initial commit
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +17 -0
- README.md +79 -0
- checkpoint-3000/config.json +60 -0
- checkpoint-3000/generation_config.json +6 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/pytorch_model.bin +3 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/special_tokens_map.json +107 -0
- checkpoint-3000/spiece.model +3 -0
- checkpoint-3000/tokenizer.json +0 -0
- checkpoint-3000/tokenizer_config.json +111 -0
- checkpoint-3000/trainer_state.json +148 -0
- checkpoint-3000/training_args.bin +3 -0
- checkpoint-4500/config.json +60 -0
- checkpoint-4500/generation_config.json +6 -0
- checkpoint-4500/optimizer.pt +3 -0
- checkpoint-4500/pytorch_model.bin +3 -0
- checkpoint-4500/rng_state.pth +3 -0
- checkpoint-4500/scheduler.pt +3 -0
- checkpoint-4500/special_tokens_map.json +107 -0
- checkpoint-4500/spiece.model +3 -0
- checkpoint-4500/tokenizer.json +0 -0
- checkpoint-4500/tokenizer_config.json +111 -0
- checkpoint-4500/trainer_state.json +214 -0
- checkpoint-4500/training_args.bin +3 -0
- checkpoint-4875/config.json +60 -0
- checkpoint-4875/generation_config.json +6 -0
- checkpoint-4875/optimizer.pt +3 -0
- checkpoint-4875/pytorch_model.bin +3 -0
- checkpoint-4875/rng_state.pth +3 -0
- checkpoint-4875/scheduler.pt +3 -0
- checkpoint-4875/special_tokens_map.json +107 -0
- checkpoint-4875/spiece.model +3 -0
- checkpoint-4875/tokenizer.json +0 -0
- checkpoint-4875/tokenizer_config.json +111 -0
- checkpoint-4875/trainer_state.json +226 -0
- checkpoint-4875/training_args.bin +3 -0
- checkpoint-5250/config.json +60 -0
- checkpoint-5250/generation_config.json +6 -0
- checkpoint-5250/optimizer.pt +3 -0
- checkpoint-5250/pytorch_model.bin +3 -0
- checkpoint-5250/rng_state.pth +3 -0
- checkpoint-5250/scheduler.pt +3 -0
- checkpoint-5250/special_tokens_map.json +107 -0
- checkpoint-5250/spiece.model +3 -0
- checkpoint-5250/tokenizer.json +0 -0
- checkpoint-5250/tokenizer_config.json +111 -0
- checkpoint-5250/trainer_state.json +244 -0
- checkpoint-5250/training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,20 @@ 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 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
36 |
+
checkpoint-4500/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
37 |
+
checkpoint-4500/training_args.bin filter=lfs diff=lfs merge=lfs -text
|
38 |
+
checkpoint-4875/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
39 |
+
checkpoint-5625/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
40 |
+
checkpoint-3000/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
41 |
+
checkpoint-4875/training_args.bin filter=lfs diff=lfs merge=lfs -text
|
42 |
+
checkpoint-5250/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
43 |
+
checkpoint-5250/training_args.bin filter=lfs diff=lfs merge=lfs -text
|
44 |
+
checkpoint-5625/training_args.bin filter=lfs diff=lfs merge=lfs -text
|
45 |
+
checkpoint-3000/training_args.bin filter=lfs diff=lfs merge=lfs -text
|
46 |
+
spiece.model filter=lfs diff=lfs merge=lfs -text
|
47 |
+
checkpoint-5625/spiece.model filter=lfs diff=lfs merge=lfs -text
|
48 |
+
checkpoint-3000/spiece.model filter=lfs diff=lfs merge=lfs -text
|
49 |
+
checkpoint-4500/spiece.model filter=lfs diff=lfs merge=lfs -text
|
50 |
+
checkpoint-4875/spiece.model filter=lfs diff=lfs merge=lfs -text
|
51 |
+
checkpoint-5250/spiece.model filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- bleu
|
7 |
+
- rouge
|
8 |
+
model-index:
|
9 |
+
- name: t5-small-codesearchnet-multilang-python-java-javascript-go
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# t5-small-codesearchnet-multilang-python-java-javascript-go
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4172
|
21 |
+
- Bleu: 0.0344
|
22 |
+
- Rouge1: 0.3447
|
23 |
+
- Rouge2: 0.2223
|
24 |
+
- Avg Length: 17.0756
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5e-05
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- gradient_accumulation_steps: 10
|
48 |
+
- total_train_batch_size: 80
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 15
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | Avg Length |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:----------:|
|
57 |
+
| No log | 1.0 | 375 | 0.4953 | 0.0246 | 0.2585 | 0.1659 | 17.688 |
|
58 |
+
| 2.1147 | 2.0 | 750 | 0.4376 | 0.0263 | 0.293 | 0.1912 | 17.044 |
|
59 |
+
| 0.4761 | 3.0 | 1125 | 0.4125 | 0.0317 | 0.2964 | 0.1965 | 17.4636 |
|
60 |
+
| 0.4163 | 4.0 | 1500 | 0.3980 | 0.0277 | 0.3095 | 0.2015 | 16.3844 |
|
61 |
+
| 0.4163 | 5.0 | 1875 | 0.3868 | 0.0293 | 0.325 | 0.2082 | 16.6804 |
|
62 |
+
| 0.3808 | 6.0 | 2250 | 0.3815 | 0.0288 | 0.3232 | 0.2089 | 16.7996 |
|
63 |
+
