End of training
Browse files
README.md
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
-
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: phi-1_5-finetuned
|
| 8 |
results: []
|
|
@@ -13,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# phi-1_5-finetuned
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -42,13 +43,10 @@ The following hyperparameters were used during training:
|
|
| 42 |
- lr_scheduler_type: cosine
|
| 43 |
- num_epochs: 1
|
| 44 |
|
| 45 |
-
### Training results
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
-
-
|
| 52 |
-
-
|
| 53 |
-
-
|
| 54 |
-
-
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
base_model: microsoft/phi-1_5
|
| 7 |
model-index:
|
| 8 |
- name: phi-1_5-finetuned
|
| 9 |
results: []
|
|
|
|
| 14 |
|
| 15 |
# phi-1_5-finetuned
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 43 |
- lr_scheduler_type: cosine
|
| 44 |
- num_epochs: 1
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
+
- PEFT 0.9.0
|
| 49 |
+
- Transformers 4.37.1
|
| 50 |
+
- Pytorch 2.2.0+cu121
|
| 51 |
+
- Datasets 2.16.1
|
| 52 |
+
- Tokenizers 0.15.1
|
adapter_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"auto_mapping": null,
|
| 3 |
"base_model_name_or_path": "microsoft/phi-1_5",
|
| 4 |
"bias": "none",
|
|
@@ -7,17 +8,23 @@
|
|
| 7 |
"init_lora_weights": true,
|
| 8 |
"layers_pattern": null,
|
| 9 |
"layers_to_transform": null,
|
|
|
|
| 10 |
"lora_alpha": 16,
|
| 11 |
"lora_dropout": 0.05,
|
|
|
|
|
|
|
| 12 |
"modules_to_save": null,
|
| 13 |
"peft_type": "LORA",
|
| 14 |
"r": 16,
|
|
|
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
-
"fc1",
|
| 18 |
-
"fc2",
|
| 19 |
"Wqkv",
|
| 20 |
-
"
|
|
|
|
|
|
|
| 21 |
],
|
| 22 |
-
"task_type": "CAUSAL_LM"
|
|
|
|
|
|
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "microsoft/phi-1_5",
|
| 5 |
"bias": "none",
|
|
|
|
| 8 |
"init_lora_weights": true,
|
| 9 |
"layers_pattern": null,
|
| 10 |
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
"lora_alpha": 16,
|
| 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": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
|
|
|
| 22 |
"Wqkv",
|
| 23 |
+
"fc2",
|
| 24 |
+
"out_proj",
|
| 25 |
+
"fc1"
|
| 26 |
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_dora": false,
|
| 29 |
+
"use_rslora": false
|
| 30 |
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc513b8c6b41d16869d641fec9704e323bddcb10a506431decebbf8200035cc6
|
| 3 |
+
size 31469312
|
runs/Mar05_16-31-53_LAPTOP-FBJ6NMBP/events.out.tfevents.1709636513.LAPTOP-FBJ6NMBP.15160.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8a91c194f0351c70e4979fd45bfa5e135af6855979fc9585705ff471ff953fa
|
| 3 |
+
size 7764
|
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 sha256:698c6d8b4714b7beb79cd5b6fcf81c71be17babce2cf45231fd2a55d645d9d58
|
| 3 |
+
size 4728
|