michalzajac
commited on
Commit
•
23ae9d6
1
Parent(s):
1e40b07
End of training
Browse files- README.md +52 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: EleutherAI/pythia-1b-deduped
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: robust_llm_pythia-wl-1b-mz-ada-v3-s-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 |
+
# robust_llm_pythia-wl-1b-mz-ada-v3-s-2
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [EleutherAI/pythia-1b-deduped](https://huggingface.co/EleutherAI/pythia-1b-deduped) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 1e-05
|
36 |
+
- train_batch_size: 8
|
37 |
+
- eval_batch_size: 64
|
38 |
+
- seed: 2
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 1
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.37.2
|
50 |
+
- Pytorch 2.2.0
|
51 |
+
- Datasets 2.17.0
|
52 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/pythia-1b-deduped",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_bias": true,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": 0.1,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 2048,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 8192,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 2048,
|
18 |
+
"model_type": "gpt_neox",
|
19 |
+
"num_attention_heads": 8,
|
20 |
+
"num_hidden_layers": 16,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rotary_emb_base": 10000,
|
25 |
+
"rotary_pct": 0.25,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.37.2",
|
29 |
+
"use_cache": false,
|
30 |
+
"use_parallel_residual": true,
|
31 |
+
"vocab_size": 50304
|
32 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d00f487885a3a6e5e8a256ca83fbe3b32b41225b011e16fbbf653febe0974d9
|
3 |
+
size 3635075536
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:137cb3b098026161dee9982bc9378152b504b0def3befe506d18503e445074ee
|
3 |
+
size 4728
|