Hugging Face's logo

kk-aivio
/
2a3c8eab-84ce-4e29-a4ee-9c2fa75713cf

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
2a3c8eab-84ce-4e29-a4ee-9c2fa75713cf
File size: 3,190 Bytes 
5a1a5aa
 
 
19865eb
5a1a5aa
19865eb
5a1a5aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e2e8f20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89f9299
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19865eb
 
 
 
 
 
 
5a1a5aa
 
 
 
 
 
 
 
 
 
 
 
 
 
19865eb
5a1a5aa
 
 
 
19865eb
5a1a5aa
 
 
 
 
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": 0.008398068444257821,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000839806844425782,
      "grad_norm": 0.6686991453170776,
      "learning_rate": 2e-05,
      "loss": 0.9571,
      "step": 1
    },
    {
      "epoch": 0.000839806844425782,
      "eval_loss": 0.9189421534538269,
      "eval_runtime": 31.43,
      "eval_samples_per_second": 15.972,
      "eval_steps_per_second": 7.986,
      "step": 1
    },
    {
      "epoch": 0.001679613688851564,
      "grad_norm": 0.7383980751037598,
      "learning_rate": 4e-05,
      "loss": 0.9637,
      "step": 2
    },
    {
      "epoch": 0.0025194205332773464,
      "grad_norm": 0.691645622253418,
      "learning_rate": 6e-05,
      "loss": 0.915,
      "step": 3
    },
    {
      "epoch": 0.0025194205332773464,
      "eval_loss": 0.9044798612594604,
      "eval_runtime": 31.4757,
      "eval_samples_per_second": 15.949,
      "eval_steps_per_second": 7.974,
      "step": 3
    },
    {
      "epoch": 0.003359227377703128,
      "grad_norm": 0.6957189440727234,
      "learning_rate": 8e-05,
      "loss": 0.9805,
      "step": 4
    },
    {
      "epoch": 0.004199034222128911,
      "grad_norm": 0.7422357797622681,
      "learning_rate": 0.0001,
      "loss": 0.8764,
      "step": 5
    },
    {
      "epoch": 0.005038841066554693,
      "grad_norm": 0.6519572138786316,
      "learning_rate": 0.00012,
      "loss": 0.8963,
      "step": 6
    },
    {
      "epoch": 0.005038841066554693,
      "eval_loss": 0.7828396558761597,
      "eval_runtime": 31.5287,
      "eval_samples_per_second": 15.922,
      "eval_steps_per_second": 7.961,
      "step": 6
    },
    {
      "epoch": 0.005878647910980474,
      "grad_norm": 0.6797656416893005,
      "learning_rate": 0.00014,
      "loss": 0.7593,
      "step": 7
    },
    {
      "epoch": 0.006718454755406256,
      "grad_norm": 0.7729480862617493,
      "learning_rate": 0.00016,
      "loss": 0.7399,
      "step": 8
    },
    {
      "epoch": 0.007558261599832038,
      "grad_norm": 0.8539050817489624,
      "learning_rate": 0.00018,
      "loss": 0.6934,
      "step": 9
    },
    {
      "epoch": 0.007558261599832038,
      "eval_loss": 0.6700757741928101,
      "eval_runtime": 31.4993,
      "eval_samples_per_second": 15.937,
      "eval_steps_per_second": 7.968,
      "step": 9
    },
    {
      "epoch": 0.008398068444257821,
      "grad_norm": 0.9188011288642883,
      "learning_rate": 0.0002,
      "loss": 0.6829,
      "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": 3822182832537600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}