Hugging Face's logo

kooff11
/
6f9c8cde-b0b1-4240-86e1-4836791bd005

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
6f9c8cde-b0b1-4240-86e1-4836791bd005
File size: 3,795 Bytes 
72799d5
 
 
a7940f3
72799d5
a7940f3
72799d5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
05bc034
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ced1648
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a7940f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72799d5
 
 
 
 
 
 
 
 
 
 
 
 
 
a7940f3
72799d5
 
 
 
a7940f3
72799d5
 
 
 
 
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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0526315789473684,
  "eval_steps": 4,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07017543859649122,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.07017543859649122,
      "eval_loss": NaN,
      "eval_runtime": 10.4393,
      "eval_samples_per_second": 9.292,
      "eval_steps_per_second": 2.395,
      "step": 1
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": NaN,
      "learning_rate": 9.85470908713026e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": NaN,
      "learning_rate": 9.42728012826605e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.2807017543859649,
      "eval_loss": NaN,
      "eval_runtime": 9.7444,
      "eval_samples_per_second": 9.954,
      "eval_steps_per_second": 2.566,
      "step": 4
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": NaN,
      "learning_rate": 8.742553740855506e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": NaN,
      "learning_rate": 7.840323733655778e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": NaN,
      "learning_rate": 6.773024435212678e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": NaN,
      "learning_rate": 5.602683401276615e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.5614035087719298,
      "eval_loss": NaN,
      "eval_runtime": 9.7423,
      "eval_samples_per_second": 9.957,
      "eval_steps_per_second": 2.566,
      "step": 8
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": NaN,
      "learning_rate": 4.397316598723385e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": NaN,
      "learning_rate": 3.226975564787322e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": NaN,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": NaN,
      "learning_rate": 1.257446259144494e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.8421052631578947,
      "eval_loss": NaN,
      "eval_runtime": 9.752,
      "eval_samples_per_second": 9.947,
      "eval_steps_per_second": 2.564,
      "step": 12
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": NaN,
      "learning_rate": 5.727198717339511e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": NaN,
      "learning_rate": 1.4529091286973995e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3553856474382336e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}