Upload model
Browse files- README.md +62 -0
- config.json +31 -0
- generation_config.json +6 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: watson-cerebras
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# watson-cerebras
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [cerebras/Cerebras-GPT-111M](https://huggingface.co/cerebras/Cerebras-GPT-111M) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.4660
|
18 |
+
- Validation Loss: 5.9842
|
19 |
+
- Epoch: 9
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
39 |
+
- training_precision: float32
|
40 |
+
|
41 |
+
### Training results
|
42 |
+
|
43 |
+
| Train Loss | Validation Loss | Epoch |
|
44 |
+
|:----------:|:---------------:|:-----:|
|
45 |
+
| 1.9574 | 4.6971 | 0 |
|
46 |
+
| 1.4977 | 4.9437 | 1 |
|
47 |
+
| 1.1154 | 5.1888 | 2 |
|
48 |
+
| 0.8291 | 5.4171 | 3 |
|
49 |
+
| 0.6540 | 5.5523 | 4 |
|
50 |
+
| 0.5654 | 5.6664 | 5 |
|
51 |
+
| 0.5230 | 5.7875 | 6 |
|
52 |
+
| 0.4976 | 5.8304 | 7 |
|
53 |
+
| 0.4838 | 5.8645 | 8 |
|
54 |
+
| 0.4660 | 5.9842 | 9 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.30.2
|
60 |
+
- TensorFlow 2.12.0
|
61 |
+
- Datasets 2.13.1
|
62 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cerebras/Cerebras-GPT-111M",
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.0,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.0,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_embd": 768,
|
15 |
+
"n_head": 12,
|
16 |
+
"n_inner": 3072,
|
17 |
+
"n_layer": 10,
|
18 |
+
"n_positions": 2048,
|
19 |
+
"reorder_and_upcast_attn": false,
|
20 |
+
"resid_pdrop": 0.0,
|
21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 50257
|
31 |
+
}
|
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": "4.30.2"
|
6 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f45f344d718e6747e7e9bc6006720004ab92db6b205c4d1a5436e13e2ece14c
|
3 |
+
size 444352640
|