Hugging Face's logo

trenden
/
a358aca3-dd6a-48d2-8db4-2aeff72ecba3

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
a358aca3-dd6a-48d2-8db4-2aeff72ecba3
File size: 3,215 Bytes 
e61d70c
 
 
3eca13e
e61d70c
3eca13e
e61d70c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
556d8ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b7ac99b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3eca13e
 
 
 
 
 
 
e61d70c
 
 
 
 
 
 
 
 
 
 
 
 
 
3eca13e
e61d70c
 
 
 
3eca13e
e61d70c
 
 
 
 
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": 0.0002584296522182955,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.5842965221829554e-05,
      "grad_norm": 3.435499906539917,
      "learning_rate": 2e-05,
      "loss": 1.4246,
      "step": 1
    },
    {
      "epoch": 2.5842965221829554e-05,
      "eval_loss": 2.1122167110443115,
      "eval_runtime": 633.4485,
      "eval_samples_per_second": 25.721,
      "eval_steps_per_second": 12.861,
      "step": 1
    },
    {
      "epoch": 5.168593044365911e-05,
      "grad_norm": 2.8410768508911133,
      "learning_rate": 4e-05,
      "loss": 1.687,
      "step": 2
    },
    {
      "epoch": 7.752889566548866e-05,
      "grad_norm": 2.6962289810180664,
      "learning_rate": 6e-05,
      "loss": 1.2136,
      "step": 3
    },
    {
      "epoch": 7.752889566548866e-05,
      "eval_loss": 2.083096742630005,
      "eval_runtime": 631.5229,
      "eval_samples_per_second": 25.8,
      "eval_steps_per_second": 12.901,
      "step": 3
    },
    {
      "epoch": 0.00010337186088731822,
      "grad_norm": 2.957984447479248,
      "learning_rate": 8e-05,
      "loss": 1.3846,
      "step": 4
    },
    {
      "epoch": 0.00012921482610914775,
      "grad_norm": 3.768646240234375,
      "learning_rate": 0.0001,
      "loss": 3.3657,
      "step": 5
    },
    {
      "epoch": 0.0001550577913309773,
      "grad_norm": 2.4247074127197266,
      "learning_rate": 0.00012,
      "loss": 1.0722,
      "step": 6
    },
    {
      "epoch": 0.0001550577913309773,
      "eval_loss": 1.7299082279205322,
      "eval_runtime": 631.1001,
      "eval_samples_per_second": 25.817,
      "eval_steps_per_second": 12.909,
      "step": 6
    },
    {
      "epoch": 0.00018090075655280687,
      "grad_norm": 3.7721331119537354,
      "learning_rate": 0.00014,
      "loss": 1.0112,
      "step": 7
    },
    {
      "epoch": 0.00020674372177463643,
      "grad_norm": 2.6731598377227783,
      "learning_rate": 0.00016,
      "loss": 0.8786,
      "step": 8
    },
    {
      "epoch": 0.00023258668699646597,
      "grad_norm": 2.0309290885925293,
      "learning_rate": 0.00018,
      "loss": 0.7873,
      "step": 9
    },
    {
      "epoch": 0.00023258668699646597,
      "eval_loss": 1.1887303590774536,
      "eval_runtime": 631.1223,
      "eval_samples_per_second": 25.816,
      "eval_steps_per_second": 12.909,
      "step": 9
    },
    {
      "epoch": 0.0002584296522182955,
      "grad_norm": 2.100818634033203,
      "learning_rate": 0.0002,
      "loss": 0.6941,
      "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": 2450672628793344.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}