
38 |
+
"num_beams": 4,
|
39 |
+
"prefix": "translate English to German: "
|
40 |
+
},
|
41 |
+
"translation_en_to_fr": {
|
42 |
+
"early_stopping": true,
|
43 |
+
"max_length": 300,
|
44 |
+
"num_beams": 4,
|
45 |
+
"prefix": "translate English to French: "
|
46 |
+
},
|
47 |
+
"translation_en_to_ro": {
|
48 |
+
"early_stopping": true,
|
49 |
+
"max_length": 300,
|
50 |
+
"num_beams": 4,
|
51 |
+
"prefix": "translate English to Romanian: "
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.19.4",
|
56 |
+
"use_cache": true,
|
57 |
+
"vocab_size": 32128
|
58 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4bef3500b6c1bc07cbe61e7ee9dcfcbfb8fafa58569407cf92d710ecd195f76
|
3 |
+
size 242070267
|
runs/Jun16_12-09-25_c34ff7159c16/1655381368.0660024/events.out.tfevents.1655381368.c34ff7159c16.10568.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd5234b3e1b7e2b32ccbb05750bb8d4e5635f5e8f49f2287c8145878762fc374
|
3 |
+
size 5436
|
runs/Jun16_12-09-25_c34ff7159c16/events.out.tfevents.1655381368.c34ff7159c16.10568.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:877b8a87239da6f195646575c105fe30adf8bcb99cecffd96cf2529a699e079a
|
3 |
+
size 19591
|
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
|
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": null, "name_or_path": "t5-small", "tokenizer_class": "T5Tokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acb29a171fcab1e64030730ed74400cc1cf48894314cd0d84d7d74fc63231930
|
3 |
+
size 3375
|