Hugging Face's logo

innadark
/
gaado

PEFT
Safetensors
qwen3
Model card Files
xet
Community
gaado
File size: 2,492 Bytes
5655d8f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
 
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 1.2253111600875854,
      "learning_rate": 2e-05,
      "loss": 5.4883,
      "step": 1
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.2487238645553589,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 5.5898,
      "step": 2
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.3708199262619019,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 5.75,
      "step": 3
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.2051873207092285,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 5.4727,
      "step": 4
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.3166049718856812,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 5.5742,
      "step": 5
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.307198166847229,
      "learning_rate": 1e-05,
      "loss": 5.4922,
      "step": 6
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.3135805130004883,
      "learning_rate": 6.909830056250527e-06,
      "loss": 5.4414,
      "step": 7
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.3186125755310059,
      "learning_rate": 4.12214747707527e-06,
      "loss": 5.4453,
      "step": 8
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.2448387145996094,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 5.4023,
      "step": 9
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.2668588161468506,
      "learning_rate": 4.894348370484648e-07,
      "loss": 5.3672,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_loss": 5.465277671813965,
      "eval_runtime": 0.2049,
      "eval_samples_per_second": 87.862,
      "eval_steps_per_second": 9.762,
      "step": 10
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2207185924784128.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}