| 0.352 | 7.0 | 2625 | 0.3720 | 0.024 | 0.3225 | 0.2119 | 15.8864 |
|
64 |
+
| 0.3295 | 8.0 | 3000 | 0.3695 | 0.0198 | 0.3142 | 0.2118 | 15.4172 |
|
65 |
+
| 0.3295 | 9.0 | 3375 | 0.3736 | 0.0305 | 0.343 | 0.2206 | 16.8566 |
|
66 |
+
| 0.3052 | 10.0 | 3750 | 0.3811 | 0.0316 | 0.3442 | 0.2215 | 16.8834 |
|
67 |
+
| 0.2887 | 11.0 | 4125 | 0.3775 | 0.023 | 0.3262 | 0.2149 | 15.6226 |
|
68 |
+
| 0.2799 | 12.0 | 4500 | 0.3793 | 0.034 | 0.3397 | 0.2186 | 16.6344 |
|
69 |
+
| 0.2799 | 13.0 | 4875 | 0.3875 | 0.0312 | 0.3389 | 0.2192 | 16.7964 |
|
70 |
+
| 0.2517 | 14.0 | 5250 | 0.3833 | 0.0337 | 0.3387 | 0.22 | 16.9076 |
|
71 |
+
| 0.2409 | 15.0 | 5625 | 0.4172 | 0.0344 | 0.3447 | 0.2223 | 17.0756 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.28.1
|
77 |
+
- Pytorch 2.0.0+cu118
|
78 |
+
- Datasets 2.12.0
|
79 |
+
- Tokenizers 0.13.3
|
checkpoint-3000/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"dense_act_fn": "relu",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "relu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": false,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
20 |
+
"num_decoder_layers": 6,
|
21 |
+
"num_heads": 8,
|
22 |
+
"num_layers": 6,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.28.1",
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 32128
|
60 |
+
}
|
checkpoint-3000/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.28.1"
|
6 |
+
}
|
checkpoint-3000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e68c15ed5879013f6299d8d1dc256c9a91f1784641311ad8971d8e47ff1371fb
|
3 |
+
size 839173
|
checkpoint-3000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fdee6e8f46d848b7e5d63bccf48ea3fee457d017acaa6f96f6f58b70f5db7cf
|
3 |
+
size 242071641
|
checkpoint-3000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff91c4cc6513b96a8a4ed0b84b5b347f900f779aa2f7554f3b5abb46233035e7
|
3 |
+
size 14575
|
checkpoint-3000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a23b5a6ee89fbe06d171d4d7c47a0dde3c9ac3cc93be5afbe9688d6b493939bc
|
3 |
+
size 881
|
checkpoint-3000/special_tokens_map.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
107 |
+
}
|
checkpoint-3000/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-3000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3000/tokenizer_config.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"clean_up_tokenization_spaces": true,
|
105 |
+
"eos_token": "</s>",
|
106 |
+
"extra_ids": 100,
|
107 |
+
"model_max_length": 512,
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"tokenizer_class": "T5Tokenizer",
|
110 |
+
"unk_token": "<unk>"
|
111 |
+
}
|
checkpoint-3000/trainer_state.json
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.36947065591812134,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python-java-javascript-go/checkpoint-3000",
|
4 |
+
"epoch": 8.0,
|
5 |
+
"global_step": 3000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_avg_length": 17.688,
|
13 |
+
"eval_bleu": 0.0246,
|
14 |
+
"eval_loss": 0.49533936381340027,
|
15 |
+
"eval_rouge1": 0.2585,
|
16 |
+
"eval_rouge2": 0.1659,
|
17 |
+
"eval_runtime": 150.4831,
|
18 |
+
"eval_samples_per_second": 33.226,
|
19 |
+
"eval_steps_per_second": 4.153,
|
20 |
+
"step": 375
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.33,
|
24 |
+
"learning_rate": 0.011610765941441059,
|
25 |
+
"loss": 2.1147,
|
26 |
+
"step": 500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"eval_avg_length": 17.044,
|
31 |
+
"eval_bleu": 0.0263,
|
32 |
+
"eval_loss": 0.4376164674758911,
|
33 |
+
"eval_rouge1": 0.293,
|
34 |
+
"eval_rouge2": 0.1912,
|
35 |
+
"eval_runtime": 147.0412,
|
36 |
+
"eval_samples_per_second": 34.004,
|
37 |
+
"eval_steps_per_second": 4.251,
|
38 |
+
"step": 750
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 2.67,
|
42 |
+
"learning_rate": 0.02326086163520813,
|
43 |
+
"loss": 0.4761,
|
44 |
+
"step": 1000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_avg_length": 17.4636,
|
49 |
+
"eval_bleu": 0.0317,
|
50 |
+
"eval_loss": 0.4124959111213684,
|
51 |
+
"eval_rouge1": 0.2964,
|
52 |
+
"eval_rouge2": 0.1965,
|
53 |
+
"eval_runtime": 147.8879,
|
54 |
+
"eval_samples_per_second": 33.809,
|
55 |
+
"eval_steps_per_second": 4.226,
|
56 |
+
"step": 1125
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"learning_rate": 0.03497391566634178,
|
61 |
+
"loss": 0.4163,
|
62 |
+
"step": 1500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.0,
|
66 |
+
"eval_avg_length": 16.3844,
|
67 |
+
"eval_bleu": 0.0277,
|
68 |
+
"eval_loss": 0.3980478346347809,
|
69 |
+
"eval_rouge1": 0.3095,
|
70 |
+
"eval_rouge2": 0.2015,
|
71 |
+
"eval_runtime": 147.1224,
|
72 |
+
"eval_samples_per_second": 33.985,
|
73 |
+
"eval_steps_per_second": 4.248,
|
74 |
+
