End of training
Browse files
README.md
CHANGED
@@ -1,13 +1,14 @@
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
-
|
|
|
4 |
tags:
|
5 |
- axolotl
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
-
- Aivesa/
|
9 |
model-index:
|
10 |
-
- name:
|
11 |
results: []
|
12 |
---
|
13 |
|
@@ -20,18 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
axolotl version: `0.6.0`
|
21 |
```yaml
|
22 |
adapter: lora
|
23 |
-
base_model:
|
24 |
bf16: auto
|
25 |
chat_template: llama3
|
26 |
dataset_prepared_path: /workspace/axolotl/data/prepared
|
27 |
datasets:
|
28 |
- ds_type: json
|
29 |
format: custom
|
30 |
-
path: Aivesa/
|
31 |
type:
|
32 |
-
|
33 |
-
|
34 |
-
field_output: caption
|
35 |
system_format: '{system}'
|
36 |
system_prompt: ''
|
37 |
debug: null
|
@@ -47,7 +47,7 @@ fsdp_config: null
|
|
47 |
gradient_accumulation_steps: 4
|
48 |
gradient_checkpointing: false
|
49 |
group_by_length: false
|
50 |
-
hub_model_id: Aivesa/
|
51 |
hub_private_repo: true
|
52 |
hub_repo: null
|
53 |
hub_strategy: checkpoint
|
@@ -89,10 +89,10 @@ use_accelerate: true
|
|
89 |
val_set_size: 0.05
|
90 |
wandb_entity: null
|
91 |
wandb_mode: online
|
92 |
-
wandb_name:
|
93 |
wandb_project: Gradients-On-Demand
|
94 |
wandb_run: your_name
|
95 |
-
wandb_runid:
|
96 |
warmup_steps: 10
|
97 |
weight_decay: 0.0
|
98 |
xformers_attention: null
|
@@ -101,11 +101,11 @@ xformers_attention: null
|
|
101 |
|
102 |
</details><br>
|
103 |
|
104 |
-
#
|
105 |
|
106 |
-
This model is a fine-tuned version of [
|
107 |
It achieves the following results on the evaluation set:
|
108 |
-
- Loss:
|
109 |
|
110 |
## Model description
|
111 |
|
@@ -139,9 +139,9 @@ The following hyperparameters were used during training:
|
|
139 |
|
140 |
| Training Loss | Epoch | Step | Validation Loss |
|
141 |
|:-------------:|:------:|:----:|:---------------:|
|
142 |
-
|
|
143 |
-
|
|
144 |
-
|
|
145 |
|
146 |
|
147 |
### Framework versions
|
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: EleutherAI/pythia-70m-deduped
|
5 |
tags:
|
6 |
- axolotl
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
+
- Aivesa/dataset_999dc897-8e91-4324-92d7-b71af8c08912
|
10 |
model-index:
|
11 |
+
- name: f8549911-86bb-4e2b-8478-525efbbc4415
|
12 |
results: []
|
13 |
---
|
14 |
|
|
|
21 |
axolotl version: `0.6.0`
|
22 |
```yaml
|
23 |
adapter: lora
|
24 |
+
base_model: EleutherAI/pythia-70m-deduped
|
25 |
bf16: auto
|
26 |
chat_template: llama3
|
27 |
dataset_prepared_path: /workspace/axolotl/data/prepared
|
28 |
datasets:
|
29 |
- ds_type: json
|
30 |
format: custom
|
31 |
+
path: Aivesa/dataset_999dc897-8e91-4324-92d7-b71af8c08912
|
32 |
type:
|
33 |
+
field_instruction: pageTitle
|
34 |
+
field_output: output
|
|
|
35 |
system_format: '{system}'
|
36 |
system_prompt: ''
|
37 |
debug: null
|
|
|
47 |
gradient_accumulation_steps: 4
|
48 |
gradient_checkpointing: false
|
49 |
group_by_length: false
|
50 |
+
hub_model_id: Aivesa/f8549911-86bb-4e2b-8478-525efbbc4415
|
51 |
hub_private_repo: true
|
52 |
hub_repo: null
|
53 |
hub_strategy: checkpoint
|
|
|
89 |
val_set_size: 0.05
|
90 |
wandb_entity: null
|
91 |
wandb_mode: online
|
92 |
+
wandb_name: 999dc897-8e91-4324-92d7-b71af8c08912
|
93 |
wandb_project: Gradients-On-Demand
|
94 |
wandb_run: your_name
|
95 |
+
wandb_runid: 999dc897-8e91-4324-92d7-b71af8c08912
|
96 |
warmup_steps: 10
|
97 |
weight_decay: 0.0
|
98 |
xformers_attention: null
|
|
|
101 |
|
102 |
</details><br>
|
103 |
|
104 |
+
# f8549911-86bb-4e2b-8478-525efbbc4415
|
105 |
|
106 |
+
This model is a fine-tuned version of [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) on the Aivesa/dataset_999dc897-8e91-4324-92d7-b71af8c08912 dataset.
|
107 |
It achieves the following results on the evaluation set:
|
108 |
+
- Loss: 182.5955
|
109 |
|
110 |
## Model description
|
111 |
|
|
|
139 |
|
140 |
| Training Loss | Epoch | Step | Validation Loss |
|
141 |
|:-------------:|:------:|:----:|:---------------:|
|
142 |
+
| 575.7077 | 0.0003 | 3 | 182.7351 |
|
143 |
+
| 962.5692 | 0.0006 | 6 | 182.6678 |
|
144 |
+
| 537.9006 | 0.0009 | 9 | 182.5955 |
|
145 |
|
146 |
|
147 |
### Framework versions
|