Jlonge4/outputs
Browse files- README.md +29 -37
- adapter_config.json +7 -7
- adapter_model.safetensors +1 -1
- runs/Sep08_03-30-31_111903198ea6/events.out.tfevents.1725766233.111903198ea6.3278.0 +3 -0
- tokenizer.json +6 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -14,30 +14,12 @@ model-index:
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/
|
18 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
|
19 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
|
20 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
|
21 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
|
22 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
|
23 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
|
24 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
|
25 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
|
26 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
|
27 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/dtvgakdw)
|
28 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/9hr7jcal)
|
29 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/goc9hcye)
|
30 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/fzw32mg0)
|
31 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/fzw32mg0)
|
32 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/fzw32mg0)
|
33 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/dphr4egm)
|
34 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/dphr4egm)
|
35 |
-
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/dphr4egm)
|
36 |
# outputs
|
37 |
|
38 |
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
-
- Loss: 1.
|
41 |
|
42 |
## Model description
|
43 |
|
@@ -65,28 +47,38 @@ The following hyperparameters were used during training:
|
|
65 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
66 |
- lr_scheduler_type: cosine_with_restarts
|
67 |
- lr_scheduler_warmup_steps: 20
|
68 |
-
- training_steps:
|
69 |
|
70 |
### Training results
|
71 |
|
72 |
| Training Loss | Epoch | Step | Validation Loss |
|
73 |
|:-------------:|:-------:|:----:|:---------------:|
|
74 |
-
|
|
75 |
-
| 1.
|
76 |
-
|
|
77 |
-
|
|
78 |
-
|
|
79 |
-
| 0.
|
80 |
-
|
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
90 |
|
91 |
|
92 |
### Framework versions
|
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
[<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/josh-longenecker1-groundedai/phi3.5-hallucination/runs/vn7nj2r3)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
# outputs
|
19 |
|
20 |
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.5219
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: cosine_with_restarts
|
49 |
- lr_scheduler_warmup_steps: 20
|
50 |
+
- training_steps: 260
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
|:-------------:|:-------:|:----:|:---------------:|
|
56 |
+
| 1.8679 | 1.1429 | 10 | 2.0237 |
|
57 |
+
| 1.3961 | 2.2857 | 20 | 1.5707 |
|
58 |
+
| 0.939 | 3.4286 | 30 | 1.1184 |
|
59 |
+
| 0.9957 | 4.5714 | 40 | 0.9883 |
|
60 |
+
| 0.8836 | 5.7143 | 50 | 0.9527 |
|
61 |
+
| 0.8069 | 6.8571 | 60 | 0.9431 |
|
62 |
+
| 0.6692 | 8.0 | 70 | 0.9416 |
|
63 |
+
| 0.7691 | 9.1429 | 80 | 0.9574 |
|
64 |
+
| 0.5804 | 10.2857 | 90 | 0.9505 |
|
65 |
+
| 0.395 | 11.4286 | 100 | 0.9772 |
|
66 |
+
| 0.3864 | 12.5714 | 110 | 1.0155 |
|
67 |
+
| 0.3433 | 13.7143 | 120 | 1.0573 |
|
68 |
+
| 0.4332 | 14.8571 | 130 | 1.0832 |
|
69 |
+
| 0.224 | 16.0 | 140 | 1.1592 |
|
70 |
+
| 0.1891 | 17.1429 | 150 | 1.2302 |
|
71 |
+
| 0.2235 | 18.2857 | 160 | 1.2603 |
|
72 |
+
| 0.1925 | 19.4286 | 170 | 1.3136 |
|
73 |
+
| 0.2264 | 20.5714 | 180 | 1.3556 |
|
74 |
+
| 0.1491 | 21.7143 | 190 | 1.4057 |
|
75 |
+
| 0.2421 | 22.8571 | 200 | 1.4966 |
|
76 |
+
| 0.1515 | 24.0 | 210 | 1.4495 |
|
77 |
+
| 0.1349 | 25.1429 | 220 | 1.5144 |
|
78 |
+
| 0.1493 | 26.2857 | 230 | 1.5340 |
|
79 |
+
| 0.1202 | 27.4286 | 240 | 1.5201 |
|
80 |
+
| 0.1154 | 28.5714 | 250 | 1.5305 |
|
81 |
+
| 0.1968 | 29.7143 | 260 | 1.5219 |
|
82 |
|
83 |
|
84 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -10,8 +10,8 @@
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
-
"lora_alpha":
|
14 |
-
"lora_dropout": 0.
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
@@ -21,12 +21,12 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"up_proj",
|
24 |
-
"v_proj",
|
25 |
-
"q_proj",
|
26 |
-
"o_proj",
|
27 |
-
"down_proj",
|
28 |
"k_proj",
|
29 |
-
"
|
|
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
+
"lora_alpha": 128,
|
14 |
+
"lora_dropout": 0.2,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"up_proj",
|
|
|
|
|
|
|
|
|
24 |
"k_proj",
|
25 |
+
"down_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"o_proj",
|
28 |
+
"q_proj",
|
29 |
+
"v_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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 142623480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c47f5b555306903f26770a32ba84cdb3afdda4a92f30a5a6a0a28d0268ee956e
|
3 |
size 142623480
|
runs/Sep08_03-30-31_111903198ea6/events.out.tfevents.1725766233.111903198ea6.3278.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91b014a21f74d49994be6a5f24ef4ae210a8bf47f20d7fe50d05847e4d52c272
|
3 |
+
size 69780
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68156363a28ce3d23f4f6fe3990ca6cd67bf6b5e851dc870c0ea8fd2a80adf41
|
3 |
size 5432
|