AvniMittal13
commited on
Commit
•
4d4a343
1
Parent(s):
3e49a24
AvniMittal13/shwartz2_normal
Browse files- README.md +12 -13
- adapter_config.json +2 -3
- adapter_model.safetensors +2 -2
- runs/Sep26_03-39-35_d871e25019a7/events.out.tfevents.1727321981.d871e25019a7.30.0 +3 -0
- runs/Sep26_03-40-21_d871e25019a7/events.out.tfevents.1727322024.d871e25019a7.30.1 +3 -0
- runs/Sep26_03-54-54_307bffa94c34/events.out.tfevents.1727322896.307bffa94c34.30.0 +3 -0
- runs/Sep26_04-13-03_aad8fdad577d/events.out.tfevents.1727323985.aad8fdad577d.30.0 +3 -0
- runs/Sep26_04-15-39_aad8fdad577d/events.out.tfevents.1727324143.aad8fdad577d.30.1 +3 -0
- runs/Sep26_04-20-40_9b7b186f542d/events.out.tfevents.1727324590.9b7b186f542d.30.0 +3 -0
- tokenizer.json +0 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 1.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -38,11 +38,9 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0001
|
41 |
-
- train_batch_size:
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
-
- gradient_accumulation_steps: 4
|
45 |
-
- total_train_batch_size: 16
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
- lr_scheduler_warmup_ratio: 0.05
|
@@ -51,18 +49,19 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss | Epoch
|
55 |
-
|
56 |
-
|
|
57 |
-
| 1.
|
58 |
-
| 1.
|
59 |
-
| 1.
|
|
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
- PEFT 0.13.1.dev0
|
65 |
-
- Transformers 4.
|
66 |
-
- Pytorch 2.4.
|
67 |
- Datasets 3.0.0
|
68 |
-
- Tokenizers 0.
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.4782
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 1
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
|
|
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: cosine
|
46 |
- lr_scheduler_warmup_ratio: 0.05
|
|
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 1.71 | 0.4 | 200 | 1.4977 |
|
55 |
+
| 1.7529 | 0.8 | 400 | 1.4883 |
|
56 |
+
| 1.1946 | 1.2 | 600 | 1.4800 |
|
57 |
+
| 1.6962 | 1.6 | 800 | 1.4786 |
|
58 |
+
| 1.1067 | 2.0 | 1000 | 1.4782 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
- PEFT 0.13.1.dev0
|
64 |
+
- Transformers 4.44.2
|
65 |
+
- Pytorch 2.4.0
|
66 |
- Datasets 3.0.0
|
67 |
+
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -16,13 +16,12 @@
|
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
"k_proj",
|
25 |
-
"
|
26 |
"v_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
|
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 4,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"k_proj",
|
24 |
+
"q_proj",
|
25 |
"v_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
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:cb5d11f068d9010e806527241c8d42aca2d4ee94afc6478598e9851df4cfc374
|
3 |
+
size 7889592
|
runs/Sep26_03-39-35_d871e25019a7/events.out.tfevents.1727321981.d871e25019a7.30.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e87f9866f4801f995b1346a788858e088b9f090a98bf27fab400dde0c6ece06b
|
3 |
+
size 4184
|
runs/Sep26_03-40-21_d871e25019a7/events.out.tfevents.1727322024.d871e25019a7.30.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60102720cc597e6df9da152c7ad6d327108c65464914d57f5242d75e5227584b
|
3 |
+
size 4184
|
runs/Sep26_03-54-54_307bffa94c34/events.out.tfevents.1727322896.307bffa94c34.30.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bbffc8e1aacb28942516a7c3372f841c5df4ebff8c1789269cb6722ec4168ac
|
3 |
+
size 4184
|
runs/Sep26_04-13-03_aad8fdad577d/events.out.tfevents.1727323985.aad8fdad577d.30.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3777c5239006c004fc83a1a6c64b033f3ac76028c9b3b4ba43320297ec988c7a
|
3 |
+
size 5318
|
runs/Sep26_04-15-39_aad8fdad577d/events.out.tfevents.1727324143.aad8fdad577d.30.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa3501dfd336fe3851fc2af92d468c3b6b02cde8d49684b1c00b048fb929e62b
|
3 |
+
size 4184
|
runs/Sep26_04-20-40_9b7b186f542d/events.out.tfevents.1727324590.9b7b186f542d.30.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:986b86b3361a3fe2ca3c88f5a8a9438ed0a5657186a9cfceb36bdd8f8066c7c1
|
3 |
+
size 217519
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
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 sha256:3ce4ef602c582e23b22f85b2b957ec0b22b2ba87ce4f7cce11f0737541d6572d
|
3 |
+
size 5432
|