ZajaczkowskiM commited on
Commit
39a6c64
·
verified ·
1 Parent(s): a210956

Training in progress, step 100

Browse files
README.md CHANGED
@@ -4,8 +4,8 @@ library_name: transformers
4
  model_name: qwen2.5-500M-sft-args1.1
5
  tags:
6
  - generated_from_trainer
7
- - trl
8
  - unsloth
 
9
  - sft
10
  licence: license
11
  ---
@@ -28,7 +28,7 @@ print(output["generated_text"])
28
 
29
  ## Training procedure
30
 
31
- [<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/01180759-warsaw-university-of-technology/SFT-Qwen-2.5-Instruct/runs/tc9xv9cr)
32
 
33
 
34
  This model was trained with SFT.
 
4
  model_name: qwen2.5-500M-sft-args1.1
5
  tags:
6
  - generated_from_trainer
 
7
  - unsloth
8
+ - trl
9
  - sft
10
  licence: license
11
  ---
 
28
 
29
  ## Training procedure
30
 
31
+ [<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/01180759-warsaw-university-of-technology/SFT-Qwen-2.5-Instruct/runs/zhrgwqou)
32
 
33
 
34
  This model was trained with SFT.
adapter_config.json CHANGED
@@ -29,13 +29,13 @@
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
- "k_proj",
33
- "up_proj",
34
- "gate_proj",
35
  "q_proj",
 
 
36
  "o_proj",
37
  "down_proj",
38
- "v_proj"
 
39
  ],
40
  "task_type": "CAUSAL_LM",
41
  "trainable_token_indices": null,
 
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
 
 
 
32
  "q_proj",
33
+ "v_proj",
34
+ "k_proj",
35
  "o_proj",
36
  "down_proj",
37
+ "gate_proj",
38
+ "up_proj"
39
  ],
40
  "task_type": "CAUSAL_LM",
41
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80c039d41936a2e37ea653f484767880321083e4d571f9482150c4d3833ea1e0
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391045aa8f01c2418fb97d603fe0880f957956a3499e5ff51c29498057aac3c4
3
  size 70430032
runs/Nov10_20-57-07_67c560d5ebac/events.out.tfevents.1762808250.67c560d5ebac.48.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a144d6c86c913dd9df5b163e367e0694a6defda34a438d7c53075262686fca
3
+ size 9889
runs/Nov10_21-00-51_67c560d5ebac/events.out.tfevents.1762808476.67c560d5ebac.48.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513827a55dfeaeda83b7b03b579100c5ca8a42e71dd01c691a09527ef6283bb7
3
+ size 15552
runs/Nov10_21-02-53_67c560d5ebac/events.out.tfevents.1762808715.67c560d5ebac.48.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a19bfad97f7d7751fa0d103714a62c991b070e2f623bfdda0864258a398baa07
3
+ size 360
runs/Nov10_21-08-04_67c560d5ebac/events.out.tfevents.1762808909.67c560d5ebac.48.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff780bb034216d116585107cfa810cd02ae6a1cf2ba9e1be456e67da2b16c160
3
+ size 27810
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ce67b436f860a8888a95e64f6adf3bb600e9f37af0649e5b84f7957650a9530
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a8e8257555f63a3b70b5d40438fbf4378a86b5c257fe109b28d9aeae9eb706
3
  size 5816