"step": 1500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_avg_length": 16.6804,
|
79 |
+
"eval_bleu": 0.0293,
|
80 |
+
"eval_loss": 0.3867902457714081,
|
81 |
+
"eval_rouge1": 0.325,
|
82 |
+
"eval_rouge2": 0.2082,
|
83 |
+
"eval_runtime": 148.2396,
|
84 |
+
"eval_samples_per_second": 33.729,
|
85 |
+
"eval_steps_per_second": 4.216,
|
86 |
+
"step": 1875
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 5.33,
|
90 |
+
"learning_rate": 0.0467718280851841,
|
91 |
+
"loss": 0.3808,
|
92 |
+
"step": 2000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 6.0,
|
96 |
+
"eval_avg_length": 16.7996,
|
97 |
+
"eval_bleu": 0.0288,
|
98 |
+
"eval_loss": 0.3814685046672821,
|
99 |
+
"eval_rouge1": 0.3232,
|
100 |
+
"eval_rouge2": 0.2089,
|
101 |
+
"eval_runtime": 148.5303,
|
102 |
+
"eval_samples_per_second": 33.663,
|
103 |
+
"eval_steps_per_second": 4.208,
|
104 |
+
"step": 2250
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.67,
|
108 |
+
"learning_rate": 0.05869544297456741,
|
109 |
+
"loss": 0.352,
|
110 |
+
"step": 2500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"eval_avg_length": 15.8864,
|
115 |
+
"eval_bleu": 0.024,
|
116 |
+
"eval_loss": 0.3719572126865387,
|
117 |
+
"eval_rouge1": 0.3225,
|
118 |
+
"eval_rouge2": 0.2119,
|
119 |
+
"eval_runtime": 149.27,
|
120 |
+
"eval_samples_per_second": 33.496,
|
121 |
+
"eval_steps_per_second": 4.187,
|
122 |
+
"step": 2625
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 8.0,
|
126 |
+
"learning_rate": 0.07078173756599426,
|
127 |
+
"loss": 0.3295,
|
128 |
+
"step": 3000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 8.0,
|
132 |
+
"eval_avg_length": 15.4172,
|
133 |
+
"eval_bleu": 0.0198,
|
134 |
+
"eval_loss": 0.36947065591812134,
|
135 |
+
"eval_rouge1": 0.3142,
|
136 |
+
"eval_rouge2": 0.2118,
|
137 |
+
"eval_runtime": 148.0999,
|
138 |
+
"eval_samples_per_second": 33.761,
|
139 |
+
"eval_steps_per_second": 4.22,
|
140 |
+
"step": 3000
|
141 |
+
}
|
142 |
+
],
|
143 |
+
"max_steps": 5625,
|
144 |
+
"num_train_epochs": 15,
|
145 |
+
"total_flos": 1.624101617664e+16,
|
146 |
+
"trial_name": null,
|
147 |
+
"trial_params": null
|
148 |
+
}
|
checkpoint-3000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51f06f3ae124ec7504d57ef8f8b1bd16ed5fe089c388d1a396b3bfc8d5bd0b4b
|
3 |
+
size 4027
|
checkpoint-4500/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"dense_act_fn": "relu",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "relu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": false,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
20 |
+
"num_decoder_layers": 6,
|
21 |
+
"num_heads": 8,
|
22 |
+
"num_layers": 6,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.28.1",
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 32128
|
60 |
+
}
|
checkpoint-4500/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.28.1"
|
6 |
+
}
|
checkpoint-4500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7289d35dcf18e4cc7ee2e229c42ead9ede0459f5a41a70e3b0411206153815e
|
3 |
+
size 839173
|
checkpoint-4500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50c631a8b6e82cb0799debcf9cc37798c3efcbea71567e923d3a66d48bd4b979
|
3 |
+
size 242071641
|
checkpoint-4500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbe1025ca7418e12fcd64d6af446b6cc8082b1d5b5b3fdf017b93b68ca121e57
|
3 |
+
size 14575
|
checkpoint-4500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:909663bf8b8745ef48c8bd726aad867de040ed32733ad1080a2efe4b0825d3f5
|
3 |
+
size 881
|
checkpoint-4500/special_tokens_map.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
107 |
+
}
|
checkpoint-4500/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-4500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4500/tokenizer_config.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"clean_up_tokenization_spaces": true,
|
105 |
+
"eos_token": "</s>",
|
106 |
+
"extra_ids": 100,
|
107 |
+
"model_max_length": 512,
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"tokenizer_class": "T5Tokenizer",
|
110 |
+
"unk_token": "<unk>"
|
111 |
+
}
|
checkpoint-4500/trainer_state.json
ADDED
@@ -0,0 +1,214 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.36947065591812134,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python-java-javascript-go/checkpoint-3000",
|
4 |
+
"epoch": 12.0,
|
5 |
+
"global_step": 4500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_avg_length": 17.688,
|
13 |
+
"eval_bleu": 0.0246,
|
14 |
+
"eval_loss": 0.49533936381340027,
|
15 |
+
"eval_rouge1": 0.2585,
|
16 |
+
"eval_rouge2": 0.1659,
|
17 |
+
"eval_runtime": 150.4831,
|
18 |
+
"eval_samples_per_second": 33.226,
|
19 |
+
"eval_steps_per_second": 4.153,
|
20 |
+
"step": 375
