Commit
•
52e5c95
1
Parent(s):
e439102
ashishpatel26/opt-6.1b-lora
Browse files
README.md
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
base_model:
|
7 |
model-index:
|
8 |
- name: outputs
|
9 |
results: []
|
@@ -12,10 +12,10 @@ model-index:
|
|
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 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/carlosslocar0/huggingface/runs/
|
16 |
# outputs
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -44,6 +44,7 @@ The following hyperparameters were used during training:
|
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 100
|
46 |
- training_steps: 200
|
|
|
47 |
|
48 |
### Training results
|
49 |
|
|
|
1 |
---
|
2 |
+
license: other
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
base_model: facebook/opt-1.3b
|
7 |
model-index:
|
8 |
- name: outputs
|
9 |
results: []
|
|
|
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 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/carlosslocar0/huggingface/runs/rdwmof3i)
|
16 |
# outputs
|
17 |
|
18 |
+
This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 100
|
46 |
- training_steps: 200
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -20,7 +20,8 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
|
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"use_dora": false,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "facebook/opt-1.3b",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
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 sha256:4bb847ea1a78da7669b6295d4517b8500df31886a57ed891a3ec0ee148305c52
|
3 |
+
size 12596472
|
runs/May25_06-33-52_e3a9dd922337/events.out.tfevents.1716618833.e3a9dd922337.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34a7b14cf2dd062b9c898244402325b1fdf287a91ae4aae559f22de82888a5fd
|
3 |
+
size 7406
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a58c776d266c43c01f78e07822ddd4c9edc97de5c899411955ee81e149b4ca9
|
3 |
size 5112
|