Text Generation
PEFT
Safetensors
lora
qwen3.5
instruction-tuning
File size: 895 Bytes
0d413dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
{
  "args": {
    "model": "Qwen/Qwen3.5-2B-Base",
    "data": "C:\\Users\\arisp\\Documents\\Research\\Memorize\\data\\sft",
    "out": "adapters/sft-run2-torch",
    "epochs": 1,
    "batch_size": 8,
    "max_batch_tokens": 4096,
    "lr": 1e-05,
    "clip": 20.0,
    "warmup": 20,
    "rank": 8,
    "scale": 20.0,
    "max_seq": 512,
    "report_every": 25,
    "eval_every": 100,
    "no_probes": false,
    "gpu_mem_frac": 0.9,
    "seed": 0
  },
  "history": [
    {
      "step": 0,
      "valid_loss": 1.3611059830069272
    },
    {
      "step": 100,
      "valid_loss": 1.2591907709679355
    },
    {
      "step": 200,
      "valid_loss": 1.2521158879783705
    },
    {
      "step": 300,
      "valid_loss": 1.2502558373648405
    },
    {
      "step": 300,
      "valid_loss": 1.2502558373648405,
      "probes_passed": 18
    }
  ]
}