ac13b
Browse files- README.md +58 -0
- added_tokens.json +4 -0
- all_results.json +8 -0
- config.json +26 -0
- generation_config.json +10 -0
- log.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jan29_09-54-51_ts-cbba87c5e7504a249f5127103d9ce40f-launcher/1706495347.9318979/events.out.tfevents.1706495347.ts-cbba87c5e7504a249f5127103d9ce40f-launcher.48748.1 +3 -0
- runs/Jan29_09-54-51_ts-cbba87c5e7504a249f5127103d9ce40f-launcher/events.out.tfevents.1706495347.ts-cbba87c5e7504a249f5127103d9ce40f-launcher.48748.0 +3 -0
- runs/Jan29_11-10-29_ts-cbba87c5e7504a249f5127103d9ce40f-launcher/1706499936.7397811/events.out.tfevents.1706499936.ts-cbba87c5e7504a249f5127103d9ce40f-launcher.67020.1 +3 -0
- runs/Jan29_11-10-29_ts-cbba87c5e7504a249f5127103d9ce40f-launcher/events.out.tfevents.1706499936.ts-cbba87c5e7504a249f5127103d9ce40f-launcher.67020.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.model +3 -0
- tokenizer_config.json +33 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- /apdcephfs/share_733425/vinnylywang/jianhuipang/datasets/RedPajama-Data-1T-Sample
|
6 |
+
model-index:
|
7 |
+
- name: allm-ac-13b
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# allm-ac-13b
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [/apdcephfs/share_733425/vinnylywang/jianhuipang/opensourcellms/llama2/Llama-2-13b-hf](https://huggingface.co//apdcephfs/share_733425/vinnylywang/jianhuipang/opensourcellms/llama2/Llama-2-13b-hf) on the /apdcephfs/share_733425/vinnylywang/jianhuipang/datasets/RedPajama-Data-1T-Sample dataset.
|
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: 2e-05
|
36 |
+
- train_batch_size: 1
|
37 |
+
- eval_batch_size: 1
|
38 |
+
- seed: 34
|
39 |
+
- distributed_type: multi-GPU
|
40 |
+
- num_devices: 32
|
41 |
+
- gradient_accumulation_steps: 16
|
42 |
+
- total_train_batch_size: 512
|
43 |
+
- total_eval_batch_size: 32
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: constant_with_warmup
|
46 |
+
- lr_scheduler_warmup_steps: 20
|
47 |
+
- num_epochs: 1.0
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- Transformers 4.28.0.dev0
|
56 |
+
- Pytorch 1.13.1+cu117
|
57 |
+
- Datasets 2.14.6
|
58 |
+
- Tokenizers 0.13.3
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<AC>": 32001,
|
3 |
+
"[PAD]": 32000
|
4 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.9326286626242646,
|
4 |
+
"train_runtime": 238313.358,
|
5 |
+
"train_samples": 930514,
|
6 |
+
"train_samples_per_second": 3.905,
|
7 |
+
"train_steps_per_second": 0.008
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/apdcephfs/share_733425/vinnylywang/jianhuipang/opensourcellms/llama2/Llama-2-13b-hf",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 5120,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 13824,
|
12 |
+
"max_position_embeddings": 4096,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 40,
|
15 |
+
"num_hidden_layers": 40,
|
16 |
+
"num_key_value_heads": 40,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"pretraining_tp": 1,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.28.0.dev0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32002
|
26 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 4096,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"temperature": 0.6,
|
8 |
+
"top_p": 0.9,
|
9 |
+
"transformers_version": "4.28.0.dev0"
|
10 |
+
}
|
log.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46340cafc0b4f6b66b0d4c4e07ce143209a954bc572928f5ca100106c6b28c65
|
3 |
+
size 26031908973
|
runs/Jan29_09-54-51_ts-cbba87c5e7504a249f5127103d9ce40f-launcher/1706495347.9318979/events.out.tfevents.1706495347.ts-cbba87c5e7504a249f5127103d9ce40f-launcher.48748.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d17d55343f7dda6ddae0154953d72a5b0ede70075cd41de72cc4d4c69f6e4cc
|
3 |
+
size 5996
|
runs/Jan29_09-54-51_ts-cbba87c5e7504a249f5127103d9ce40f-launcher/events.out.tfevents.1706495347.ts-cbba87c5e7504a249f5127103d9ce40f-launcher.48748.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a103fed1924be1d7550061ddbc2a42e2d11590177dd9f35ca048e96d20d6cb4a
|
3 |
+
size 4181
|
runs/Jan29_11-10-29_ts-cbba87c5e7504a249f5127103d9ce40f-launcher/1706499936.7397811/events.out.tfevents.1706499936.ts-cbba87c5e7504a249f5127103d9ce40f-launcher.67020.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee5828628b4763fc165f0b119b438a272e266ce31338f1e19543eeb6e505dc37
|
3 |
+
size 5996
|
runs/Jan29_11-10-29_ts-cbba87c5e7504a249f5127103d9ce40f-launcher/events.out.tfevents.1706499936.ts-cbba87c5e7504a249f5127103d9ce40f-launcher.67020.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9a2d26f6765507e2933a3da43cb5f7680eb8c11a70aedeb02d55e15a0e13f1a
|
3 |
+
size 289424
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"__type": "AddedToken",
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"clean_up_tokenization_spaces": false,
|
11 |
+
"eos_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"legacy": false,
|
20 |
+
"model_max_length": 1000000000000000019884624838656,
|
21 |
+
"pad_token": null,
|
22 |
+
"padding_side": "right",
|
23 |
+
"special_tokens_map_file": "/apdcephfs/share_733425/vinnylywang/jianhuipang/opensourcellms/llama2/Llama-2-13b-hf/special_tokens_map.json",
|
24 |
+
"tokenizer_class": "LlamaTokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.9326286626242646,
|
4 |
+
"train_runtime": 238313.358,
|
5 |
+
"train_samples": 930514,
|
6 |
+
"train_samples_per_second": 3.905,
|
7 |
+
"train_steps_per_second": 0.008
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55a4f3390ca6f85880fbffe616beb0dc09677d11c83800ed180e75e15fc417c4
|
3 |
+
size 4795
|