End of training
Browse files- README.md +21 -23
- adapter_model.bin +2 -2
README.md
CHANGED
@@ -4,9 +4,9 @@ library_name: peft
|
|
4 |
tags:
|
5 |
- axolotl
|
6 |
- generated_from_trainer
|
7 |
-
base_model:
|
8 |
model-index:
|
9 |
-
- name:
|
10 |
results: []
|
11 |
---
|
12 |
|
@@ -19,19 +19,19 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
axolotl version: `0.4.1`
|
20 |
```yaml
|
21 |
adapter: lora
|
22 |
-
base_model:
|
23 |
bf16: auto
|
24 |
datasets:
|
25 |
- data_files:
|
26 |
-
-
|
27 |
ds_type: json
|
28 |
format: custom
|
29 |
-
path:
|
30 |
type:
|
31 |
field: null
|
32 |
-
field_input:
|
33 |
-
field_instruction:
|
34 |
-
field_output:
|
35 |
field_system: null
|
36 |
format: null
|
37 |
no_input_format: null
|
@@ -51,7 +51,7 @@ fsdp_config: null
|
|
51 |
gradient_accumulation_steps: 4
|
52 |
gradient_checkpointing: true
|
53 |
group_by_length: false
|
54 |
-
hub_model_id: FatCat87/
|
55 |
learning_rate: 0.0002
|
56 |
load_in_4bit: false
|
57 |
load_in_8bit: true
|
@@ -73,8 +73,7 @@ sample_packing: true
|
|
73 |
saves_per_epoch: 1
|
74 |
seed: 701
|
75 |
sequence_len: 4096
|
76 |
-
special_tokens:
|
77 |
-
pad_token: </s>
|
78 |
strict: false
|
79 |
tf32: false
|
80 |
tokenizer_type: AutoTokenizer
|
@@ -83,9 +82,9 @@ val_set_size: 0.1
|
|
83 |
wandb_entity: fatcat87-taopanda
|
84 |
wandb_log_model: null
|
85 |
wandb_mode: online
|
86 |
-
wandb_name:
|
87 |
wandb_project: subnet56
|
88 |
-
wandb_runid:
|
89 |
wandb_watch: null
|
90 |
warmup_ratio: 0.05
|
91 |
weight_decay: 0.0
|
@@ -95,12 +94,12 @@ xformers_attention: null
|
|
95 |
|
96 |
</details><br>
|
97 |
|
98 |
-
[<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/fatcat87-taopanda/subnet56/runs/
|
99 |
-
#
|
100 |
|
101 |
-
This model is a fine-tuned version of [
|
102 |
It achieves the following results on the evaluation set:
|
103 |
-
- Loss:
|
104 |
|
105 |
## Model description
|
106 |
|
@@ -130,18 +129,17 @@ The following hyperparameters were used during training:
|
|
130 |
- total_eval_batch_size: 4
|
131 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
132 |
- lr_scheduler_type: cosine
|
133 |
-
- lr_scheduler_warmup_steps:
|
134 |
- num_epochs: 1
|
135 |
|
136 |
### Training results
|
137 |
|
138 |
| Training Loss | Epoch | Step | Validation Loss |
|
139 |
|:-------------:|:------:|:----:|:---------------:|
|
140 |
-
|
|
141 |
-
|
|
142 |
-
|
|
143 |
-
|
|
144 |
-
| 2.6571 | 0.9846 | 32 | 2.7122 |
|
145 |
|
146 |
|
147 |
### Framework versions
|
|
|
4 |
tags:
|
5 |
- axolotl
|
6 |
- generated_from_trainer
|
7 |
+
base_model: unsloth/Qwen2.5-0.5B-Instruct
|
8 |
model-index:
|
9 |
+
- name: f2c37cd7-d8ff-4753-9fa2-fd45b186c216
|
10 |
results: []
|
11 |
---
|
12 |
|
|
|
19 |
axolotl version: `0.4.1`
|
20 |
```yaml
|
21 |
adapter: lora
|
22 |
+
base_model: unsloth/Qwen2.5-0.5B-Instruct
|
23 |
bf16: auto
|
24 |
datasets:
|
25 |
- data_files:
|
26 |
+
- 8a7bfa6a070007c1_train_data.json
|
27 |
ds_type: json
|
28 |
format: custom
|
29 |
+
path: 8a7bfa6a070007c1_train_data.json
|
30 |
type:
|
31 |
field: null
|
32 |
+
field_input: null
|
33 |
+
field_instruction: question
|
34 |
+
field_output: answer
|
35 |
field_system: null
|
36 |
format: null
|
37 |
no_input_format: null
|
|
|
51 |
gradient_accumulation_steps: 4
|
52 |
gradient_checkpointing: true
|
53 |
group_by_length: false
|
54 |
+
hub_model_id: FatCat87/f2c37cd7-d8ff-4753-9fa2-fd45b186c216
|
55 |
learning_rate: 0.0002
|
56 |
load_in_4bit: false
|
57 |
load_in_8bit: true
|
|
|
73 |
saves_per_epoch: 1
|
74 |
seed: 701
|
75 |
sequence_len: 4096
|
76 |
+
special_tokens: null
|
|
|
77 |
strict: false
|
78 |
tf32: false
|
79 |
tokenizer_type: AutoTokenizer
|
|
|
82 |
wandb_entity: fatcat87-taopanda
|
83 |
wandb_log_model: null
|
84 |
wandb_mode: online
|
85 |
+
wandb_name: f2c37cd7-d8ff-4753-9fa2-fd45b186c216
|
86 |
wandb_project: subnet56
|
87 |
+
wandb_runid: f2c37cd7-d8ff-4753-9fa2-fd45b186c216
|
88 |
wandb_watch: null
|
89 |
warmup_ratio: 0.05
|
90 |
weight_decay: 0.0
|
|
|
94 |
|
95 |
</details><br>
|
96 |
|
97 |
+
[<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/fatcat87-taopanda/subnet56/runs/lrmaou1e)
|
98 |
+
# f2c37cd7-d8ff-4753-9fa2-fd45b186c216
|
99 |
|
100 |
+
This model is a fine-tuned version of [unsloth/Qwen2.5-0.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct) on the None dataset.
|
101 |
It achieves the following results on the evaluation set:
|
102 |
+
- Loss: 1.2166
|
103 |
|
104 |
## Model description
|
105 |
|
|
|
129 |
- total_eval_batch_size: 4
|
130 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
131 |
- lr_scheduler_type: cosine
|
132 |
+
- lr_scheduler_warmup_steps: 4
|
133 |
- num_epochs: 1
|
134 |
|
135 |
### Training results
|
136 |
|
137 |
| Training Loss | Epoch | Step | Validation Loss |
|
138 |
|:-------------:|:------:|:----:|:---------------:|
|
139 |
+
| 2.1114 | 0.0103 | 1 | 2.1366 |
|
140 |
+
| 1.4492 | 0.2577 | 25 | 1.4891 |
|
141 |
+
| 1.2531 | 0.5155 | 50 | 1.2947 |
|
142 |
+
| 1.2349 | 0.7732 | 75 | 1.2166 |
|
|
|
143 |
|
144 |
|
145 |
### Framework versions
|
adapter_model.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 sha256:17fafc8aac5daab6d28871a91efcc7e449fad0523da85cd7ab1b29ab5192d64b
|
3 |
+
size 70506570
|