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 +21,18 @@ 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 |
-
field_input:
|
33 |
-
field_instruction:
|
34 |
-
field_output:
|
35 |
system_format: '{system}'
|
36 |
system_prompt: ''
|
37 |
debug: null
|
@@ -47,7 +48,7 @@ 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
|
@@ -87,10 +88,10 @@ use_accelerate: true
|
|
87 |
val_set_size: 0.05
|
88 |
wandb_entity: null
|
89 |
wandb_mode: online
|
90 |
-
wandb_name:
|
91 |
wandb_project: Gradients-On-Demand
|
92 |
wandb_run: your_name
|
93 |
-
wandb_runid:
|
94 |
warmup_steps: 10
|
95 |
weight_decay: 0.0
|
96 |
xformers_attention: null
|
@@ -99,11 +100,11 @@ xformers_attention: null
|
|
99 |
|
100 |
</details><br>
|
101 |
|
102 |
-
#
|
103 |
|
104 |
-
This model is a fine-tuned version of [
|
105 |
It achieves the following results on the evaluation set:
|
106 |
-
- Loss:
|
107 |
|
108 |
## Model description
|
109 |
|
@@ -137,9 +138,9 @@ The following hyperparameters were used during training:
|
|
137 |
|
138 |
| Training Loss | Epoch | Step | Validation Loss |
|
139 |
|:-------------:|:------:|:----:|:---------------:|
|
140 |
-
|
|
141 |
-
|
|
142 |
-
|
|
143 |
|
144 |
|
145 |
### Framework versions
|
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: unsloth/gemma-1.1-2b-it
|
5 |
tags:
|
6 |
- axolotl
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
+
- Aivesa/dataset_10c4ef31-0fc3-4816-b201-f9aacd17dea9
|
10 |
model-index:
|
11 |
+
- name: 8cab53b2-556d-49e0-8244-ccfc9d241733
|
12 |
results: []
|
13 |
---
|
14 |
|
|
|
21 |
axolotl version: `0.6.0`
|
22 |
```yaml
|
23 |
adapter: lora
|
24 |
+
base_model: unsloth/gemma-1.1-2b-it
|
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_10c4ef31-0fc3-4816-b201-f9aacd17dea9
|
32 |
type:
|
33 |
+
field_input: whole_func_string
|
34 |
+
field_instruction: func_name
|
35 |
+
field_output: func_documentation_string
|
36 |
system_format: '{system}'
|
37 |
system_prompt: ''
|
38 |
debug: null
|
|
|
48 |
gradient_accumulation_steps: 4
|
49 |
gradient_checkpointing: false
|
50 |
group_by_length: false
|
51 |
+
hub_model_id: Aivesa/8cab53b2-556d-49e0-8244-ccfc9d241733
|
52 |
hub_private_repo: true
|
53 |
hub_repo: null
|
54 |
hub_strategy: checkpoint
|
|
|
88 |
val_set_size: 0.05
|
89 |
wandb_entity: null
|
90 |
wandb_mode: online
|
91 |
+
wandb_name: 10c4ef31-0fc3-4816-b201-f9aacd17dea9
|
92 |
wandb_project: Gradients-On-Demand
|
93 |
wandb_run: your_name
|
94 |
+
wandb_runid: 10c4ef31-0fc3-4816-b201-f9aacd17dea9
|
95 |
warmup_steps: 10
|
96 |
weight_decay: 0.0
|
97 |
xformers_attention: null
|
|
|
100 |
|
101 |
</details><br>
|
102 |
|
103 |
+
# 8cab53b2-556d-49e0-8244-ccfc9d241733
|
104 |
|
105 |
+
This model is a fine-tuned version of [unsloth/gemma-1.1-2b-it](https://huggingface.co/unsloth/gemma-1.1-2b-it) on the Aivesa/dataset_10c4ef31-0fc3-4816-b201-f9aacd17dea9 dataset.
|
106 |
It achieves the following results on the evaluation set:
|
107 |
+
- Loss: 0.1719
|
108 |
|
109 |
## Model description
|
110 |
|
|
|
138 |
|
139 |
| Training Loss | Epoch | Step | Validation Loss |
|
140 |
|:-------------:|:------:|:----:|:---------------:|
|
141 |
+
| 0.7611 | 0.0002 | 3 | 0.9646 |
|
142 |
+
| 0.4984 | 0.0004 | 6 | 0.5004 |
|
143 |
+
| 0.2296 | 0.0007 | 9 | 0.1719 |
|
144 |
|
145 |
|
146 |
### Framework versions
|