VTSNLP/base_LLM_200M
Browse files- README.md +47 -0
- config.json +34 -0
- generation_config.json +5 -0
- model.safetensors +3 -0
- runs/Oct01_12-31-49_kao-dgxa-e10-u17/events.out.tfevents.1727782320.kao-dgxa-e10-u17.243276.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: base_LLM_200M
|
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 |
+
# base_LLM_200M
|
13 |
+
|
14 |
+
This model was trained from scratch on an unknown dataset.
|
15 |
+
|
16 |
+
## Model description
|
17 |
+
|
18 |
+
More information needed
|
19 |
+
|
20 |
+
## Intended uses & limitations
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Training and evaluation data
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training procedure
|
29 |
+
|
30 |
+
### Training hyperparameters
|
31 |
+
|
32 |
+
The following hyperparameters were used during training:
|
33 |
+
- learning_rate: 3.6e-05
|
34 |
+
- train_batch_size: 4
|
35 |
+
- eval_batch_size: 1
|
36 |
+
- seed: 42
|
37 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
+
- lr_scheduler_type: linear
|
39 |
+
- num_epochs: 1
|
40 |
+
- mixed_precision_training: Native AMP
|
41 |
+
|
42 |
+
### Framework versions
|
43 |
+
|
44 |
+
- Transformers 4.40.1
|
45 |
+
- Pytorch 2.3.0+cu121
|
46 |
+
- Datasets 2.19.0
|
47 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "base_LLM_200M/checkpoint-755000",
|
3 |
+
"abili": false,
|
4 |
+
"architectures": [
|
5 |
+
"MptForCausalLM"
|
6 |
+
],
|
7 |
+
"attn_config": {
|
8 |
+
"model_type": ""
|
9 |
+
},
|
10 |
+
"d_model": 768,
|
11 |
+
"emb_pdrop": 0.0,
|
12 |
+
"embedding_fraction": 1.0,
|
13 |
+
"expansion_ratio": 4,
|
14 |
+
"init_device": "cpu",
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"layer_norm_epsilon": 1e-05,
|
17 |
+
"learned_pos_emb": true,
|
18 |
+
"logit_scale": null,
|
19 |
+
"max_seq_len": 8192,
|
20 |
+
"model_type": "mpt",
|
21 |
+
"n_heads": 12,
|
22 |
+
"n_layers": 12,
|
23 |
+
"no_bias": true,
|
24 |
+
"norm_type": "low_precision_layernorm",
|
25 |
+
"pad_token_id": 128001,
|
26 |
+
"resid_pdrop": 0.0,
|
27 |
+
"rope": true,
|
28 |
+
"rope_theta": 100000,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.40.1",
|
31 |
+
"use_cache": false,
|
32 |
+
"verbose": 0,
|
33 |
+
"vocab_size": 128256
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.40.1",
|
4 |
+
"use_cache": false
|
5 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a667bebfc779892c88b7ad9e3f07f3153051f9a39f88abc66541ad0237a8743b
|
3 |
+
size 733826032
|
runs/Oct01_12-31-49_kao-dgxa-e10-u17/events.out.tfevents.1727782320.kao-dgxa-e10-u17.243276.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d29a7a89fafc1d977d64b71ed187228893309019c86fb44c32a8192f47031ad6
|
3 |
+
size 74696
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a93a2d94c52d66c8f051c9b280bc1875eba482cfb1f3ffffa9212cf2f8c62ee9
|
3 |
+
size 5112
|