Model save
Browse files- README.md +3 -6
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- all_results.json +4 -4
- train_results.json +4 -4
- trainer_state.json +9 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,20 +1,17 @@
|
|
1 |
---
|
2 |
base_model: Qwen/Qwen3-1.7B-Base
|
3 |
-
datasets: atomwalk12/linalg-debug
|
4 |
library_name: transformers
|
5 |
model_name: Qwen3-1.7B-Base-SFT
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
-
- sft
|
9 |
-
- linalg-zero
|
10 |
- trl
|
11 |
-
-
|
12 |
licence: license
|
13 |
---
|
14 |
|
15 |
# Model Card for Qwen3-1.7B-Base-SFT
|
16 |
|
17 |
-
This model is a fine-tuned version of [Qwen/Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base)
|
18 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
19 |
|
20 |
## Quick start
|
@@ -30,7 +27,7 @@ print(output["generated_text"])
|
|
30 |
|
31 |
## Training procedure
|
32 |
|
33 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/walks/huggingface/runs/
|
34 |
|
35 |
|
36 |
This model was trained with SFT.
|
|
|
1 |
---
|
2 |
base_model: Qwen/Qwen3-1.7B-Base
|
|
|
3 |
library_name: transformers
|
4 |
model_name: Qwen3-1.7B-Base-SFT
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
|
|
7 |
- trl
|
8 |
+
- sft
|
9 |
licence: license
|
10 |
---
|
11 |
|
12 |
# Model Card for Qwen3-1.7B-Base-SFT
|
13 |
|
14 |
+
This model is a fine-tuned version of [Qwen/Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base).
|
15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
16 |
|
17 |
## Quick start
|
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/walks/huggingface/runs/zycvekym)
|
31 |
|
32 |
|
33 |
This model was trained with SFT.
|
adapter_config.json
CHANGED
@@ -25,12 +25,12 @@
|
|
25 |
"rank_pattern": {},
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
28 |
-
"k_proj",
|
29 |
-
"o_proj",
|
30 |
"v_proj",
|
31 |
"q_proj",
|
32 |
-
"
|
33 |
"gate_proj",
|
|
|
|
|
34 |
"down_proj"
|
35 |
],
|
36 |
"task_type": "CAUSAL_LM",
|
|
|
25 |
"rank_pattern": {},
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
|
|
|
|
28 |
"v_proj",
|
29 |
"q_proj",
|
30 |
+
"o_proj",
|
31 |
"gate_proj",
|
32 |
+
"up_proj",
|
33 |
+
"k_proj",
|
34 |
"down_proj"
|
35 |
],
|
36 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 69782384
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41f5b090f3d0037006ebf9aac6b4eacec2b5eea8df1c0f09646cad88114db92b
|
3 |
size 69782384
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"total_flos": 661444288892928.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 5,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"total_flos": 661444288892928.0,
|
3 |
+
"train_loss": 0.0,
|
4 |
+
"train_runtime": 1.2759,
|
5 |
"train_samples": 5,
|
6 |
+
"train_samples_per_second": 19.594,
|
7 |
+
"train_steps_per_second": 3.919
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"total_flos": 661444288892928.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 5,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"total_flos": 661444288892928.0,
|
3 |
+
"train_loss": 0.0,
|
4 |
+
"train_runtime": 1.2759,
|
5 |
"train_samples": 5,
|
6 |
+
"train_samples_per_second": 19.594,
|
7 |
+
"train_steps_per_second": 3.919
|
8 |
}
|
trainer_state.json
CHANGED
@@ -57,6 +57,15 @@
|
|
57 |
"train_runtime": 18.2726,
|
58 |
"train_samples_per_second": 1.368,
|
59 |
"train_steps_per_second": 0.274
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
}
|
61 |
],
|
62 |
"logging_steps": 1,
|
|
|
57 |
"train_runtime": 18.2726,
|
58 |
"train_samples_per_second": 1.368,
|
59 |
"train_steps_per_second": 0.274
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 5.0,
|
63 |
+
"step": 5,
|
64 |
+
"total_flos": 661444288892928.0,
|
65 |
+
"train_loss": 0.0,
|
66 |
+
"train_runtime": 1.2759,
|
67 |
+
"train_samples_per_second": 19.594,
|
68 |
+
"train_steps_per_second": 3.919
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 1,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10641
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31066859bc63690b78379d0f36cd0ecb70d0daddc3fdbea5f2262c390c1497dd
|
3 |
size 10641
|