Commit
•
a2d9b19
1
Parent(s):
ee2f440
End of training
Browse files- README.md +51 -0
- config.json +33 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- runs/Dec16_18-59-21_5c865fdaac76/events.out.tfevents.1702753176.5c865fdaac76.1170.0 +3 -0
- runs/Dec16_19-02-14_5c865fdaac76/events.out.tfevents.1702753338.5c865fdaac76.1170.1 +3 -0
- runs/Dec16_19-09-23_5c865fdaac76/events.out.tfevents.1702753781.5c865fdaac76.1170.2 +3 -0
- runs/Dec16_19-10-15_5c865fdaac76/events.out.tfevents.1702753828.5c865fdaac76.1170.3 +3 -0
- runs/Dec16_19-10-15_5c865fdaac76/events.out.tfevents.1702753881.5c865fdaac76.1170.4 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: bigscience-bloom-rail-1.0
|
3 |
+
base_model: bigscience/bloomz-560m
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: BLOOM560mfinetune
|
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 |
+
# BLOOM560mfinetune
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on an unknown 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: 5
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 2
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.35.2
|
50 |
+
- Pytorch 2.1.0+cu121
|
51 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigscience/bloomz-560m",
|
3 |
+
"apply_residual_connection_post_layernorm": false,
|
4 |
+
"architectures": [
|
5 |
+
"BloomForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"attention_softmax_in_fp32": true,
|
9 |
+
"bias_dropout_fusion": true,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"masked_softmax_fusion": true,
|
17 |
+
"model_type": "bloom",
|
18 |
+
"n_head": 16,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 24,
|
21 |
+
"offset_alibi": 100,
|
22 |
+
"pad_token_id": 3,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"seq_length": 2048,
|
25 |
+
"skip_bias_add": true,
|
26 |
+
"skip_bias_add_qkv": false,
|
27 |
+
"slow_but_exact": false,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.35.2",
|
30 |
+
"unk_token_id": 0,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 250880
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.35.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e5f61fbbfd5dd09a703695971850088e7f6f4f4478493726eb2a18b447cd38e
|
3 |
+
size 2236892304
|
runs/Dec16_18-59-21_5c865fdaac76/events.out.tfevents.1702753176.5c865fdaac76.1170.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a396992f7649f9d38238e787a645c72ade5a458c8081ae740f43314261c93c6b
|
3 |
+
size 4325
|
runs/Dec16_19-02-14_5c865fdaac76/events.out.tfevents.1702753338.5c865fdaac76.1170.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c18a2ffa2dedc6e560844ee310ad9e573e479a4a81cba36dbc4526957b9c6843
|
3 |
+
size 4325
|
runs/Dec16_19-09-23_5c865fdaac76/events.out.tfevents.1702753781.5c865fdaac76.1170.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24e390ceff93bc1136c9376fd4696d477480e8ea9ded3b25ded0073cbd222f77
|
3 |
+
size 4348
|
runs/Dec16_19-10-15_5c865fdaac76/events.out.tfevents.1702753828.5c865fdaac76.1170.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:368a10dca87875f3ef8ada810114731a54554054ec5b46936f190ee1f71373d8
|
3 |
+
size 4348
|
runs/Dec16_19-10-15_5c865fdaac76/events.out.tfevents.1702753881.5c865fdaac76.1170.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3df52e8b973c7d1a5f94a21fe3b16e178ded492c0aa35ff3a528bc06d50ed7a9
|
3 |
+
size 4859
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4300c248e1b3d2b373ab8874b1a2de6586588c9953bf5250665c26a7dc538bf2
|
3 |
+
size 4600
|