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.33,
|
24 |
+
"learning_rate": 0.011610765941441059,
|
25 |
+
"loss": 2.1147,
|
26 |
+
"step": 500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"eval_avg_length": 17.044,
|
31 |
+
"eval_bleu": 0.0263,
|
32 |
+
"eval_loss": 0.4376164674758911,
|
33 |
+
"eval_rouge1": 0.293,
|
34 |
+
"eval_rouge2": 0.1912,
|
35 |
+
"eval_runtime": 147.0412,
|
36 |
+
"eval_samples_per_second": 34.004,
|
37 |
+
"eval_steps_per_second": 4.251,
|
38 |
+
"step": 750
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 2.67,
|
42 |
+
"learning_rate": 0.02326086163520813,
|
43 |
+
"loss": 0.4761,
|
44 |
+
"step": 1000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_avg_length": 17.4636,
|
49 |
+
"eval_bleu": 0.0317,
|
50 |
+
"eval_loss": 0.4124959111213684,
|
51 |
+
"eval_rouge1": 0.2964,
|
52 |
+
"eval_rouge2": 0.1965,
|
53 |
+
"eval_runtime": 147.8879,
|
54 |
+
"eval_samples_per_second": 33.809,
|
55 |
+
"eval_steps_per_second": 4.226,
|
56 |
+
"step": 1125
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"learning_rate": 0.03497391566634178,
|
61 |
+
"loss": 0.4163,
|
62 |
+
"step": 1500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.0,
|
66 |
+
"eval_avg_length": 16.3844,
|
67 |
+
"eval_bleu": 0.0277,
|
68 |
+
"eval_loss": 0.3980478346347809,
|
69 |
+
"eval_rouge1": 0.3095,
|
70 |
+
"eval_rouge2": 0.2015,
|
71 |
+
"eval_runtime": 147.1224,
|
72 |
+
"eval_samples_per_second": 33.985,
|
73 |
+
"eval_steps_per_second": 4.248,
|
74 |
+
"step": 1500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_avg_length": 16.6804,
|
79 |
+
"eval_bleu": 0.0293,
|
80 |
+
"eval_loss": 0.3867902457714081,
|
81 |
+
"eval_rouge1": 0.325,
|
82 |
+
"eval_rouge2": 0.2082,
|
83 |
+
"eval_runtime": 148.2396,
|
84 |
+
"eval_samples_per_second": 33.729,
|
85 |
+
"eval_steps_per_second": 4.216,
|
86 |
+
"step": 1875
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 5.33,
|
90 |
+
"learning_rate": 0.0467718280851841,
|
91 |
+
"loss": 0.3808,
|
92 |
+
"step": 2000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 6.0,
|
96 |
+
"eval_avg_length": 16.7996,
|
97 |
+
"eval_bleu": 0.0288,
|
98 |
+
"eval_loss": 0.3814685046672821,
|
99 |
+
"eval_rouge1": 0.3232,
|
100 |
+
"eval_rouge2": 0.2089,
|
101 |
+
"eval_runtime": 148.5303,
|
102 |
+
"eval_samples_per_second": 33.663,
|
103 |
+
"eval_steps_per_second": 4.208,
|
104 |
+
"step": 2250
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.67,
|
108 |
+
"learning_rate": 0.05869544297456741,
|
109 |
+
"loss": 0.352,
|
110 |
+
"step": 2500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"eval_avg_length": 15.8864,
|
115 |
+
"eval_bleu": 0.024,
|
116 |
+
"eval_loss": 0.3719572126865387,
|
117 |
+
"eval_rouge1": 0.3225,
|
118 |
+
"eval_rouge2": 0.2119,
|
119 |
+
"eval_runtime": 149.27,
|
120 |
+
"eval_samples_per_second": 33.496,
|
121 |
+
"eval_steps_per_second": 4.187,
|
122 |
+
"step": 2625
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 8.0,
|
126 |
+
"learning_rate": 0.07078173756599426,
|
127 |
+
"loss": 0.3295,
|
128 |
+
"step": 3000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 8.0,
|
132 |
+
"eval_avg_length": 15.4172,
|
133 |
+
"eval_bleu": 0.0198,
|
134 |
+
"eval_loss": 0.36947065591812134,
|
135 |
+
"eval_rouge1": 0.3142,
|
136 |
+
"eval_rouge2": 0.2118,
|
137 |
+
"eval_runtime": 148.0999,
|
138 |
+
"eval_samples_per_second": 33.761,
|
139 |
+
"eval_steps_per_second": 4.22,
|
140 |
+
"step": 3000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 9.0,
|
144 |
+
"eval_avg_length": 16.8566,
|
145 |
+
"eval_bleu": 0.0305,
|
146 |
+
"eval_loss": 0.37361040711402893,
|
147 |
+
"eval_rouge1": 0.343,
|
148 |
+
"eval_rouge2": 0.2206,
|
149 |
+
"eval_runtime": 147.2089,
|
150 |
+
"eval_samples_per_second": 33.965,
|
151 |
+
"eval_steps_per_second": 4.246,
|
152 |
+
"step": 3375
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 9.33,
|
156 |
+
"learning_rate": 0.083040751516819,
|
157 |
+
"loss": 0.3052,
|
158 |
+
"step": 3500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 10.0,
|
162 |
+
"eval_avg_length": 16.8834,
|
163 |
+
"eval_bleu": 0.0316,
|
164 |
+
"eval_loss": 0.3810863196849823,
|
165 |
+
"eval_rouge1": 0.3442,
|
166 |
+
"eval_rouge2": 0.2215,
|
167 |
+
"eval_runtime": 148.536,
|
168 |
+
"eval_samples_per_second": 33.662,
|
169 |
+
"eval_steps_per_second": 4.208,
|
170 |
+
"step": 3750
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 10.67,
|
174 |
+
"learning_rate": 0.09552394598722458,
|
175 |
+
"loss": 0.2887,
|
176 |
+
"step": 4000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 11.0,
|
180 |
+
"eval_avg_length": 15.6226,
|
181 |
+
"eval_bleu": 0.023,
|
182 |
+
"eval_loss": 0.3774949610233307,
|
