ianmckenzie
commited on
Commit
•
e14903b
1
Parent(s):
6a69d12
End of training
Browse files- README.md +51 -0
- config.json +44 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: stanford-crfm/celebrimbor-gpt2-medium-x81
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: robust_llm_celebrimbor-ian-imdb-v0
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# robust_llm_celebrimbor-ian-imdb-v0
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [stanford-crfm/celebrimbor-gpt2-medium-x81](https://huggingface.co/stanford-crfm/celebrimbor-gpt2-medium-x81) on an unknown dataset.
|
16 |
+
|
17 |
+
## Model description
|
18 |
+
|
19 |
+
More information needed
|
20 |
+
|
21 |
+
## Intended uses & limitations
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Training and evaluation data
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training procedure
|
30 |
+
|
31 |
+
### Training hyperparameters
|
32 |
+
|
33 |
+
The following hyperparameters were used during training:
|
34 |
+
- learning_rate: 1e-05
|
35 |
+
- train_batch_size: 8
|
36 |
+
- eval_batch_size: 64
|
37 |
+
- seed: 42
|
38 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
39 |
+
- lr_scheduler_type: linear
|
40 |
+
- num_epochs: 1
|
41 |
+
|
42 |
+
### Training results
|
43 |
+
|
44 |
+
|
45 |
+
|
46 |
+
### Framework versions
|
47 |
+
|
48 |
+
- Transformers 4.37.2
|
49 |
+
- Pytorch 2.2.0
|
50 |
+
- Datasets 2.17.0
|
51 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stanford-crfm/celebrimbor-gpt2-medium-x81",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 1024,
|
17 |
+
"n_head": 16,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 24,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"n_special": 0,
|
22 |
+
"pad_token_id": 50256,
|
23 |
+
"predict_special_tokens": true,
|
24 |
+
"problem_type": "single_label_classification",
|
25 |
+
"reorder_and_upcast_attn": true,
|
26 |
+
"resid_pdrop": 0.1,
|
27 |
+
"scale_attn_by_inverse_layer_idx": true,
|
28 |
+
"scale_attn_weights": true,
|
29 |
+
"summary_activation": null,
|
30 |
+
"summary_first_dropout": 0.1,
|
31 |
+
"summary_proj_to_labels": true,
|
32 |
+
"summary_type": "cls_index",
|
33 |
+
"summary_use_proj": true,
|
34 |
+
"task_specific_params": {
|
35 |
+
"text-generation": {
|
36 |
+
"do_sample": true,
|
37 |
+
"max_length": 50
|
38 |
+
}
|
39 |
+
},
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.37.2",
|
42 |
+
"use_cache": false,
|
43 |
+
"vocab_size": 50257
|
44 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:654547e4809850b78647d91d528cdfb06c1fd0fd89ab0624cf977641d063598f
|
3 |
+
size 1419331144
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b67579ad813a9111e63308d175e6d9bdf656be31f8a072c1e79e425aee4323ab
|
3 |
+
size 4728
|