Delete output
Browse files- output/.ipynb_checkpoints/README-checkpoint.md +0 -57
- output/.ipynb_checkpoints/config-checkpoint.json +0 -39
- output/README.md +0 -57
- output/added_tokens.json +0 -6
- output/all_results.json +0 -16
- output/config.json +0 -39
- output/eval_results.json +0 -10
- output/generation_config.json +0 -6
- output/merges.txt +0 -0
- output/model.safetensors +0 -3
- output/special_tokens_map.json +0 -53
- output/tokenizer.json +0 -0
- output/tokenizer_config.json +0 -57
- output/train_results.json +0 -9
- output/trainer_state.json +0 -42
- output/training_args.bin +0 -3
- output/vocab.json +0 -0
output/.ipynb_checkpoints/README-checkpoint.md
DELETED
@@ -1,57 +0,0 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: nferruz/ProtGPT2
|
4 |
-
tags:
|
5 |
-
- generated_from_trainer
|
6 |
-
metrics:
|
7 |
-
- accuracy
|
8 |
-
model-index:
|
9 |
-
- name: output
|
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 |
-
# output
|
17 |
-
|
18 |
-
This model is a fine-tuned version of [nferruz/ProtGPT2](https://huggingface.co/nferruz/ProtGPT2) on an unknown dataset.
|
19 |
-
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 17.4453
|
21 |
-
- Accuracy: 0.0333
|
22 |
-
|
23 |
-
## Model description
|
24 |
-
|
25 |
-
More information needed
|
26 |
-
|
27 |
-
## Intended uses & limitations
|
28 |
-
|
29 |
-
More information needed
|
30 |
-
|
31 |
-
## Training and evaluation data
|
32 |
-
|
33 |
-
More information needed
|
34 |
-
|
35 |
-
## Training procedure
|
36 |
-
|
37 |
-
### Training hyperparameters
|
38 |
-
|
39 |
-
The following hyperparameters were used during training:
|
40 |
-
- learning_rate: 1e-06
|
41 |
-
- train_batch_size: 8
|
42 |
-
- eval_batch_size: 8
|
43 |
-
- seed: 42
|
44 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
-
- lr_scheduler_type: linear
|
46 |
-
- num_epochs: 3.0
|
47 |
-
|
48 |
-
### Training results
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
### Framework versions
|
53 |
-
|
54 |
-
- Transformers 4.41.0.dev0
|
55 |
-
- Pytorch 2.3.0+cu121
|
56 |
-
- Datasets 2.19.1
|
57 |
-
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/.ipynb_checkpoints/config-checkpoint.json
DELETED
@@ -1,39 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "nferruz/ProtGPT2",
|
3 |
-
"activation_function": "gelu_new",
|
4 |
-
"architectures": [
|
5 |
-
"GPT2LMHeadModel"
|
6 |
-
],
|
7 |
-
"attn_pdrop": 0.1,
|
8 |
-
"bos_token_id": 0,
|
9 |
-
"embd_pdrop": 0.1,
|
10 |
-
"eos_token_id": 0,
|
11 |
-
"initializer_range": 0.02,
|
12 |
-
"layer_norm_epsilon": 1e-05,
|
13 |
-
"model_type": "gpt2",
|
14 |
-
"n_ctx": 1024,
|
15 |
-
"n_embd": 1280,
|
16 |
-
"n_head": 20,
|
17 |
-
"n_inner": null,
|
18 |
-
"n_layer": 36,
|
19 |
-
"n_positions": 1024,
|
20 |
-
"reorder_and_upcast_attn": false,
|
21 |
-
"resid_pdrop": 0.1,
|
22 |
-
"scale_attn_by_inverse_layer_idx": false,
|
23 |
-
"scale_attn_weights": true,
|
24 |
-
"summary_activation": null,
|
25 |
-
"summary_first_dropout": 0.1,
|
26 |
-
"summary_proj_to_labels": true,
|
27 |
-
"summary_type": "cls_index",
|
28 |
-
"summary_use_proj": true,
|
29 |
-
"task_specific_params": {
|
30 |
-
"text-generation": {
|
31 |
-
"do_sample": true,
|
32 |
-
"max_length": 50
|
33 |
-
}
|
34 |
-
},
|
35 |
-
"torch_dtype": "float32",
|
36 |
-
"transformers_version": "4.41.0.dev0",
|
37 |
-
"use_cache": true,
|
38 |
-
"vocab_size": 50261
|
39 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/README.md
DELETED
@@ -1,57 +0,0 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: nferruz/ProtGPT2
|
4 |
-
tags:
|
5 |
-
- generated_from_trainer
|
6 |
-
metrics:
|
7 |
-
- accuracy
|
8 |
-
model-index:
|
9 |
-
- name: output
|
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 |
-
# output
|
17 |
-
|
18 |
-
This model is a fine-tuned version of [nferruz/ProtGPT2](https://huggingface.co/nferruz/ProtGPT2) on an unknown dataset.