183 |
+
"eval_rouge1": 0.3262,
|
184 |
+
"eval_rouge2": 0.2149,
|
185 |
+
"eval_runtime": 147.496,
|
186 |
+
"eval_samples_per_second": 33.899,
|
187 |
+
"eval_steps_per_second": 4.237,
|
188 |
+
"step": 4125
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 12.0,
|
192 |
+
"learning_rate": 0.10829657316207886,
|
193 |
+
"loss": 0.2799,
|
194 |
+
"step": 4500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 12.0,
|
198 |
+
"eval_avg_length": 16.6344,
|
199 |
+
"eval_bleu": 0.034,
|
200 |
+
"eval_loss": 0.3793126344680786,
|
201 |
+
"eval_rouge1": 0.3397,
|
202 |
+
"eval_rouge2": 0.2186,
|
203 |
+
"eval_runtime": 147.6165,
|
204 |
+
"eval_samples_per_second": 33.872,
|
205 |
+
"eval_steps_per_second": 4.234,
|
206 |
+
"step": 4500
|
207 |
+
}
|
208 |
+
],
|
209 |
+
"max_steps": 5625,
|
210 |
+
"num_train_epochs": 15,
|
211 |
+
"total_flos": 2.436152426496e+16,
|
212 |
+
"trial_name": null,
|
213 |
+
"trial_params": null
|
214 |
+
}
|
checkpoint-4500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51f06f3ae124ec7504d57ef8f8b1bd16ed5fe089c388d1a396b3bfc8d5bd0b4b
|
3 |
+
size 4027
|
checkpoint-4875/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"dense_act_fn": "relu",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "relu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": false,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
20 |
+
"num_decoder_layers": 6,
|
21 |
+
"num_heads": 8,
|
22 |
+
"num_layers": 6,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.28.1",
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 32128
|
60 |
+
}
|
checkpoint-4875/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.28.1"
|
6 |
+
}
|
checkpoint-4875/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a61128a1eac2bd33b2d1be9e0cb5bbe3e8b87b024d2b175044dbe20fe43e33a4
|
3 |
+
size 839173
|
checkpoint-4875/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44c6800d737bd9d3cb7daae767bf722835a386c43211c9c0bfec56364a3b4b05
|
3 |
+
size 242071641
|
checkpoint-4875/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d642ece88c4bb28fd024d7d1af893e023e7b298920bad92cfb0dbea65055c6d9
|
3 |
+
size 14575
|
checkpoint-4875/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e7797c5869052a954064b5702ab79020ade4f9507ead71c5376fa4790855d42
|
3 |
+
size 881
|
checkpoint-4875/special_tokens_map.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
107 |
+
}
|
checkpoint-4875/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-4875/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4875/tokenizer_config.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"clean_up_tokenization_spaces": true,
|
105 |
+
"eos_token": "</s>",
|
106 |
+
"extra_ids": 100,
|
107 |
+
"model_max_length": 512,
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"tokenizer_class": "T5Tokenizer",
|
110 |
+
"unk_token": "<unk>"
|
111 |
+
}
|
checkpoint-4875/trainer_state.json
ADDED
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.36947065591812134,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python-java-javascript-go/checkpoint-3000",
|
4 |
+
"epoch": 13.0,
|
5 |
+
"global_step": 4875,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_avg_length": 17.688,
|
13 |
+
"eval_bleu": 0.0246,
|
14 |
+
"eval_loss": 0.49533936381340027,
|
15 |
+
"eval_rouge1": 0.2585,
|
16 |
+
"eval_rouge2": 0.1659,
|
17 |
+
"eval_runtime": 150.4831,
|
18 |
+
"eval_samples_per_second": 33.226,
|
19 |
+
"eval_steps_per_second": 4.153,
|
20 |
+
"step": 375
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.33,
|
24 |
+
"learning_rate": 0.011610765941441059,
|
25 |
+
"loss": 2.1147,
|
26 |
+
"step": 500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"eval_avg_length": 17.044,
|
31 |
+
"eval_bleu": 0.0263,
|
32 |
+
"eval_loss": 0.4376164674758911,
|
33 |
+
"eval_rouge1": 0.293,
|
34 |
+
"eval_rouge2": 0.1912,
|
35 |
+
"eval_runtime": 147.0412,
|
36 |
+
"eval_samples_per_second": 34.004,
|
37 |
+
"eval_steps_per_second": 4.251,
|
38 |
+
"step": 750
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 2.67,
|
42 |
+
"learning_rate": 0.02326086163520813,
|
43 |
+
"loss": 0.4761,
|
44 |
+
"step": 1000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_avg_length": 17.4636,
|
49 |
+
"eval_bleu": 0.0317,
|
50 |
+
"eval_loss": 0.4124959111213684,
|
51 |
+
"eval_rouge1": 0.2964,
|
52 |
+
"eval_rouge2": 0.1965,
|
53 |
+
"eval_runtime": 147.8879,
|
54 |
+
"eval_samples_per_second": 33.809,
|
55 |
+
"eval_steps_per_second": 4.226,
|
56 |
+
"step": 1125
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"learning_rate": 0.03497391566634178,
|
61 |
+
"loss": 0.4163,
|
62 |
+
"step": 1500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.0,
|
66 |
