Hugging Face's logo

adammandic87
/
a4b602b9-442e-471b-a4f7-6692a152d401

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
a4b602b9-442e-471b-a4f7-6692a152d401
File size: 2,972 Bytes 
2866191
 
 
6d46c02
2866191
6d46c02
2866191
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c87ad59
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3d088f5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6d46c02
 
 
 
 
 
 
2866191
 
 
 
 
 
 
 
 
 
 
 
 
 
6d46c02
2866191
 
 
 
6d46c02
2866191
 
 
 
 
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": 0.0009455370650529501,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.455370650529501e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 9.455370650529501e-05,
      "eval_loss": NaN,
      "eval_runtime": 18.3443,
      "eval_samples_per_second": 242.745,
      "eval_steps_per_second": 121.4,
      "step": 1
    },
    {
      "epoch": 0.00018910741301059002,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00028366111951588503,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00028366111951588503,
      "eval_loss": NaN,
      "eval_runtime": 17.2628,
      "eval_samples_per_second": 257.954,
      "eval_steps_per_second": 129.006,
      "step": 3
    },
    {
      "epoch": 0.00037821482602118004,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00047276853252647505,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0005673222390317701,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005673222390317701,
      "eval_loss": NaN,
      "eval_runtime": 17.3709,
      "eval_samples_per_second": 256.348,
      "eval_steps_per_second": 128.203,
      "step": 6
    },
    {
      "epoch": 0.000661875945537065,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0007564296520423601,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.000850983358547655,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.000850983358547655,
      "eval_loss": NaN,
      "eval_runtime": 17.3163,
      "eval_samples_per_second": 257.157,
      "eval_steps_per_second": 128.607,
      "step": 9
    },
    {
      "epoch": 0.0009455370650529501,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 994836480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}