Hugging Face's logo

leixa
/
bcd5c5b1-7cae-48d6-8646-0d38d3d1f107

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
bcd5c5b1-7cae-48d6-8646-0d38d3d1f107
File size: 3,980 Bytes 
6ce5dc9
 
 
4db6d12
6ce5dc9
4db6d12
6ce5dc9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3106a24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cae8ed9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96b1e00
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e3063dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91ef5f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4db6d12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ce5dc9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4db6d12
6ce5dc9
 
 
 
 
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
172
173
174
175
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11155378486055777,
  "eval_steps": 5,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031872509960159364,
      "eval_loss": NaN,
      "eval_runtime": 8.0945,
      "eval_samples_per_second": 32.738,
      "eval_steps_per_second": 8.277,
      "step": 1
    },
    {
      "epoch": 0.009561752988047808,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.01593625498007968,
      "eval_loss": NaN,
      "eval_runtime": 7.5519,
      "eval_samples_per_second": 35.09,
      "eval_steps_per_second": 8.872,
      "step": 5
    },
    {
      "epoch": 0.019123505976095617,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.028685258964143426,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.03187250996015936,
      "eval_loss": NaN,
      "eval_runtime": 7.5738,
      "eval_samples_per_second": 34.989,
      "eval_steps_per_second": 8.846,
      "step": 10
    },
    {
      "epoch": 0.03824701195219123,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.04780876494023904,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.04780876494023904,
      "eval_loss": NaN,
      "eval_runtime": 7.5825,
      "eval_samples_per_second": 34.949,
      "eval_steps_per_second": 8.836,
      "step": 15
    },
    {
      "epoch": 0.05737051792828685,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.06374501992031872,
      "eval_loss": NaN,
      "eval_runtime": 7.5612,
      "eval_samples_per_second": 35.047,
      "eval_steps_per_second": 8.861,
      "step": 20
    },
    {
      "epoch": 0.06693227091633466,
      "grad_norm": NaN,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.07649402390438247,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0796812749003984,
      "eval_loss": NaN,
      "eval_runtime": 7.5832,
      "eval_samples_per_second": 34.946,
      "eval_steps_per_second": 8.835,
      "step": 25
    },
    {
      "epoch": 0.08605577689243028,
      "grad_norm": NaN,
      "learning_rate": 6.167226819279528e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.09561752988047809,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.09561752988047809,
      "eval_loss": NaN,
      "eval_runtime": 7.5712,
      "eval_samples_per_second": 35.001,
      "eval_steps_per_second": 8.849,
      "step": 30
    },
    {
      "epoch": 0.1051792828685259,
      "grad_norm": NaN,
      "learning_rate": 3.832773180720475e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.11155378486055777,
      "eval_loss": NaN,
      "eval_runtime": 7.5795,
      "eval_samples_per_second": 34.963,
      "eval_steps_per_second": 8.84,
      "step": 35
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4635471548252160.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}