Commit
Β·
72d433b
1
Parent(s):
e54e3e6
renamed finetuned codet5 checkpoint folders
Browse files- codet5base_512/config.json β finetuned_codet5base_512/.ipynb_checkpoints/config-checkpoint.json +0 -0
- finetuned_codet5base_512/config.json +68 -0
- {codet5base_512 β finetuned_codet5base_512}/generation_config.json +0 -0
- {codet5base_512 β finetuned_codet5base_512}/merges.txt +0 -0
- {codet5base_512 β finetuned_codet5base_512}/optimizer.pt +0 -0
- {codet5base_512 β finetuned_codet5base_512}/pytorch_model.bin +0 -0
- {codet5base_512 β finetuned_codet5base_512}/rng_state_0.pth +0 -0
- {codet5base_512 β finetuned_codet5base_512}/rng_state_1.pth +0 -0
- {codet5base_512 β finetuned_codet5base_512}/scaler.pt +0 -0
- {codet5base_512 β finetuned_codet5base_512}/scheduler.pt +0 -0
- {codet5base_512 β finetuned_codet5base_512}/special_tokens_map.json +0 -0
- {codet5base_512 β finetuned_codet5base_512}/tokenizer.json +0 -0
- {codet5base_512 β finetuned_codet5base_512}/tokenizer_config.json +0 -0
- {codet5base_512 β finetuned_codet5base_512}/trainer_state.json +0 -0
- {codet5base_512 β finetuned_codet5base_512}/training_args.bin +0 -0
- {codet5base_512 β finetuned_codet5base_512}/vocab.json +0 -0
- codet5large_512/config.json β finetuned_codet5large_512/.ipynb_checkpoints/config-checkpoint.json +0 -0
- finetuned_codet5large_512/config.json +61 -0
- {codet5large_512 β finetuned_codet5large_512}/generation_config.json +0 -0
- {codet5large_512 β finetuned_codet5large_512}/merges.txt +0 -0
- {codet5large_512 β finetuned_codet5large_512}/optimizer.pt +0 -0
- {codet5large_512 β finetuned_codet5large_512}/pytorch_model.bin +0 -0
- {codet5large_512 β finetuned_codet5large_512}/rng_state_0.pth +0 -0
- {codet5large_512 β finetuned_codet5large_512}/rng_state_1.pth +0 -0
- {codet5large_512 β finetuned_codet5large_512}/rng_state_2.pth +0 -0
- {codet5large_512 β finetuned_codet5large_512}/rng_state_3.pth +0 -0
- {codet5large_512 β finetuned_codet5large_512}/scaler.pt +0 -0
- {codet5large_512 β finetuned_codet5large_512}/scheduler.pt +0 -0
- {codet5large_512 β finetuned_codet5large_512}/special_tokens_map.json +0 -0
- {codet5large_512 β finetuned_codet5large_512}/tokenizer.json +0 -0
- {codet5large_512 β finetuned_codet5large_512}/tokenizer_config.json +0 -0
- {codet5large_512 β finetuned_codet5large_512}/trainer_state.json +0 -0
- {codet5large_512 β finetuned_codet5large_512}/training_args.bin +0 -0
- {codet5large_512 β finetuned_codet5large_512}/vocab.json +0 -0
codet5base_512/config.json β finetuned_codet5base_512/.ipynb_checkpoints/config-checkpoint.json
RENAMED
File without changes
|
finetuned_codet5base_512/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Salesforce/codet5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"d_ff": 3072,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "relu",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"feed_forward_proj": "relu",
|
15 |
+
"gradient_checkpointing": false,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0"
|
18 |
+
},
|
19 |
+
"initializer_factor": 1.0,
|
20 |
+
"is_encoder_decoder": true,
|
21 |
+
"is_gated_act": false,
|
22 |
+
"label2id": {
|
23 |
+
"LABEL_0": 0
|
24 |
+
},
|
25 |
+
"layer_norm_epsilon": 1e-06,
|
26 |
+
"model_type": "t5",
|
27 |
+
"n_positions": 512,
|
28 |
+
"num_decoder_layers": 12,
|
29 |
+
"num_heads": 12,
|
30 |
+
"num_layers": 12,
|
31 |
+
"output_past": true,
|
32 |
+
"pad_token_id": 0,
|
33 |
+
"relative_attention_max_distance": 128,
|
34 |
+
"relative_attention_num_buckets": 32,
|
35 |
+
"task_specific_params": {
|
36 |
+
"summarization": {
|
37 |
+
"early_stopping": true,
|
38 |
+
"length_penalty": 2.0,
|
39 |
+
"max_length": 200,
|
40 |
+
"min_length": 30,
|
41 |
+
"no_repeat_ngram_size": 3,
|
42 |
+
"num_beams": 4,
|
43 |
+
"prefix": "summarize: "
|
44 |
+
},
|
45 |
+
"translation_en_to_de": {
|
46 |
+
"early_stopping": true,
|
47 |
+
"max_length": 300,
|
48 |
+
"num_beams": 4,
|
49 |
+
"prefix": "translate English to German: "
|
50 |
+
},
|
51 |
+
"translation_en_to_fr": {
|
52 |
+
"early_stopping": true,
|
53 |
+
"max_length": 300,
|
54 |
+
"num_beams": 4,
|
55 |
+
"prefix": "translate English to French: "
|
56 |
