Hash-tag Producer
Browse files- README.md +1 -0
- summary/README.md +62 -0
- summary/checkpoint-1000/config.json +53 -0
- summary/checkpoint-1000/generation_config.json +9 -0
- summary/checkpoint-1000/model.safetensors +3 -0
- summary/checkpoint-1000/optimizer.pt +3 -0
- summary/checkpoint-1000/rng_state.pth +3 -0
- summary/checkpoint-1000/scheduler.pt +3 -0
- summary/checkpoint-1000/trainer_state.json +49 -0
- summary/checkpoint-1000/training_args.bin +3 -0
- summary/checkpoint-2000/config.json +53 -0
- summary/checkpoint-2000/generation_config.json +9 -0
- summary/checkpoint-2000/model.safetensors +3 -0
- summary/checkpoint-2000/optimizer.pt +3 -0
- summary/checkpoint-2000/rng_state.pth +3 -0
- summary/checkpoint-2000/scheduler.pt +3 -0
- summary/checkpoint-2000/trainer_state.json +77 -0
- summary/checkpoint-2000/training_args.bin +3 -0
- summary/config.json +53 -0
- summary/generation_config.json +9 -0
- summary/model.safetensors +3 -0
- summary/training_args.bin +3 -0
README.md
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
license: mit
|
3 |
base_model: gogamza/kobart-summarization
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
7 |
- name: modelling
|
|
|
2 |
license: mit
|
3 |
base_model: gogamza/kobart-summarization
|
4 |
tags:
|
5 |
+
- kobart-hashtag
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
8 |
- name: modelling
|
summary/README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: gogamza/kobart-summarization
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: summary
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# summary
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [gogamza/kobart-summarization](https://huggingface.co/gogamza/kobart-summarization) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.3772
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5.6e-05
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- lr_scheduler_warmup_steps: 300
|
44 |
+
- num_epochs: 50
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 1.4775 | 1.42 | 500 | 0.3851 |
|
51 |
+
| 0.2468 | 2.85 | 1000 | 0.3772 |
|
52 |
+
| 0.1299 | 4.27 | 1500 | 0.4203 |
|
53 |
+
| 0.0721 | 5.7 | 2000 | 0.4461 |
|
54 |
+
| 0.0425 | 7.12 | 2500 | 0.4582 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.37.1
|
60 |
+
- Pytorch 2.1.2+cu118
|
61 |
+
- Datasets 2.16.1
|
62 |
+
- Tokenizers 0.15.0
|
summary/checkpoint-1000/config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gogamza/kobart-summarization",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"author": "Heewon Jeon([email protected])",
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.1,
|
14 |
+
"classifier_dropout": 0.1,
|
15 |
+
"d_model": 768,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 3072,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"do_blenderbot_90_layernorm": false,
|
22 |
+
"dropout": 0.1,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 1,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": false,
|
30 |
+
"forced_eos_token_id": 2,
|
31 |
+
"id2label": {
|
32 |
+
"0": "NEGATIVE",
|
33 |
+
"1": "POSITIVE"
|
34 |
+
},
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_encoder_decoder": true,
|
37 |
+
"label2id": {
|
38 |
+
"NEGATIVE": 0,
|
39 |
+
"POSITIVE": 1
|
40 |
+
},
|
41 |
+
"max_position_embeddings": 1026,
|
42 |
+
"model_type": "bart",
|
43 |
+
"normalize_before": false,
|
44 |
+
"normalize_embedding": true,
|
45 |
+
"num_hidden_layers": 6,
|
46 |
+
"pad_token_id": 3,
|
47 |
+
"scale_embedding": false,
|
48 |
+
"static_position_embeddings": false,
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.37.1",
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 30000
|
53 |
+
}
|
summary/checkpoint-1000/generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"forced_eos_token_id": 2,
|
7 |
+
"pad_token_id": 3,
|
8 |
+
"transformers_version": "4.37.1"
|
9 |
+
}
|
summary/checkpoint-1000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaaefe8555148be9c217d03389c6f318a062734e3d21c862428dc24dd077c966
|
3 |
+
size 495589768
|
