Model save
Browse files
README.md
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
model-index:
|
7 |
- name: phi-2-finetuned
|
8 |
results: []
|
@@ -33,12 +34,15 @@ More information needed
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 0.0002
|
36 |
-
- train_batch_size:
|
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: constant
|
41 |
-
-
|
|
|
42 |
|
43 |
### Training results
|
44 |
|
@@ -46,7 +50,8 @@ The following hyperparameters were used during training:
|
|
46 |
|
47 |
### Framework versions
|
48 |
|
49 |
-
-
|
|
|
50 |
- Pytorch 2.1.0+cu121
|
51 |
- Datasets 2.16.1
|
52 |
-
- Tokenizers 0.15.0
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
base_model: microsoft/phi-2
|
7 |
model-index:
|
8 |
- name: phi-2-finetuned
|
9 |
results: []
|
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 0.0002
|
37 |
+
- train_batch_size: 8
|
38 |
- eval_batch_size: 8
|
39 |
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 4
|
41 |
+
- total_train_batch_size: 32
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: constant
|
44 |
+
- lr_scheduler_warmup_ratio: 0.03
|
45 |
+
- num_epochs: 20
|
46 |
|
47 |
### Training results
|
48 |
|
|
|
50 |
|
51 |
### Framework versions
|
52 |
|
53 |
+
- PEFT 0.7.1
|
54 |
+
- Transformers 4.36.0
|
55 |
- Pytorch 2.1.0+cu121
|
56 |
- Datasets 2.16.1
|
57 |
+
- Tokenizers 0.15.0
|
adapter_config.json
CHANGED
@@ -9,18 +9,23 @@
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
-
"lora_alpha":
|
13 |
"lora_dropout": 0.1,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
-
"r":
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
|
|
|
|
|
|
|
|
|
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
"lora_dropout": 0.1,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"fc1",
|
23 |
+
"lm_head",
|
24 |
+
"fc2",
|
25 |
+
"k_proj",
|
26 |
+
"q_proj",
|
27 |
+
"v_proj",
|
28 |
+
"o_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6138b3893e6e44c9fe18b3f0aebcb7b4c4214d1d5beaae8ec322c75312525af0
|
3 |
+
size 347895224
|
runs/Jan12_04-01-39_b3be375e58ed/events.out.tfevents.1705032105.b3be375e58ed.157.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5289985b3ddd04836ed15b8b563425ae2bc87a523e81e35381a556e6c1352094
|
3 |
+
size 5549
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b7c8bb8d4339fa7bfee37f1783b0e8244d19d07328a7beb9d45a5fe4df442b6
|
3 |
+
size 4728
|