Hugging Face's logo

jssky
/
267607c4-3f58-4ff8-ad72-625352a06ab8

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
267607c4-3f58-4ff8-ad72-625352a06ab8
File size: 2,876 Bytes 
91fccc1
 
 
de3ba12
91fccc1
de3ba12
91fccc1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
541ac7f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
de3ba12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91fccc1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
de3ba12
91fccc1
 
 
 
 
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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004109119963474489,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004565688848304988,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 6.1476,
      "step": 1
    },
    {
      "epoch": 0.0004565688848304988,
      "eval_loss": 8.7471342086792,
      "eval_runtime": 60.3923,
      "eval_samples_per_second": 7.65,
      "eval_steps_per_second": 7.65,
      "step": 1
    },
    {
      "epoch": 0.0009131377696609977,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 8.1898,
      "step": 2
    },
    {
      "epoch": 0.0013697066544914964,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 6.0634,
      "step": 3
    },
    {
      "epoch": 0.0013697066544914964,
      "eval_loss": 8.7471342086792,
      "eval_runtime": 60.3302,
      "eval_samples_per_second": 7.658,
      "eval_steps_per_second": 7.658,
      "step": 3
    },
    {
      "epoch": 0.0018262755393219953,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.7222,
      "step": 4
    },
    {
      "epoch": 0.002282844424152494,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.0675,
      "step": 5
    },
    {
      "epoch": 0.002739413308982993,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.9791,
      "step": 6
    },
    {
      "epoch": 0.002739413308982993,
      "eval_loss": 8.7471342086792,
      "eval_runtime": 60.3363,
      "eval_samples_per_second": 7.657,
      "eval_steps_per_second": 7.657,
      "step": 6
    },
    {
      "epoch": 0.0031959821938134917,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 8.8075,
      "step": 7
    },
    {
      "epoch": 0.0036525510786439906,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.0902,
      "step": 8
    },
    {
      "epoch": 0.004109119963474489,
      "grad_norm": 34.917747497558594,
      "learning_rate": 2e-05,
      "loss": 6.32,
      "step": 9
    },
    {
      "epoch": 0.004109119963474489,
      "eval_loss": 8.7471342086792,
      "eval_runtime": 59.8996,
      "eval_samples_per_second": 7.713,
      "eval_steps_per_second": 7.713,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1809536922943488.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}