Hugging Face's logo

kooff11
/
65d9c680-cee4-4aed-81f6-b3492563fd49

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
65d9c680-cee4-4aed-81f6-b3492563fd49
File size: 3,173 Bytes 
f51f8e1
 
 
fcf5a96
f51f8e1
fcf5a96
f51f8e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ab6ccf6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eba001c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fcf5a96
 
 
 
 
 
 
f51f8e1
 
 
 
 
 
 
 
 
 
 
 
 
 
fcf5a96
f51f8e1
 
 
 
fcf5a96
f51f8e1
 
 
 
 
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": 0.09216589861751152,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009216589861751152,
      "grad_norm": 14.310744285583496,
      "learning_rate": 2e-05,
      "loss": 5.6609,
      "step": 1
    },
    {
      "epoch": 0.009216589861751152,
      "eval_loss": 5.6318440437316895,
      "eval_runtime": 5.0294,
      "eval_samples_per_second": 36.386,
      "eval_steps_per_second": 4.573,
      "step": 1
    },
    {
      "epoch": 0.018433179723502304,
      "grad_norm": 16.09499740600586,
      "learning_rate": 4e-05,
      "loss": 6.1363,
      "step": 2
    },
    {
      "epoch": 0.027649769585253458,
      "grad_norm": 12.103375434875488,
      "learning_rate": 6e-05,
      "loss": 5.1534,
      "step": 3
    },
    {
      "epoch": 0.027649769585253458,
      "eval_loss": 5.331299781799316,
      "eval_runtime": 4.9679,
      "eval_samples_per_second": 36.836,
      "eval_steps_per_second": 4.63,
      "step": 3
    },
    {
      "epoch": 0.03686635944700461,
      "grad_norm": 13.103915214538574,
      "learning_rate": 8e-05,
      "loss": 5.4683,
      "step": 4
    },
    {
      "epoch": 0.04608294930875576,
      "grad_norm": 11.824213981628418,
      "learning_rate": 0.0001,
      "loss": 4.5965,
      "step": 5
    },
    {
      "epoch": 0.055299539170506916,
      "grad_norm": 9.575993537902832,
      "learning_rate": 0.00012,
      "loss": 4.1653,
      "step": 6
    },
    {
      "epoch": 0.055299539170506916,
      "eval_loss": 3.606476306915283,
      "eval_runtime": 4.945,
      "eval_samples_per_second": 37.007,
      "eval_steps_per_second": 4.651,
      "step": 6
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 10.15619945526123,
      "learning_rate": 0.00014,
      "loss": 3.9804,
      "step": 7
    },
    {
      "epoch": 0.07373271889400922,
      "grad_norm": 5.944631576538086,
      "learning_rate": 0.00016,
      "loss": 2.7903,
      "step": 8
    },
    {
      "epoch": 0.08294930875576037,
      "grad_norm": 5.762338638305664,
      "learning_rate": 0.00018,
      "loss": 2.8695,
      "step": 9
    },
    {
      "epoch": 0.08294930875576037,
      "eval_loss": 2.5336620807647705,
      "eval_runtime": 4.8033,
      "eval_samples_per_second": 38.098,
      "eval_steps_per_second": 4.788,
      "step": 9
    },
    {
      "epoch": 0.09216589861751152,
      "grad_norm": 7.361027717590332,
      "learning_rate": 0.0002,
      "loss": 2.2716,
      "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": 1.574040552603648e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}