Hugging Face's logo

imdatta0
/
lora_final

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
lora_final
File size: 2,086 Bytes 
8b1b653
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
 
{
  "best_metric": 1.9893906116485596,
  "best_model_checkpoint": "/home/datta0/models/lora_final/Qwen2-7B_pct_ortho/checkpoint-16",
  "epoch": 0.041223832528180356,
  "eval_steps": 8,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025764895330112722,
      "grad_norm": 3.2372000217437744,
      "learning_rate": 3.75e-05,
      "loss": 2.0292,
      "step": 1
    },
    {
      "epoch": 0.010305958132045089,
      "grad_norm": 2.4374635219573975,
      "learning_rate": 0.00015,
      "loss": 2.1277,
      "step": 4
    },
    {
      "epoch": 0.020611916264090178,
      "grad_norm": 2.3065264225006104,
      "learning_rate": 0.0003,
      "loss": 2.0836,
      "step": 8
    },
    {
      "epoch": 0.020611916264090178,
      "eval_loss": 1.999721884727478,
      "eval_runtime": 10.3706,
      "eval_samples_per_second": 23.624,
      "eval_steps_per_second": 2.989,
      "step": 8
    },
    {
      "epoch": 0.030917874396135265,
      "grad_norm": 2.9390103816986084,
      "learning_rate": 0.0002999179886011389,
      "loss": 2.0317,
      "step": 12
    },
    {
      "epoch": 0.041223832528180356,
      "grad_norm": 1.5938222408294678,
      "learning_rate": 0.00029967204408281613,
      "loss": 2.0451,
      "step": 16
    },
    {
      "epoch": 0.041223832528180356,
      "eval_loss": 1.9893906116485596,
      "eval_runtime": 10.3682,
      "eval_samples_per_second": 23.63,
      "eval_steps_per_second": 2.99,
      "step": 16
    }
  ],
  "logging_steps": 4,
  "max_steps": 388,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 8,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.571587033838387e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}