Hugging Face's logo

ClarenceDan
/
07f0c06e-024f-470b-9db3-bf4df2173cf9

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
07f0c06e-024f-470b-9db3-bf4df2173cf9
File size: 2,971 Bytes 
b2ff178
 
 
a55db06
b2ff178
a55db06
b2ff178
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70989ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cb8822f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a55db06
 
 
 
 
 
 
b2ff178
 
 
 
 
 
 
 
 
 
 
 
 
 
a55db06
b2ff178
 
 
 
a55db06
b2ff178
 
 
 
 
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": 0.0018535681186283596,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018535681186283596,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00018535681186283596,
      "eval_loss": NaN,
      "eval_runtime": 46.0307,
      "eval_samples_per_second": 49.358,
      "eval_steps_per_second": 24.679,
      "step": 1
    },
    {
      "epoch": 0.0003707136237256719,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0005560704355885078,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005560704355885078,
      "eval_loss": NaN,
      "eval_runtime": 45.1878,
      "eval_samples_per_second": 50.279,
      "eval_steps_per_second": 25.14,
      "step": 3
    },
    {
      "epoch": 0.0007414272474513438,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0009267840593141798,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0011121408711770157,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0011121408711770157,
      "eval_loss": NaN,
      "eval_runtime": 45.1378,
      "eval_samples_per_second": 50.335,
      "eval_steps_per_second": 25.167,
      "step": 6
    },
    {
      "epoch": 0.0012974976830398518,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0014828544949026877,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0016682113067655235,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0016682113067655235,
      "eval_loss": NaN,
      "eval_runtime": 44.8166,
      "eval_samples_per_second": 50.696,
      "eval_steps_per_second": 25.348,
      "step": 9
    },
    {
      "epoch": 0.0018535681186283596,
      "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": 389157910216704.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}