Hugging Face's logo

dzanbek
/
e7d3e260-1f09-41c9-8384-47c616f650d3

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
e7d3e260-1f09-41c9-8384-47c616f650d3
File size: 3,174 Bytes 
9cdd7f7
 
 
c407f44
9cdd7f7
c407f44
9cdd7f7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c407f44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9cdd7f7
 
 
 
 
 
 
 
 
 
 
 
 
 
c407f44
9cdd7f7
 
 
 
c407f44
9cdd7f7
 
 
 
 
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": 0.02289639381797367,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022896393817973667,
      "grad_norm": 4.149505615234375,
      "learning_rate": 2e-05,
      "loss": 4.2034,
      "step": 1
    },
    {
      "epoch": 0.0022896393817973667,
      "eval_loss": 4.1785359382629395,
      "eval_runtime": 29.4614,
      "eval_samples_per_second": 6.245,
      "eval_steps_per_second": 3.123,
      "step": 1
    },
    {
      "epoch": 0.0045792787635947334,
      "grad_norm": 4.028379917144775,
      "learning_rate": 4e-05,
      "loss": 4.7035,
      "step": 2
    },
    {
      "epoch": 0.006868918145392101,
      "grad_norm": 3.707000732421875,
      "learning_rate": 6e-05,
      "loss": 4.149,
      "step": 3
    },
    {
      "epoch": 0.006868918145392101,
      "eval_loss": 4.107508182525635,
      "eval_runtime": 29.7334,
      "eval_samples_per_second": 6.188,
      "eval_steps_per_second": 3.094,
      "step": 3
    },
    {
      "epoch": 0.009158557527189467,
      "grad_norm": 3.4329545497894287,
      "learning_rate": 8e-05,
      "loss": 3.7555,
      "step": 4
    },
    {
      "epoch": 0.011448196908986834,
      "grad_norm": 3.9176552295684814,
      "learning_rate": 0.0001,
      "loss": 4.0517,
      "step": 5
    },
    {
      "epoch": 0.013737836290784202,
      "grad_norm": 3.739713430404663,
      "learning_rate": 0.00012,
      "loss": 3.7634,
      "step": 6
    },
    {
      "epoch": 0.013737836290784202,
      "eval_loss": 3.4562952518463135,
      "eval_runtime": 29.7619,
      "eval_samples_per_second": 6.182,
      "eval_steps_per_second": 3.091,
      "step": 6
    },
    {
      "epoch": 0.01602747567258157,
      "grad_norm": 3.4949848651885986,
      "learning_rate": 0.00014,
      "loss": 3.4091,
      "step": 7
    },
    {
      "epoch": 0.018317115054378934,
      "grad_norm": 5.311485290527344,
      "learning_rate": 0.00016,
      "loss": 3.3507,
      "step": 8
    },
    {
      "epoch": 0.0206067544361763,
      "grad_norm": 9.926668167114258,
      "learning_rate": 0.00018,
      "loss": 3.4155,
      "step": 9
    },
    {
      "epoch": 0.0206067544361763,
      "eval_loss": 3.2308547496795654,
      "eval_runtime": 29.8059,
      "eval_samples_per_second": 6.173,
      "eval_steps_per_second": 3.087,
      "step": 9
    },
    {
      "epoch": 0.02289639381797367,
      "grad_norm": 10.94023609161377,
      "learning_rate": 0.0002,
      "loss": 3.003,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4491064828231680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}