owenisas commited on
Commit
7fd182c
·
verified ·
1 Parent(s): 29a2646

Training in progress, step 200

Browse files
README.md CHANGED
@@ -4,9 +4,9 @@ library_name: transformers
4
  model_name: temp
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
  - sft
9
- - unsloth
10
  licence: license
11
  ---
12
 
@@ -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/reunifylabs-reunify-labs/huggingface/runs/wi8970im)
32
 
33
 
34
  This model was trained with SFT.
@@ -37,7 +37,7 @@ This model was trained with SFT.
37
 
38
  - TRL: 0.22.2
39
  - Transformers: 4.56.2
40
- - Pytorch: 2.7.1
41
  - Datasets: 4.3.0
42
  - Tokenizers: 0.22.2
43
 
 
4
  model_name: temp
5
  tags:
6
  - generated_from_trainer
7
+ - unsloth
8
  - trl
9
  - sft
 
10
  licence: license
11
  ---
12
 
 
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/reunifylabs-reunify-labs/huggingface/runs/mxxmtahg)
32
 
33
 
34
  This model was trained with SFT.
 
37
 
38
  - TRL: 0.22.2
39
  - Transformers: 4.56.2
40
+ - Pytorch: 2.9.0+cu128
41
  - Datasets: 4.3.0
42
  - Tokenizers: 0.22.2
43
 
adapter_config.json CHANGED
@@ -27,21 +27,21 @@
27
  "megatron_core": "megatron.core",
28
  "modules_to_save": null,
29
  "peft_type": "LORA",
30
- "peft_version": "0.18.1",
31
  "qalora_group_size": 16,
32
  "r": 32,
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
- "out_proj",
37
- "o_proj",
38
- "in_proj",
39
  "down_proj",
40
  "gate_proj",
 
 
41
  "q_proj",
42
- "v_proj",
43
- "k_proj",
44
- "up_proj"
45
  ],
46
  "target_parameters": null,
47
  "task_type": "CAUSAL_LM",
 
27
  "megatron_core": "megatron.core",
28
  "modules_to_save": null,
29
  "peft_type": "LORA",
30
+ "peft_version": "0.18.0",
31
  "qalora_group_size": 16,
32
  "r": 32,
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
+ "k_proj",
 
 
37
  "down_proj",
38
  "gate_proj",
39
+ "out_proj",
40
+ "o_proj",
41
  "q_proj",
42
+ "up_proj",
43
+ "in_proj",
44
+ "v_proj"
45
  ],
46
  "target_parameters": null,
47
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05f40edbfeebb58978aa105a2fb9fb4e84a92fd73556c844cb1beb528dd3b8c0
3
  size 3537299144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d51391eae20fd1e2416fc130cc061ef37cae0dce1392cfc4c82bb34308c5af
3
  size 3537299144
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e25d71cb7e66cc3a62d94b61be69c2073bf6f975952262cee95223958bfe5467
3
- size 6289
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:908a527816bc09fbe07f310e4f80e352792f6417bc1abafa58d2254bddc3d1db
3
+ size 6225