Hugging Face's logo

dimasik1987
/
47464ff7-8c20-4c29-a942-d61b60e74a90

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
47464ff7-8c20-4c29-a942-d61b60e74a90
File size: 3,375 Bytes 
7831ba9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9767441860465116,
  "eval_steps": 25,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18604651162790697,
      "grad_norm": NaN,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.18604651162790697,
      "eval_loss": NaN,
      "eval_runtime": 2.4989,
      "eval_samples_per_second": 2.001,
      "eval_steps_per_second": 1.201,
      "step": 1
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": NaN,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": NaN,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 1.1162790697674418,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 1.302325581395349,
      "grad_norm": NaN,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 1.4883720930232558,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 1.6744186046511627,
      "grad_norm": NaN,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 2.046511627906977,
      "grad_norm": NaN,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 2.2325581395348837,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 2.4186046511627906,
      "grad_norm": NaN,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 2.604651162790698,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 2.7906976744186047,
      "grad_norm": NaN,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 2.9767441860465116,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.409904245558477e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}