Hugging Face's logo

cwaud
/
63ee0cce-b794-48ef-8922-0d864dea7926

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
63ee0cce-b794-48ef-8922-0d864dea7926
File size: 3,202 Bytes 
104554d
 
 
08dcf51
104554d
08dcf51
104554d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
225d788
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
887b777
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
08dcf51
 
 
 
 
 
 
104554d
 
 
 
 
 
 
 
 
 
 
 
 
 
08dcf51
104554d
 
 
 
08dcf51
104554d
 
 
 
 
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": 0.00013798194506248857,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3798194506248858e-05,
      "grad_norm": 11.564373970031738,
      "learning_rate": 2e-05,
      "loss": 10.563,
      "step": 1
    },
    {
      "epoch": 1.3798194506248858e-05,
      "eval_loss": 10.16752815246582,
      "eval_runtime": 4125.8399,
      "eval_samples_per_second": 7.396,
      "eval_steps_per_second": 3.698,
      "step": 1
    },
    {
      "epoch": 2.7596389012497716e-05,
      "grad_norm": 13.19704532623291,
      "learning_rate": 4e-05,
      "loss": 11.0015,
      "step": 2
    },
    {
      "epoch": 4.139458351874657e-05,
      "grad_norm": 10.903892517089844,
      "learning_rate": 6e-05,
      "loss": 10.4111,
      "step": 3
    },
    {
      "epoch": 4.139458351874657e-05,
      "eval_loss": 9.961125373840332,
      "eval_runtime": 4123.3416,
      "eval_samples_per_second": 7.401,
      "eval_steps_per_second": 3.7,
      "step": 3
    },
    {
      "epoch": 5.519277802499543e-05,
      "grad_norm": 11.607290267944336,
      "learning_rate": 8e-05,
      "loss": 9.734,
      "step": 4
    },
    {
      "epoch": 6.899097253124429e-05,
      "grad_norm": 13.406005859375,
      "learning_rate": 0.0001,
      "loss": 7.917,
      "step": 5
    },
    {
      "epoch": 8.278916703749314e-05,
      "grad_norm": 12.174226760864258,
      "learning_rate": 0.00012,
      "loss": 8.65,
      "step": 6
    },
    {
      "epoch": 8.278916703749314e-05,
      "eval_loss": 7.667308807373047,
      "eval_runtime": 4120.9144,
      "eval_samples_per_second": 7.405,
      "eval_steps_per_second": 3.703,
      "step": 6
    },
    {
      "epoch": 9.6587361543742e-05,
      "grad_norm": 14.514153480529785,
      "learning_rate": 0.00014,
      "loss": 7.5376,
      "step": 7
    },
    {
      "epoch": 0.00011038555604999086,
      "grad_norm": 11.81023120880127,
      "learning_rate": 0.00016,
      "loss": 6.6161,
      "step": 8
    },
    {
      "epoch": 0.0001241837505562397,
      "grad_norm": 12.662259101867676,
      "learning_rate": 0.00018,
      "loss": 5.8399,
      "step": 9
    },
    {
      "epoch": 0.0001241837505562397,
      "eval_loss": 5.220765113830566,
      "eval_runtime": 4119.8507,
      "eval_samples_per_second": 7.407,
      "eval_steps_per_second": 3.704,
      "step": 9
    },
    {
      "epoch": 0.00013798194506248857,
      "grad_norm": 10.579679489135742,
      "learning_rate": 0.0002,
      "loss": 4.6917,
      "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": 1911091416268800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}