tsilva commited on
Commit
5d4375b
·
verified ·
1 Parent(s): dbc8d7f

End of training

Browse files
README.md CHANGED
@@ -29,7 +29,7 @@ print(output["generated_text"])
29
 
30
  ## Training procedure
31
 
32
- [<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/tsilva/huggingface/runs/5daytdmd)
33
 
34
 
35
  This model was trained with SFT.
 
29
 
30
  ## Training procedure
31
 
32
+ [<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/tsilva/huggingface/runs/xd5e2l92)
33
 
34
 
35
  This model was trained with SFT.
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 8,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 6,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "gate_proj",
27
+ "k_proj",
28
+ "down_proj",
29
+ "v_proj",
30
+ "o_proj",
31
+ "up_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70aaf3749f0981a307bf6c735ef398b1e763fc474aefc5eda991b3e03a5a30e6
3
+ size 7380952
runs/Feb20_16-44-11_3474ee83a617/events.out.tfevents.1740069857.3474ee83a617.1288.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2819f8344ec2f1feaa07ecfbdfdb1afbe6c4f54cf42c735eeeb7d1858ff134
3
+ size 40003
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2148fae3180e7171b74f0f843e512904441a540b59ca4ee14c68651dac97037
3
- size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b12d108bb4c6d283daf832b49d188df52d07a160c5089aa19e38e8509a159961
3
+ size 5624