summary/checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe823b34aad96a0aad5a48d7105899b4a0d93666f2505de9b7ebb3f8031b0d55
|
3 |
+
size 991096314
|
summary/checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfc3860843d2f28a8166d3b37d46989af44566fae53e55aac0dfe4537f8511e0
|
3 |
+
size 14244
|
summary/checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:933464ad2184cbaa671990e8d169bfba24f19cc3ee21645e3920a0851f745585
|
3 |
+
size 1064
|
summary/checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.37720897793769836,
|
3 |
+
"best_model_checkpoint": "C:/Users/user/Documents/EWHA/log/log/modelling/summary/checkpoint-1000",
|
4 |
+
"epoch": 2.849002849002849,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.42,
|
13 |
+
"learning_rate": 5.5350724637681156e-05,
|
14 |
+
"loss": 1.4776,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.42,
|
19 |
+
"eval_loss": 0.3854794204235077,
|
20 |
+
"eval_runtime": 3.9836,
|
21 |
+
"eval_samples_per_second": 78.572,
|
22 |
+
"eval_steps_per_second": 10.041,
|
23 |
+
"step": 500
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.85,
|
27 |
+
"learning_rate": 5.372753623188405e-05,
|
28 |
+
"loss": 0.2469,
|
29 |
+
"step": 1000
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.85,
|
33 |
+
"eval_loss": 0.37720897793769836,
|
34 |
+
"eval_runtime": 3.9849,
|
35 |
+
"eval_samples_per_second": 78.547,
|
36 |
+
"eval_steps_per_second": 10.038,
|
37 |
+
"step": 1000
|
38 |
+
}
|
39 |
+
],
|
40 |
+
"logging_steps": 500,
|
41 |
+
"max_steps": 17550,
|
42 |
+
"num_input_tokens_seen": 0,
|
43 |
+
"num_train_epochs": 50,
|
44 |
+
"save_steps": 1000,
|
45 |
+
"total_flos": 2438945832960000.0,
|
46 |
+
"train_batch_size": 8,
|
47 |
+
"trial_name": null,
|
48 |
+
"trial_params": null
|
49 |
+
}
|
summary/checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a3fccd80e5474dd784ce999ac5d814a06dd74525db50ff68adc5fc250eba2a
|
3 |
+
size 4920
|
summary/checkpoint-2000/config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gogamza/kobart-summarization",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"author": "Heewon Jeon([email protected])",
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.1,
|
14 |
+
"classifier_dropout": 0.1,
|
15 |
+
"d_model": 768,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 3072,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"do_blenderbot_90_layernorm": false,
|
22 |
+
"dropout": 0.1,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 1,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": false,
|
30 |
+
"forced_eos_token_id": 2,
|
31 |
+
"id2label": {
|
32 |
+
"0": "NEGATIVE",
|
33 |
+
"1": "POSITIVE"
|
34 |
+
},
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_encoder_decoder": true,
|
37 |
+
"label2id": {
|
38 |
+
"NEGATIVE": 0,
|
39 |
+
"POSITIVE": 1
|
40 |
+
},
|
41 |
+
"max_position_embeddings": 1026,
|
42 |
+
"model_type": "bart",
|
43 |
+
"normalize_before": false,
|
44 |
+
"normalize_embedding": true,
|
45 |
+
"num_hidden_layers": 6,
|
46 |
+
"pad_token_id": 3,
|
47 |
+
"scale_embedding": false,
|
48 |
+
"static_position_embeddings": false,
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.37.1",
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 30000
|
53 |
+
}
|
summary/checkpoint-2000/generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"forced_eos_token_id": 2,
|
7 |
+
"pad_token_id": 3,
|
8 |
+
"transformers_version": "4.37.1"
|
9 |
+
}
|
summary/checkpoint-2000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58dc8ee0c3c6e3e50f12cbf70efb982c804e68635ab14b1819a9720d6180e061
|
3 |
+
size 495589768
|
summary/checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b0c55dfb531c09dc50373061e36273159e0a62a424c23d6a40df63f0ceba0b2
|
3 |
+
size 991096314
|
summary/checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80ec748c674904e17fc31da63c0d46571d28a546e5f3640632f0982b16f18198
|
3 |
+
size 14244
|
summary/checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50dadf3cf33ef7ebd5ad575ddf367de7b19bed3e6759b50c3955496605ab9082
|
3 |
+
size 1064
|
