Hugging Face's logo

ClarenceDan
/
46dbd3dd-3688-4ff3-94d5-d7e8be2944bb

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
46dbd3dd-3688-4ff3-94d5-d7e8be2944bb
File size: 3,206 Bytes 
8ec5e45
 
 
8be6180
8ec5e45
8be6180
8ec5e45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9b31e39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ef6d2d6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8be6180
 
 
 
 
 
 
8ec5e45
 
 
 
 
 
 
 
 
 
 
 
 
 
8be6180
8ec5e45
 
 
 
8be6180
8ec5e45
 
 
 
 
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
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008078196946441554,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.078196946441554e-05,
      "grad_norm": 10.836163520812988,
      "learning_rate": 2e-05,
      "loss": 5.2973,
      "step": 1
    },
    {
      "epoch": 8.078196946441554e-05,
      "eval_loss": 6.08513069152832,
      "eval_runtime": 190.4047,
      "eval_samples_per_second": 27.379,
      "eval_steps_per_second": 13.692,
      "step": 1
    },
    {
      "epoch": 0.00016156393892883107,
      "grad_norm": 15.810860633850098,
      "learning_rate": 4e-05,
      "loss": 6.7627,
      "step": 2
    },
    {
      "epoch": 0.00024234590839324662,
      "grad_norm": 11.094259262084961,
      "learning_rate": 6e-05,
      "loss": 5.5142,
      "step": 3
    },
    {
      "epoch": 0.00024234590839324662,
      "eval_loss": 5.897503852844238,
      "eval_runtime": 185.1619,
      "eval_samples_per_second": 28.154,
      "eval_steps_per_second": 14.08,
      "step": 3
    },
    {
      "epoch": 0.00032312787785766214,
      "grad_norm": 13.849967956542969,
      "learning_rate": 8e-05,
      "loss": 6.0094,
      "step": 4
    },
    {
      "epoch": 0.0004039098473220777,
      "grad_norm": 11.20494556427002,
      "learning_rate": 0.0001,
      "loss": 5.0195,
      "step": 5
    },
    {
      "epoch": 0.00048469181678649324,
      "grad_norm": 10.72175407409668,
      "learning_rate": 0.00012,
      "loss": 4.6667,
      "step": 6
    },
    {
      "epoch": 0.00048469181678649324,
      "eval_loss": 3.9255988597869873,
      "eval_runtime": 186.96,
      "eval_samples_per_second": 27.883,
      "eval_steps_per_second": 13.944,
      "step": 6
    },
    {
      "epoch": 0.0005654737862509088,
      "grad_norm": 9.823970794677734,
      "learning_rate": 0.00014,
      "loss": 3.7467,
      "step": 7
    },
    {
      "epoch": 0.0006462557557153243,
      "grad_norm": 9.715559959411621,
      "learning_rate": 0.00016,
      "loss": 3.0583,
      "step": 8
    },
    {
      "epoch": 0.0007270377251797399,
      "grad_norm": 9.468438148498535,
      "learning_rate": 0.00018,
      "loss": 2.6625,
      "step": 9
    },
    {
      "epoch": 0.0007270377251797399,
      "eval_loss": 1.930371642112732,
      "eval_runtime": 84.7272,
      "eval_samples_per_second": 61.527,
      "eval_steps_per_second": 30.769,
      "step": 9
    },
    {
      "epoch": 0.0008078196946441554,
      "grad_norm": 9.221755981445312,
      "learning_rate": 0.0002,
      "loss": 2.0402,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 489477793382400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}