KimByeongSu
commited on
Commit
•
0786c90
1
Parent(s):
32ece93
gpt-neo-125m-cs-finetuning-500-2
Browse files- README.md +59 -0
- config.json +55 -0
- emissions.csv +2 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- runs/Apr10_16-11-33_kbs/events.out.tfevents.1712733096.kbs.27236.5 +3 -0
- runs/Apr10_16-11-33_kbs/events.out.tfevents.1712733109.kbs.27236.6 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: EleutherAI/gpt-neo-125m
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: gpt-neo-125m-cs-finetuning-500-2
|
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 |
+
# gpt-neo-125m-cs-finetuning-500-2
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [EleutherAI/gpt-neo-125m](https://huggingface.co/EleutherAI/gpt-neo-125m) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 3.5173
|
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: 2e-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 |
+
- num_epochs: 3.0
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 6 | 3.5929 |
|
50 |
+
| No log | 2.0 | 12 | 3.5353 |
|
51 |
+
| No log | 3.0 | 18 | 3.5173 |
|
52 |
+
|
53 |
+
|
54 |
+
### Framework versions
|
55 |
+
|
56 |
+
- Transformers 4.36.2
|
57 |
+
- Pytorch 1.13.1+cu117
|
58 |
+
- Datasets 2.14.6
|
59 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/gpt-neo-125m",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"local",
|
11 |
+
"global",
|
12 |
+
"local",
|
13 |
+
"global",
|
14 |
+
"local",
|
15 |
+
"global",
|
16 |
+
"local",
|
17 |
+
"global",
|
18 |
+
"local",
|
19 |
+
"global",
|
20 |
+
"local"
|
21 |
+
],
|
22 |
+
"attention_types": [
|
23 |
+
[
|
24 |
+
[
|
25 |
+
"global",
|
26 |
+
"local"
|
27 |
+
],
|
28 |
+
6
|
29 |
+
]
|
30 |
+
],
|
31 |
+
"bos_token_id": 50256,
|
32 |
+
"classifier_dropout": 0.1,
|
33 |
+
"embed_dropout": 0,
|
34 |
+
"eos_token_id": 50256,
|
35 |
+
"gradient_checkpointing": false,
|
36 |
+
"hidden_size": 768,
|
37 |
+
"initializer_range": 0.02,
|
38 |
+
"intermediate_size": null,
|
39 |
+
"layer_norm_epsilon": 1e-05,
|
40 |
+
"max_position_embeddings": 2048,
|
41 |
+
"model_type": "gpt_neo",
|
42 |
+
"num_heads": 12,
|
43 |
+
"num_layers": 12,
|
44 |
+
"resid_dropout": 0,
|
45 |
+
"summary_activation": null,
|
46 |
+
"summary_first_dropout": 0.1,
|
47 |
+
"summary_proj_to_labels": true,
|
48 |
+
"summary_type": "cls_index",
|
49 |
+
"summary_use_proj": true,
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.36.2",
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 50257,
|
54 |
+
"window_size": 256
|
55 |
+
}
|
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 |
+
2024-04-10T16:11:49,codecarbon,f7587213-eb73-4c2c-b915-630349211caf,13.35900616645813,0.00030776781032010195,2.303822653311196e-05,42.5,126.726,11.905189990997316,0.00015769868195056916,0.0004700128714772066,4.41517421904707e-05,0.0006718632956182464,South Korea,KOR,gyeonggi-do,,,Windows-10-10.0.19045-SP0,3.9.18,2.2.3,20,12th Gen Intel(R) Core(TM) i7-12700,1,1 x NVIDIA GeForce RTX 3060,126.7741,37.6999,31.747173309326172,machine,N,1.0
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:407deeae80275b63ae2b849add38fa1386e661c79eb66812df4948183d17d7e1
|
3 |
+
size 500811336
|
runs/Apr10_16-11-33_kbs/events.out.tfevents.1712733096.kbs.27236.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bfd86c00bf1b2c5537bbfe22a21645f51692ba63683adbc54868208e7da3a05
|
3 |
+
size 5956
|
runs/Apr10_16-11-33_kbs/events.out.tfevents.1712733109.kbs.27236.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b5dc5d180797eb718141c4c52656b5609123aaeeb11e97418d5cac6d1446a26
|
3 |
+
size 306
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2567bd8910b08b12cbe2e8877e2a1ebdbe0b371c3311dfe14d0f8d5535182a86
|
3 |
+
size 4283
|