spx-25
Browse files- README.md +59 -0
- config.json +26 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: spx2
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# spx2
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: nan
|
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: 0.1
|
36 |
+
- train_batch_size: 2
|
37 |
+
- eval_batch_size: 2
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 5
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
47 |
+
| 1.8846 | 1.0 | 9996 | nan |
|
48 |
+
| 1.2821 | 2.0 | 19992 | nan |
|
49 |
+
| 1.0979 | 3.0 | 29988 | nan |
|
50 |
+
| 0.9594 | 4.0 | 39984 | nan |
|
51 |
+
| 0.8992 | 5.0 | 49980 | nan |
|
52 |
+
|
53 |
+
|
54 |
+
### Framework versions
|
55 |
+
|
56 |
+
- Transformers 4.33.1
|
57 |
+
- Pytorch 2.0.1+cu117
|
58 |
+
- Datasets 2.14.5
|
59 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 1,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"hidden_act": "silu",
|
8 |
+
"hidden_size": 4096,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 11008,
|
11 |
+
"max_position_embeddings": 2048,
|
12 |
+
"model_type": "llama",
|
13 |
+
"num_attention_heads": 4,
|
14 |
+
"num_hidden_layers": 4,
|
15 |
+
"num_key_value_heads": 4,
|
16 |
+
"pretraining_tp": 1,
|
17 |
+
"rms_norm_eps": 1e-06,
|
18 |
+
"rope_scaling": null,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.33.1",
|
23 |
+
"type_vocab_size": 1,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 248
|
26 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.33.1"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc3edd9adefdf7fca7bc71239266af6849e588ef04a592505d1c98ebc370ba74
|
3 |
+
size 3246289382
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3097e1264956d88bbcb245059fb696279ee820d55130650ee57ca67d99f6586
|
3 |
+
size 4027
|