+
"eval_avg_length": 16.3844,
|
67 |
+
"eval_bleu": 0.0277,
|
68 |
+
"eval_loss": 0.3980478346347809,
|
69 |
+
"eval_rouge1": 0.3095,
|
70 |
+
"eval_rouge2": 0.2015,
|
71 |
+
"eval_runtime": 147.1224,
|
72 |
+
"eval_samples_per_second": 33.985,
|
73 |
+
"eval_steps_per_second": 4.248,
|
74 |
+
"step": 1500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_avg_length": 16.6804,
|
79 |
+
"eval_bleu": 0.0293,
|
80 |
+
"eval_loss": 0.3867902457714081,
|
81 |
+
"eval_rouge1": 0.325,
|
82 |
+
"eval_rouge2": 0.2082,
|
83 |
+
"eval_runtime": 148.2396,
|
84 |
+
"eval_samples_per_second": 33.729,
|
85 |
+
"eval_steps_per_second": 4.216,
|
86 |
+
"step": 1875
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 5.33,
|
90 |
+
"learning_rate": 0.0467718280851841,
|
91 |
+
"loss": 0.3808,
|
92 |
+
"step": 2000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 6.0,
|
96 |
+
"eval_avg_length": 16.7996,
|
97 |
+
"eval_bleu": 0.0288,
|
98 |
+
"eval_loss": 0.3814685046672821,
|
99 |
+
"eval_rouge1": 0.3232,
|
100 |
+
"eval_rouge2": 0.2089,
|
101 |
+
"eval_runtime": 148.5303,
|
102 |
+
"eval_samples_per_second": 33.663,
|
103 |
+
"eval_steps_per_second": 4.208,
|
104 |
+
"step": 2250
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.67,
|
108 |
+
"learning_rate": 0.05869544297456741,
|
109 |
+
"loss": 0.352,
|
110 |
+
"step": 2500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"eval_avg_length": 15.8864,
|
115 |
+
"eval_bleu": 0.024,
|
116 |
+
"eval_loss": 0.3719572126865387,
|
117 |
+
"eval_rouge1": 0.3225,
|
118 |
+
"eval_rouge2": 0.2119,
|
119 |
+
"eval_runtime": 149.27,
|
120 |
+
"eval_samples_per_second": 33.496,
|
121 |
+
"eval_steps_per_second": 4.187,
|
122 |
+
"step": 2625
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 8.0,
|
126 |
+
"learning_rate": 0.07078173756599426,
|
127 |
+
"loss": 0.3295,
|
128 |
+
"step": 3000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 8.0,
|
132 |
+
"eval_avg_length": 15.4172,
|
133 |
+
"eval_bleu": 0.0198,
|
134 |
+
"eval_loss": 0.36947065591812134,
|
135 |
+
"eval_rouge1": 0.3142,
|
136 |
+
"eval_rouge2": 0.2118,
|
137 |
+
"eval_runtime": 148.0999,
|
138 |
+
"eval_samples_per_second": 33.761,
|
139 |
+
"eval_steps_per_second": 4.22,
|
140 |
+
"step": 3000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 9.0,
|
144 |
+
"eval_avg_length": 16.8566,
|
145 |
+
"eval_bleu": 0.0305,
|
146 |
+
"eval_loss": 0.37361040711402893,
|
147 |
+
"eval_rouge1": 0.343,
|
148 |
+
"eval_rouge2": 0.2206,
|
149 |
+
"eval_runtime": 147.2089,
|
150 |
+
"eval_samples_per_second": 33.965,
|
151 |
+
"eval_steps_per_second": 4.246,
|
152 |
+
"step": 3375
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 9.33,
|
156 |
+
"learning_rate": 0.083040751516819,
|
157 |
+
"loss": 0.3052,
|
158 |
+
"step": 3500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 10.0,
|
162 |
+
"eval_avg_length": 16.8834,
|
163 |
+
"eval_bleu": 0.0316,
|
164 |
+
"eval_loss": 0.3810863196849823,
|
165 |
+
"eval_rouge1": 0.3442,
|
166 |
+
"eval_rouge2": 0.2215,
|
167 |
+
"eval_runtime": 148.536,
|
168 |
+
"eval_samples_per_second": 33.662,
|
169 |
+
"eval_steps_per_second": 4.208,
|
170 |
+
"step": 3750
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 10.67,
|
174 |
+
"learning_rate": 0.09552394598722458,
|
175 |
+
"loss": 0.2887,
|
176 |
+
"step": 4000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 11.0,
|
180 |
+
"eval_avg_length": 15.6226,
|
181 |
+
"eval_bleu": 0.023,
|
182 |
+
"eval_loss": 0.3774949610233307,
|
183 |
+
"eval_rouge1": 0.3262,
|
184 |
+
"eval_rouge2": 0.2149,
|
185 |
+
"eval_runtime": 147.496,
|
186 |
+
"eval_samples_per_second": 33.899,
|
187 |
+
"eval_steps_per_second": 4.237,
|
188 |
+
"step": 4125
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 12.0,
|
192 |
+
"learning_rate": 0.10829657316207886,
|
193 |
+
"loss": 0.2799,
|
194 |
+
"step": 4500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 12.0,
|
198 |
+
"eval_avg_length": 16.6344,
|
199 |
+
"eval_bleu": 0.034,
|
200 |
+
"eval_loss": 0.3793126344680786,
|
201 |
+
"eval_rouge1": 0.3397,
|
202 |
+
"eval_rouge2": 0.2186,
|
203 |
+
"eval_runtime": 147.6165,
|
204 |
+
"eval_samples_per_second": 33.872,
|
205 |
+
"eval_steps_per_second": 4.234,
|
206 |
+
"step": 4500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 13.0,
|
210 |
+
"eval_avg_length": 16.7964,
|
211 |
+
"eval_bleu": 0.0312,
|
212 |
+
"eval_loss": 0.3875396251678467,
|
213 |
+
"eval_rouge1": 0.3389,
|
214 |
+
"eval_rouge2": 0.2192,
|
215 |
+
"eval_runtime": 147.7995,
|
216 |
+
"eval_samples_per_second": 33.83,
|
217 |
+
"eval_steps_per_second": 4.229,
|
218 |
+
"step": 4875
|
219 |
+
}
|
220 |
+
],
|
221 |
+
"max_steps": 5625,
|
222 |
+
