End of training
Browse files- README.md +58 -0
- adapter_config.json +27 -0
- adapter_model.safetensors +3 -0
- runs/Jan25_21-21-32_ea1ae1bcc730/events.out.tfevents.1706217720.ea1ae1bcc730.1199.0 +3 -0
- runs/Jan25_21-21-32_ea1ae1bcc730/events.out.tfevents.1706217749.ea1ae1bcc730.1199.1 +3 -0
- runs/Jan25_21-21-32_ea1ae1bcc730/events.out.tfevents.1706217858.ea1ae1bcc730.1199.2 +3 -0
- runs/Jan25_21-27-44_ea1ae1bcc730/events.out.tfevents.1706218067.ea1ae1bcc730.1199.3 +3 -0
- runs/Jan25_21-27-44_ea1ae1bcc730/events.out.tfevents.1706218261.ea1ae1bcc730.1199.4 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: lrds-code/samba-1.1B
|
7 |
+
model-index:
|
8 |
+
- name: outputs
|
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 |
+
# outputs
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [lrds-code/samba-1.1B](https://huggingface.co/lrds-code/samba-1.1B) 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: 0.0002
|
37 |
+
- train_batch_size: 2
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 8
|
41 |
+
- total_train_batch_size: 16
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 2
|
45 |
+
- num_epochs: 1
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- PEFT 0.7.2.dev0
|
55 |
+
- Transformers 4.38.0.dev0
|
56 |
+
- Pytorch 2.1.0+cu121
|
57 |
+
- Datasets 2.16.1
|
58 |
+
- Tokenizers 0.15.1
|
adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "lrds-code/samba-1.1B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"gate_proj",
|
23 |
+
"up_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c2fb57eb07e67a530d1eaa7613b9994bf96656637131e9b2d83c030f956903b
|
3 |
+
size 10824696
|
runs/Jan25_21-21-32_ea1ae1bcc730/events.out.tfevents.1706217720.ea1ae1bcc730.1199.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa31b53d5f8deeb76672e74f9d235bc53c8acb027e58f39b64ab6bc9006733ce
|
3 |
+
size 4792
|
runs/Jan25_21-21-32_ea1ae1bcc730/events.out.tfevents.1706217749.ea1ae1bcc730.1199.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e9f39dbb5112017dd2ec5cdaa8542c717183917d6b84a3f42f2a43b5b028304
|
3 |
+
size 4792
|
runs/Jan25_21-21-32_ea1ae1bcc730/events.out.tfevents.1706217858.ea1ae1bcc730.1199.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4042953149e1d0318b74e0ce9614a0355bed9698040d0e6d4dba05ae6a4b21d8
|
3 |
+
size 4792
|
runs/Jan25_21-27-44_ea1ae1bcc730/events.out.tfevents.1706218067.ea1ae1bcc730.1199.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:596a331ffee03b6026e110f495a0c72b7680b8468c1844018f458292c4c22d9d
|
3 |
+
size 4790
|
runs/Jan25_21-27-44_ea1ae1bcc730/events.out.tfevents.1706218261.ea1ae1bcc730.1199.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1fcc9e3246c07f5afe464612462b789fccf73666a5e45db6281ca00bb84fff7
|
3 |
+
size 13762
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:824cf0808538616442d50307bf71e35dde0ea05bbd2d2a657d10138268ea5e6e
|
3 |
+
size 4728
|