|
19 |
-
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 17.4453
|
21 |
-
- Accuracy: 0.0333
|
22 |
-
|
23 |
-
## Model description
|
24 |
-
|
25 |
-
More information needed
|
26 |
-
|
27 |
-
## Intended uses & limitations
|
28 |
-
|
29 |
-
More information needed
|
30 |
-
|
31 |
-
## Training and evaluation data
|
32 |
-
|
33 |
-
More information needed
|
34 |
-
|
35 |
-
## Training procedure
|
36 |
-
|
37 |
-
### Training hyperparameters
|
38 |
-
|
39 |
-
The following hyperparameters were used during training:
|
40 |
-
- learning_rate: 1e-06
|
41 |
-
- train_batch_size: 8
|
42 |
-
- eval_batch_size: 8
|
43 |
-
- seed: 42
|
44 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
-
- lr_scheduler_type: linear
|
46 |
-
- num_epochs: 3.0
|
47 |
-
|
48 |
-
### Training results
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
### Framework versions
|
53 |
-
|
54 |
-
- Transformers 4.41.0.dev0
|
55 |
-
- Pytorch 2.3.0+cu121
|
56 |
-
- Datasets 2.19.1
|
57 |
-
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/added_tokens.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"LABEL": 50258,
|
3 |
-
"NEGATIVE": 50260,
|
4 |
-
"POSITIVE": 50259,
|
5 |
-
"SEQUENCE": 50257
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/all_results.json
DELETED
@@ -1,16 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 3.0,
|
3 |
-
"eval_accuracy": 0.033327800217635886,
|
4 |
-
"eval_loss": 17.445270538330078,
|
5 |
-
"eval_runtime": 64.8009,
|
6 |
-
"eval_samples": 53,
|
7 |
-
"eval_samples_per_second": 0.818,
|
8 |
-
"eval_steps_per_second": 0.108,
|
9 |
-
"perplexity": 37703765.88695272,
|
10 |
-
"total_flos": 2755037940940800.0,
|
11 |
-
"train_loss": 18.205491054205247,
|
12 |
-
"train_runtime": 2686.1496,
|
13 |
-
"train_samples": 211,
|
14 |
-
"train_samples_per_second": 0.236,
|
15 |
-
"train_steps_per_second": 0.03
|
16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/config.json
DELETED
@@ -1,39 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "nferruz/ProtGPT2",
|
3 |
-
"activation_function": "gelu_new",
|
4 |
-
"architectures": [
|
5 |
-
"GPT2LMHeadModel"
|
6 |
-
],
|
7 |
-
"attn_pdrop": 0.1,
|
8 |
-
"bos_token_id": 0,
|
9 |
-
"embd_pdrop": 0.1,
|
10 |
-
"eos_token_id": 0,
|
11 |
-
"initializer_range": 0.02,
|
12 |
-
"layer_norm_epsilon": 1e-05,
|
13 |
-
"model_type": "gpt2",
|
14 |
-
"n_ctx": 1024,
|
15 |
-
"n_embd": 1280,
|
16 |
-
"n_head": 20,
|
17 |
-
"n_inner": null,
|
18 |
-
"n_layer": 36,
|
19 |
-
"n_positions": 1024,
|
20 |
-
"reorder_and_upcast_attn": false,
|
21 |
-
"resid_pdrop": 0.1,
|
22 |
-
"scale_attn_by_inverse_layer_idx": false,
|
23 |
-
"scale_attn_weights": true,
|
24 |
-
"summary_activation": null,
|
25 |
-
"summary_first_dropout": 0.1,
|
26 |
-
"summary_proj_to_labels": true,
|
27 |
-
"summary_type": "cls_index",
|
28 |
-
"summary_use_proj": true,
|
29 |
-
"task_specific_params": {
|
30 |
-
"text-generation": {
|
31 |
-
"do_sample": true,
|
32 |
-
"max_length": 50
|
33 |
-
}
|
34 |
-
},
|
35 |
-
"torch_dtype": "float32",
|
36 |
-
"transformers_version": "4.41.0.dev0",
|
37 |
-
"use_cache": true,
|
38 |
-
"vocab_size": 50261
|
39 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/eval_results.json
DELETED
@@ -1,10 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 3.0,
|
3 |
-
"eval_accuracy": 0.033327800217635886,
|
4 |
-
"eval_loss": 17.445270538330078,
|
5 |
-
"eval_runtime": 64.8009,
|
6 |
-
"eval_samples": 53,
|
7 |
-
"eval_samples_per_second": 0.818,
|
8 |
-
"eval_steps_per_second": 0.108,
|
9 |
-
"perplexity": 37703765.88695272
|
10 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/generation_config.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"bos_token_id": 0,
|
4 |
-
"eos_token_id": 0,
|
5 |
-
"transformers_version": "4.41.0.dev0"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
output/model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:e5fe86886873f86be8df7fa1c0318bde417ed8d01d41bc7713f7fefe52e4cd6e
|
3 |
-
size 3096186408
|
|
|
|
|
|
|
|
output/special_tokens_map.json
DELETED
@@ -1,53 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
{
|
4 |
-
"content": "SEQUENCE",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