"num_train_epochs": 15,
|
223 |
+
"total_flos": 2.639165128704e+16,
|
224 |
+
"trial_name": null,
|
225 |
+
"trial_params": null
|
226 |
+
}
|
checkpoint-4875/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51f06f3ae124ec7504d57ef8f8b1bd16ed5fe089c388d1a396b3bfc8d5bd0b4b
|
3 |
+
size 4027
|
checkpoint-5250/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"dense_act_fn": "relu",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "relu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": false,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
20 |
+
"num_decoder_layers": 6,
|
21 |
+
"num_heads": 8,
|
22 |
+
"num_layers": 6,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.28.1",
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 32128
|
60 |
+
}
|
checkpoint-5250/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.28.1"
|
6 |
+
}
|
checkpoint-5250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32e8aa62b1a404211aad4dd680b05e9ce428d979276dab03afe88cb57d996fdd
|
3 |
+
size 839173
|
checkpoint-5250/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc53f483cb9ec871e70d9badd6d13e26a6dd07cd816b8e1592d37cb7625450c4
|
3 |
+
size 242071641
|
checkpoint-5250/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87e0f7e0e0915fb1bddd37cdf619379b10989487f1a64facecd5fd5fc54bc37e
|
3 |
+
size 14575
|
checkpoint-5250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ae5cd6cdc018faaa12bfb2de05b3d6d7c3c95aefab81cbbe238167125aeb001
|
3 |
+
size 881
|
checkpoint-5250/special_tokens_map.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
107 |
+
}
|
checkpoint-5250/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-5250/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-5250/tokenizer_config.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"clean_up_tokenization_spaces": true,
|
105 |
+
"eos_token": "</s>",
|
106 |
+
"extra_ids": 100,
|
107 |
+
"model_max_length": 512,
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"tokenizer_class": "T5Tokenizer",
|
110 |
+
"unk_token": "<unk>"
|
111 |
+
}
|
checkpoint-5250/trainer_state.json
ADDED
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.36947065591812134,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python-java-javascript-go/checkpoint-3000",
|
4 |
+
"epoch": 14.0,
|
5 |
+
"global_step": 5250,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_avg_length": 17.688,
|
13 |
+
"eval_bleu": 0.0246,
|
14 |
+
"eval_loss": 0.49533936381340027,
|
15 |
+
"eval_rouge1": 0.2585,
|
16 |
+
"eval_rouge2": 0.1659,
|
17 |
+
"eval_runtime": 150.4831,
|
18 |
+
"eval_samples_per_second": 33.226,
|
19 |
+
"eval_steps_per_second": 4.153,
|
20 |
+
"step": 375
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.33,
|
24 |
+
"learning_rate": 0.011610765941441059,
|
25 |
+
"loss": 2.1147,
|
26 |
+
"step": 500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"eval_avg_length": 17.044,
|
31 |
+
"eval_bleu": 0.0263,
|
32 |
+
"eval_loss": 0.4376164674758911,
|
33 |
+
"eval_rouge1": 0.293,
|
34 |
+
"eval_rouge2": 0.1912,
|
35 |
+
"eval_runtime": 147.0412,
|
36 |
+
"eval_samples_per_second": 34.004,
|
37 |
+
"eval_steps_per_second": 4.251,
|
38 |
+
"step": 750
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 2.67,
|
42 |
+
"learning_rate": 0.02326086163520813,
|
43 |
+
"loss": 0.4761,
|
44 |
+
"step": 1000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_avg_length": 17.4636,
|
49 |
+
"eval_bleu": 0.0317,
|
50 |
+
"eval_loss": 0.4124959111213684,
|
51 |
+
"eval_rouge1": 0.2964,
|
52 |
+
"eval_rouge2": 0.1965,
|
53 |
+
"eval_runtime": 147.8879,
|
54 |
+
"eval_samples_per_second": 33.809,
|
55 |
+
"eval_steps_per_second": 4.226,
|
56 |
+
"step": 1125
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"learning_rate": 0.03497391566634178,
|
61 |
+
"loss": 0.4163,
|
62 |
+
"step": 1500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.0,
|
66 |
+
"eval_avg_length": 16.3844,
|
67 |
+
"eval_bleu": 0.0277,
|
68 |
+
"eval_loss": 0.3980478346347809,
|
69 |
+
"eval_rouge1": 0.3095,
|
70 |
+
"eval_rouge2": 0.2015,
|
71 |
+
"eval_runtime": 147.1224,
|
72 |
+
"eval_samples_per_second": 33.985,
|
73 |
+
"eval_steps_per_second": 4.248,
|
74 |
+
"step": 1500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_avg_length": 16.6804,
|
79 |
+
"eval_bleu": 0.0293,
|
80 |
+
"eval_loss": 0.3867902457714081,
|
81 |
+
"eval_rouge1": 0.325,
|
82 |
+
"eval_rouge2": 0.2082,
|
83 |
+
"eval_runtime": 148.2396,
|
84 |
+
"eval_samples_per_second": 33.729,
|
85 |
+
"eval_steps_per_second": 4.216,
|
86 |
+
"step": 1875
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 5.33,
|
90 |
+
"learning_rate": 0.0467718280851841,
|
91 |
+
"loss": 0.3808,
|
92 |
+