summary/checkpoint-2000/trainer_state.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.37720897793769836,
|
3 |
+
"best_model_checkpoint": "C:/Users/user/Documents/EWHA/log/log/modelling/summary/checkpoint-1000",
|
4 |
+
"epoch": 5.698005698005698,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.42,
|
13 |
+
"learning_rate": 5.5350724637681156e-05,
|
14 |
+
"loss": 1.4776,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.42,
|
19 |
+
"eval_loss": 0.3854794204235077,
|
20 |
+
"eval_runtime": 3.9836,
|
21 |
+
"eval_samples_per_second": 78.572,
|
22 |
+
"eval_steps_per_second": 10.041,
|
23 |
+
"step": 500
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.85,
|
27 |
+
"learning_rate": 5.372753623188405e-05,
|
28 |
+
"loss": 0.2469,
|
29 |
+
"step": 1000
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.85,
|
33 |
+
"eval_loss": 0.37720897793769836,
|
34 |
+
"eval_runtime": 3.9849,
|
35 |
+
"eval_samples_per_second": 78.547,
|
36 |
+
"eval_steps_per_second": 10.038,
|
37 |
+
"step": 1000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 4.27,
|
41 |
+
"learning_rate": 5.210434782608695e-05,
|
42 |
+
"loss": 0.1303,
|
43 |
+
"step": 1500
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 4.27,
|
47 |
+
"eval_loss": 0.4201067090034485,
|
48 |
+
"eval_runtime": 3.9854,
|
49 |
+
"eval_samples_per_second": 78.536,
|
50 |
+
"eval_steps_per_second": 10.037,
|
51 |
+
"step": 1500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 5.7,
|
55 |
+
"learning_rate": 5.0481159420289856e-05,
|
56 |
+
"loss": 0.0722,
|
57 |
+
"step": 2000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 5.7,
|
61 |
+
"eval_loss": 0.4348262846469879,
|
62 |
+
"eval_runtime": 3.9835,
|
63 |
+
"eval_samples_per_second": 78.574,
|
64 |
+
"eval_steps_per_second": 10.041,
|
65 |
+
"step": 2000
|
66 |
+
}
|
67 |
+
],
|
68 |
+
"logging_steps": 500,
|
69 |
+
"max_steps": 17550,
|
70 |
+
"num_input_tokens_seen": 0,
|
71 |
+
"num_train_epochs": 50,
|
72 |
+
"save_steps": 1000,
|
73 |
+
"total_flos": 4877891665920000.0,
|
74 |
+
"train_batch_size": 8,
|
75 |
+
"trial_name": null,
|
76 |
+
"trial_params": null
|
77 |
+
}
|
summary/checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a3fccd80e5474dd784ce999ac5d814a06dd74525db50ff68adc5fc250eba2a
|
3 |
+
size 4920
|
summary/config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gogamza/kobart-summarization",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"author": "Heewon Jeon([email protected])",
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.1,
|
14 |
+
"classifier_dropout": 0.1,
|
15 |
+
"d_model": 768,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 3072,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"do_blenderbot_90_layernorm": false,
|
22 |
+
"dropout": 0.1,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 1,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": false,
|
30 |
+
"forced_eos_token_id": 2,
|
31 |
+
"id2label": {
|
32 |
+
"0": "NEGATIVE",
|
33 |
+
"1": "POSITIVE"
|
34 |
+
},
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_encoder_decoder": true,
|
37 |
+
"label2id": {
|
38 |
+
"NEGATIVE": 0,
|
39 |
+
"POSITIVE": 1
|
40 |
+
},
|
41 |
+
"max_position_embeddings": 1026,
|
42 |
+
"model_type": "bart",
|
43 |
+
"normalize_before": false,
|
44 |
+
"normalize_embedding": true,
|
45 |
+
"num_hidden_layers": 6,
|
46 |
+
"pad_token_id": 3,
|
47 |
+
"scale_embedding": false,
|
48 |
+
"static_position_embeddings": false,
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.37.1",
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 30000
|
53 |
+
}
|
summary/generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"forced_eos_token_id": 2,
|
7 |
+
"pad_token_id": 3,
|
8 |
+
"transformers_version": "4.37.1"
|
9 |
+
}
|
summary/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58dc8ee0c3c6e3e50f12cbf70efb982c804e68635ab14b1819a9720d6180e061
|
3 |
+
size 495589768
|
summary/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a3fccd80e5474dd784ce999ac5d814a06dd74525db50ff68adc5fc250eba2a
|
3 |
+
size 4920
|