arshiakarimian1
commited on
Commit
•
4f33d64
1
Parent(s):
662a615
End of training
Browse files- README.md +55 -0
- config.json +39 -0
- generation_config.json +11 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: llama3.1
|
4 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: spam-student-6-512
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# spam-student-6-512
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 5e-06
|
37 |
+
- train_batch_size: 8
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- lr_scheduler_warmup_steps: 500
|
43 |
+
- num_epochs: 1
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.44.2
|
53 |
+
- Pytorch 2.4.0+cu121
|
54 |
+
- Datasets 2.21.0
|
55 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 512,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 14336,
|
18 |
+
"max_position_embeddings": 131072,
|
19 |
+
"mlp_bias": false,
|
20 |
+
"model_type": "llama",
|
21 |
+
"num_attention_heads": 32,
|
22 |
+
"num_hidden_layers": 6,
|
23 |
+
"num_key_value_heads": 8,
|
24 |
+
"pretraining_tp": 1,
|
25 |
+
"rms_norm_eps": 1e-05,
|
26 |
+
"rope_scaling": {
|
27 |
+
"factor": 8.0,
|
28 |
+
"high_freq_factor": 4.0,
|
29 |
+
"low_freq_factor": 1.0,
|
30 |
+
"original_max_position_embeddings": 8192,
|
31 |
+
"rope_type": "llama3"
|
32 |
+
},
|
33 |
+
"rope_theta": 500000.0,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.44.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 128256
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 128000,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128008,
|
7 |
+
128009
|
8 |
+
],
|
9 |
+
"pad_token_id": 128009,
|
10 |
+
"transformers_version": "4.44.2"
|
11 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4d44f67b3c938330dae2eeb2926bca7ce2c7909944d0bd40b0ba066a63f5c20
|
3 |
+
size 1069580488
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40bda64994a0dfcca18e3c6e92aa30fcfb62a0c909564d6af79332c9c6a7e8e4
|
3 |
+
size 5176
|