+
},
|
57 |
+
"translation_en_to_ro": {
|
58 |
+
"early_stopping": true,
|
59 |
+
"max_length": 300,
|
60 |
+
"num_beams": 4,
|
61 |
+
"prefix": "translate English to Romanian: "
|
62 |
+
}
|
63 |
+
},
|
64 |
+
"torch_dtype": "float32",
|
65 |
+
"transformers_version": "4.26.1",
|
66 |
+
"use_cache": true,
|
67 |
+
"vocab_size": 32100
|
68 |
+
}
|
{codet5base_512 β finetuned_codet5base_512}/generation_config.json
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/merges.txt
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/optimizer.pt
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/pytorch_model.bin
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/rng_state_0.pth
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/rng_state_1.pth
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/scaler.pt
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/scheduler.pt
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/special_tokens_map.json
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/tokenizer.json
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/tokenizer_config.json
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/trainer_state.json
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/training_args.bin
RENAMED
File without changes
|
{codet5base_512 β finetuned_codet5base_512}/vocab.json
RENAMED
File without changes
|
codet5large_512/config.json β finetuned_codet5large_512/.ipynb_checkpoints/config-checkpoint.json
RENAMED
File without changes
|
finetuned_codet5large_512/config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Salesforce/codet5-large",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"d_ff": 4096,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "relu",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"feed_forward_proj": "relu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": false,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 24,
|
22 |
+
"num_heads": 16,
|
23 |
+
"num_layers": 24,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"task_specific_params": {
|
29 |
+
"summarization": {
|
30 |
+
"early_stopping": true,
|
31 |
+
"length_penalty": 2.0,
|
32 |
+
"max_length": 200,
|
33 |
+
"min_length": 30,
|
34 |
+
"no_repeat_ngram_size": 3,
|
35 |
+
"num_beams": 4,
|
36 |
+
"prefix": "summarize: "
|
37 |
+
},
|
38 |
+
"translation_en_to_de": {
|
39 |
+
"early_stopping": true,
|
40 |
+
"max_length": 300,
|
41 |
+
"num_beams": 4,
|
42 |
+
"prefix": "translate English to German: "
|
43 |
+
},
|
44 |
+
"translation_en_to_fr": {
|
45 |
+
"early_stopping": true,
|
46 |
+
"max_length": 300,
|
47 |
+
"num_beams": 4,
|
48 |
+
"prefix": "translate English to French: "
|
49 |
+
},
|
50 |
+
"translation_en_to_ro": {
|
51 |
+
"early_stopping": true,
|
52 |
+
"max_length": 300,
|
53 |
+
"num_beams": 4,
|
54 |
+
"prefix": "translate English to Romanian: "
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.26.1",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 32100
|
61 |
+
}
|
{codet5large_512 β finetuned_codet5large_512}/generation_config.json
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/merges.txt
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/optimizer.pt
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/pytorch_model.bin
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/rng_state_0.pth
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/rng_state_1.pth
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/rng_state_2.pth
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/rng_state_3.pth
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/scaler.pt
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/scheduler.pt
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/special_tokens_map.json
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/tokenizer.json
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/tokenizer_config.json
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/trainer_state.json
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/training_args.bin
RENAMED
File without changes
|
{codet5large_512 β finetuned_codet5large_512}/vocab.json
RENAMED
File without changes
|