Dauka-transformers
commited on
Commit
•
f4acddb
1
Parent(s):
7e1f21f
End of training
Browse files- README.md +91 -0
- config.json +39 -0
- emissions.csv +2 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- runs/Apr18_17-16-25_gpu212-02/events.out.tfevents.1713449794.gpu212-02.3270517.0 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +52 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: gpt2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: otu_gpt
|
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 |
+
# otu_gpt
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 4.6030
|
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: 0.0002
|
38 |
+
- train_batch_size: 256
|
39 |
+
- eval_batch_size: 128
|
40 |
+
- seed: 42
|
41 |
+
- distributed_type: multi-GPU
|
42 |
+
- num_devices: 8
|
43 |
+
- total_train_batch_size: 2048
|
44 |
+
- total_eval_batch_size: 1024
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 30
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:------:|:---------------:|
|
54 |
+
| 5.413 | 1.0 | 6430 | 5.3753 |
|
55 |
+
| 5.1384 | 2.0 | 12860 | 5.1224 |
|
56 |
+
| 4.996 | 3.0 | 19290 | 4.9950 |
|
57 |
+
| 4.9047 | 4.0 | 25720 | 4.9112 |
|
58 |
+
| 4.8292 | 5.0 | 32150 | 4.8572 |
|
59 |
+
| 4.7709 | 6.0 | 38580 | 4.8168 |
|
60 |
+
| 4.7345 | 7.0 | 45010 | 4.7872 |
|
61 |
+
| 4.6996 | 8.0 | 51440 | 4.7637 |
|
62 |
+
| 4.6509 | 9.0 | 57870 | 4.7396 |
|
63 |
+
| 4.6326 | 10.0 | 64300 | 4.7248 |
|
64 |
+
| 4.6049 | 11.0 | 70730 | 4.7104 |
|
65 |
+
| 4.5894 | 12.0 | 77160 | 4.6994 |
|
66 |
+
| 4.5574 | 13.0 | 83590 | 4.6868 |
|
67 |
+
| 4.5415 | 14.0 | 90020 | 4.6758 |
|
68 |
+
| 4.5283 | 15.0 | 96450 | 4.6676 |
|
69 |
+
| 4.4993 | 16.0 | 102880 | 4.6605 |
|
70 |
+
| 4.486 | 17.0 | 109310 | 4.6532 |
|
71 |
+
| 4.4675 | 18.0 | 115740 | 4.6467 |
|
72 |
+
| 4.4588 | 19.0 | 122170 | 4.6410 |
|
73 |
+
| 4.4402 | 20.0 | 128600 | 4.6347 |
|
74 |
+
| 4.4182 | 21.0 | 135030 | 4.6292 |
|
75 |
+
| 4.4031 | 22.0 | 141460 | 4.6262 |
|
76 |
+
| 4.3857 | 23.0 | 147890 | 4.6200 |
|
77 |
+
| 4.3726 | 24.0 | 154320 | 4.6150 |
|
78 |
+
| 4.3575 | 25.0 | 160750 | 4.6130 |
|
79 |
+
| 4.3369 | 26.0 | 167180 | 4.6102 |
|
80 |
+
| 4.3106 | 27.0 | 173610 | 4.6064 |
|
81 |
+
| 4.3068 | 28.0 | 180040 | 4.6044 |
|
82 |
+
| 4.2803 | 29.0 | 186470 | 4.6026 |
|
83 |
+
| 4.268 | 30.0 | 192900 | 4.6030 |
|
84 |
+
|
85 |
+
|
86 |
+
### Framework versions
|
87 |
+
|
88 |
+
- Transformers 4.39.3
|
89 |
+
- Pytorch 2.2.2+cu121
|
90 |
+
- Datasets 2.18.0
|
91 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
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": 2,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 512,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
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": "4.39.3",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 30000
|
39 |
+
}
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
+
2024-04-19T10:36:24,codecarbon,e0f1b38f-623d-4272-ad7f-42fab2e3fa40,62360.96308684349,3.5488854445795033,5.69087658193692e-05,82.5,0.0,282.9607129096985,1.4289430953671538,0.0,4.782612704686579,6.2115558000537385,Saudi Arabia,SAU,mecca region,,,Linux-5.14.0-162.23.1.el9_1.x86_64-x86_64-with-glibc2.34,3.9.13,2.2.3,24,Intel(R) Xeon(R) Platinum 8260 CPU @ 2.40GHz,8,8 x Tesla V100-SXM2-32GB,39.1165,22.2825,754.5619010925293,machine,N,1.0
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.39.3"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4fa7bb0731432a2eeb943bd266c1b9170ab8e71c75044ae02cfd08e0c017916
|
3 |
+
size 435544704
|
runs/Apr18_17-16-25_gpu212-02/events.out.tfevents.1713449794.gpu212-02.3270517.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aeef4a3673d25b0411093835d971314650a775d1461927e5e828c13523c14a0
|
3 |
+
size 115030
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"mask_token": {
|
17 |
+
"content": "<mask>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"pad_token": {
|
24 |
+
"content": "<pad>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "<unk>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"eos_token": "</s>",
|
47 |
+
"mask_token": "<mask>",
|
48 |
+
"model_max_length": 1000000000000000019884624838656,
|
49 |
+
"pad_token": "<pad>",
|
50 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
51 |
+
"unk_token": "<unk>"
|
52 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d894311cb5ce24ea446aebb038953d746d7700b87545b4525c279842feda8e39
|
3 |
+
size 4920
|