"step": 2000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 6.0,
|
96 |
+
"eval_avg_length": 16.7996,
|
97 |
+
"eval_bleu": 0.0288,
|
98 |
+
"eval_loss": 0.3814685046672821,
|
99 |
+
"eval_rouge1": 0.3232,
|
100 |
+
"eval_rouge2": 0.2089,
|
101 |
+
"eval_runtime": 148.5303,
|
102 |
+
"eval_samples_per_second": 33.663,
|
103 |
+
"eval_steps_per_second": 4.208,
|
104 |
+
"step": 2250
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.67,
|
108 |
+
"learning_rate": 0.05869544297456741,
|
109 |
+
"loss": 0.352,
|
110 |
+
"step": 2500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"eval_avg_length": 15.8864,
|
115 |
+
"eval_bleu": 0.024,
|
116 |
+
"eval_loss": 0.3719572126865387,
|
117 |
+
"eval_rouge1": 0.3225,
|
118 |
+
"eval_rouge2": 0.2119,
|
119 |
+
"eval_runtime": 149.27,
|
120 |
+
"eval_samples_per_second": 33.496,
|
121 |
+
"eval_steps_per_second": 4.187,
|
122 |
+
"step": 2625
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 8.0,
|
126 |
+
"learning_rate": 0.07078173756599426,
|
127 |
+
"loss": 0.3295,
|
128 |
+
"step": 3000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 8.0,
|
132 |
+
"eval_avg_length": 15.4172,
|
133 |
+
"eval_bleu": 0.0198,
|
134 |
+
"eval_loss": 0.36947065591812134,
|
135 |
+
"eval_rouge1": 0.3142,
|
136 |
+
"eval_rouge2": 0.2118,
|
137 |
+
"eval_runtime": 148.0999,
|
138 |
+
"eval_samples_per_second": 33.761,
|
139 |
+
"eval_steps_per_second": 4.22,
|
140 |
+
"step": 3000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 9.0,
|
144 |
+
"eval_avg_length": 16.8566,
|
145 |
+
"eval_bleu": 0.0305,
|
146 |
+
"eval_loss": 0.37361040711402893,
|
147 |
+
"eval_rouge1": 0.343,
|
148 |
+
"eval_rouge2": 0.2206,
|
149 |
+
"eval_runtime": 147.2089,
|
150 |
+
"eval_samples_per_second": 33.965,
|
151 |
+
"eval_steps_per_second": 4.246,
|
152 |
+
"step": 3375
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 9.33,
|
156 |
+
"learning_rate": 0.083040751516819,
|
157 |
+
"loss": 0.3052,
|
158 |
+
"step": 3500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 10.0,
|
162 |
+
"eval_avg_length": 16.8834,
|
163 |
+
"eval_bleu": 0.0316,
|
164 |
+
"eval_loss": 0.3810863196849823,
|
165 |
+
"eval_rouge1": 0.3442,
|
166 |
+
"eval_rouge2": 0.2215,
|
167 |
+
"eval_runtime": 148.536,
|
168 |
+
"eval_samples_per_second": 33.662,
|
169 |
+
"eval_steps_per_second": 4.208,
|
170 |
+
"step": 3750
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 10.67,
|
174 |
+
"learning_rate": 0.09552394598722458,
|
175 |
+
"loss": 0.2887,
|
176 |
+
"step": 4000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 11.0,
|
180 |
+
"eval_avg_length": 15.6226,
|
181 |
+
"eval_bleu": 0.023,
|
182 |
+
"eval_loss": 0.3774949610233307,
|
183 |
+
"eval_rouge1": 0.3262,
|
184 |
+
"eval_rouge2": 0.2149,
|
185 |
+
"eval_runtime": 147.496,
|
186 |
+
"eval_samples_per_second": 33.899,
|
187 |
+
"eval_steps_per_second": 4.237,
|
188 |
+
"step": 4125
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 12.0,
|
192 |
+
"learning_rate": 0.10829657316207886,
|
193 |
+
"loss": 0.2799,
|
194 |
+
"step": 4500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 12.0,
|
198 |
+
"eval_avg_length": 16.6344,
|
199 |
+
"eval_bleu": 0.034,
|
200 |
+
"eval_loss": 0.3793126344680786,
|
201 |
+
"eval_rouge1": 0.3397,
|
202 |
+
"eval_rouge2": 0.2186,
|
203 |
+
"eval_runtime": 147.6165,
|
204 |
+
"eval_samples_per_second": 33.872,
|
205 |
+
"eval_steps_per_second": 4.234,
|
206 |
+
"step": 4500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 13.0,
|
210 |
+
"eval_avg_length": 16.7964,
|
211 |
+
"eval_bleu": 0.0312,
|
212 |
+
"eval_loss": 0.3875396251678467,
|
213 |
+
"eval_rouge1": 0.3389,
|
214 |
+
"eval_rouge2": 0.2192,
|
215 |
+
"eval_runtime": 147.7995,
|
216 |
+
"eval_samples_per_second": 33.83,
|
217 |
+
"eval_steps_per_second": 4.229,
|
218 |
+
"step": 4875
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 13.33,
|
222 |
+
"learning_rate": 0.12130403518676758,
|
223 |
+
"loss": 0.2517,
|
224 |
+
"step": 5000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 14.0,
|
228 |
+
"eval_avg_length": 16.9076,
|
229 |
+
"eval_bleu": 0.0337,
|
230 |
+
"eval_loss": 0.3832905888557434,
|
231 |
+
"eval_rouge1": 0.3387,
|
232 |
+
"eval_rouge2": 0.22,
|
233 |
+
"eval_runtime": 147.2933,
|
234 |
+
"eval_samples_per_second": 33.946,
|
235 |
+
"eval_steps_per_second": 4.243,
|
236 |
+
"step": 5250
|
237 |
+
}
|
238 |
+
],
|
239 |
+
"max_steps": 5625,
|
240 |
+
"num_train_epochs": 15,
|
241 |
+
"total_flos": 2.842177830912e+16,
|
242 |
+
"trial_name": null,
|
243 |
+
"trial_params": null
|
244 |
+
}
|
checkpoint-5250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51f06f3ae124ec7504d57ef8f8b1bd16ed5fe089c388d1a396b3bfc8d5bd0b4b
|
3 |
+
size 4027
|