-
{
|
11 |
-
"content": "LABEL",
|
12 |
-
"lstrip": false,
|
13 |
-
"normalized": false,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
},
|
17 |
-
{
|
18 |
-
"content": "POSITIVE",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
},
|
24 |
-
{
|
25 |
-
"content": "NEGATIVE",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": false,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
}
|
31 |
-
],
|
32 |
-
"bos_token": {
|
33 |
-
"content": "<|endoftext|>",
|
34 |
-
"lstrip": false,
|
35 |
-
"normalized": true,
|
36 |
-
"rstrip": false,
|
37 |
-
"single_word": false
|
38 |
-
},
|
39 |
-
"eos_token": {
|
40 |
-
"content": "<|endoftext|>",
|
41 |
-
"lstrip": false,
|
42 |
-
"normalized": true,
|
43 |
-
"rstrip": false,
|
44 |
-
"single_word": false
|
45 |
-
},
|
46 |
-
"unk_token": {
|
47 |
-
"content": "<|endoftext|>",
|
48 |
-
"lstrip": false,
|
49 |
-
"normalized": true,
|
50 |
-
"rstrip": false,
|
51 |
-
"single_word": false
|
52 |
-
}
|
53 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
output/tokenizer_config.json
DELETED
@@ -1,57 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"0": {
|
5 |
-
"content": "<|endoftext|>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": true,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"50257": {
|
13 |
-
"content": "SEQUENCE",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false,
|
18 |
-
"special": true
|
19 |
-
},
|
20 |
-
"50258": {
|
21 |
-
"content": "LABEL",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": true
|
27 |
-
},
|
28 |
-
"50259": {
|
29 |
-
"content": "POSITIVE",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": false,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": true
|
35 |
-
},
|
36 |
-
"50260": {
|
37 |
-
"content": "NEGATIVE",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": true
|
43 |
-
}
|
44 |
-
},
|
45 |
-
"additional_special_tokens": [
|
46 |
-
"SEQUENCE",
|
47 |
-
"LABEL",
|
48 |
-
"POSITIVE",
|
49 |
-
"NEGATIVE"
|
50 |
-
],
|
51 |
-
"bos_token": "<|endoftext|>",
|
52 |
-
"clean_up_tokenization_spaces": true,
|
53 |
-
"eos_token": "<|endoftext|>",
|
54 |
-
"model_max_length": 1000000000000000019884624838656,
|
55 |
-
"tokenizer_class": "GPT2Tokenizer",
|
56 |
-
"unk_token": "<|endoftext|>"
|
57 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/train_results.json
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 3.0,
|
3 |
-
"total_flos": 2755037940940800.0,
|
4 |
-
"train_loss": 18.205491054205247,
|
5 |
-
"train_runtime": 2686.1496,
|
6 |
-
"train_samples": 211,
|
7 |
-
"train_samples_per_second": 0.236,
|
8 |
-
"train_steps_per_second": 0.03
|
9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/trainer_state.json
DELETED
@@ -1,42 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 3.0,
|
5 |
-
"eval_steps": 500,
|
6 |
-
"global_step": 81,
|
7 |
-
"is_hyper_param_search": false,
|
8 |
-
"is_local_process_zero": true,
|
9 |
-
"is_world_process_zero": true,
|
10 |
-
"log_history": [
|
11 |
-
{
|
12 |
-
"epoch": 3.0,
|
13 |
-
"step": 81,
|
14 |
-
"total_flos": 2755037940940800.0,
|
15 |
-
"train_loss": 18.205491054205247,
|
16 |
-
"train_runtime": 2686.1496,
|
17 |
-
"train_samples_per_second": 0.236,
|
18 |
-
"train_steps_per_second": 0.03
|
19 |
-
}
|
20 |
-
],
|
21 |
-
"logging_steps": 500,
|
22 |
-
"max_steps": 81,
|
23 |
-
"num_input_tokens_seen": 0,
|
24 |
-
"num_train_epochs": 3,
|
25 |
-
"save_steps": 500,
|
26 |
-
"stateful_callbacks": {
|
27 |
-
"TrainerControl": {
|
28 |
-
"args": {
|
29 |
-
"should_epoch_stop": false,
|
30 |
-
"should_evaluate": false,
|
31 |
-
"should_log": false,
|
32 |
-
"should_save": false,
|
33 |
-
"should_training_stop": false
|
34 |
-
},
|
35 |
-
"attributes": {}
|
36 |
-
}
|
37 |
-
},
|
38 |
-
"total_flos": 2755037940940800.0,
|
39 |
-
"train_batch_size": 8,
|
40 |
-
"trial_name": null,
|
41 |
-
"trial_params": null
|
42 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
output/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:5371f35bff206707f9ddaf992638a117f21ea77e0dff29ff32167fb76831cb11
|
3 |
-
size 5048
|
|
|
|
|
|
|
|
output/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|