Hugging Face's logo

ClarenceDan
/
31d82ed8-b854-43e2-9aae-d1d023d9f76f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
31d82ed8-b854-43e2-9aae-d1d023d9f76f
File size: 2,983 Bytes 
adeb13c
 
 
edf5cca
adeb13c
edf5cca
adeb13c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d17a7ef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2a7c6ff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
edf5cca
 
 
 
 
 
 
adeb13c
 
 
 
 
 
 
 
 
 
 
 
 
 
edf5cca
adeb13c
 
 
 
edf5cca
adeb13c
 
 
 
 
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": 0.00030105066682722703,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.0105066682722702e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 3.0105066682722702e-05,
      "eval_loss": NaN,
      "eval_runtime": 589.0487,
      "eval_samples_per_second": 23.745,
      "eval_steps_per_second": 11.873,
      "step": 1
    },
    {
      "epoch": 6.0210133365445404e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 9.031520004816811e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 9.031520004816811e-05,
      "eval_loss": NaN,
      "eval_runtime": 586.1568,
      "eval_samples_per_second": 23.862,
      "eval_steps_per_second": 11.932,
      "step": 3
    },
    {
      "epoch": 0.00012042026673089081,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00015052533341361352,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00018063040009633623,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00018063040009633623,
      "eval_loss": NaN,
      "eval_runtime": 588.8611,
      "eval_samples_per_second": 23.753,
      "eval_steps_per_second": 11.877,
      "step": 6
    },
    {
      "epoch": 0.0002107354667790589,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00024084053346178162,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0002709456001445043,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0002709456001445043,
      "eval_loss": NaN,
      "eval_runtime": 586.997,
      "eval_samples_per_second": 23.828,
      "eval_steps_per_second": 11.915,
      "step": 9
    },
    {
      "epoch": 0.00030105066682722703,
      "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": 624864830423040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}