Hugging Face's logo

sn56b2
/
3a53dabf-2bdc-4497-b566-05ac392755fb

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
3a53dabf-2bdc-4497-b566-05ac392755fb
File size: 3,277 Bytes 
75183fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03204930662557781,
  "eval_steps": 13,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002465331278890601,
      "grad_norm": 26.539125442504883,
      "learning_rate": 1e-05,
      "loss": 3.6602,
      "step": 1
    },
    {
      "epoch": 0.002465331278890601,
      "eval_loss": 3.617913246154785,
      "eval_runtime": 29.3583,
      "eval_samples_per_second": 93.091,
      "eval_steps_per_second": 11.649,
      "step": 1
    },
    {
      "epoch": 0.004930662557781202,
      "grad_norm": 24.928752899169922,
      "learning_rate": 2e-05,
      "loss": 3.5913,
      "step": 2
    },
    {
      "epoch": 0.007395993836671803,
      "grad_norm": 25.013662338256836,
      "learning_rate": 3e-05,
      "loss": 3.4352,
      "step": 3
    },
    {
      "epoch": 0.009861325115562404,
      "grad_norm": 26.976316452026367,
      "learning_rate": 4e-05,
      "loss": 3.4006,
      "step": 4
    },
    {
      "epoch": 0.012326656394453005,
      "grad_norm": 19.72706413269043,
      "learning_rate": 5e-05,
      "loss": 3.0162,
      "step": 5
    },
    {
      "epoch": 0.014791987673343606,
      "grad_norm": 17.657188415527344,
      "learning_rate": 6e-05,
      "loss": 2.4475,
      "step": 6
    },
    {
      "epoch": 0.017257318952234205,
      "grad_norm": 22.630268096923828,
      "learning_rate": 7e-05,
      "loss": 1.8466,
      "step": 7
    },
    {
      "epoch": 0.019722650231124808,
      "grad_norm": 15.391894340515137,
      "learning_rate": 8e-05,
      "loss": 1.1958,
      "step": 8
    },
    {
      "epoch": 0.022187981510015407,
      "grad_norm": 17.156049728393555,
      "learning_rate": 9e-05,
      "loss": 0.9063,
      "step": 9
    },
    {
      "epoch": 0.02465331278890601,
      "grad_norm": 14.354949951171875,
      "learning_rate": 0.0001,
      "loss": 0.5376,
      "step": 10
    },
    {
      "epoch": 0.02711864406779661,
      "grad_norm": 4.375965595245361,
      "learning_rate": 9.98458666866564e-05,
      "loss": 0.1246,
      "step": 11
    },
    {
      "epoch": 0.029583975346687212,
      "grad_norm": 1.0381114482879639,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0747,
      "step": 12
    },
    {
      "epoch": 0.03204930662557781,
      "grad_norm": 2.4687139987945557,
      "learning_rate": 9.861849601988383e-05,
      "loss": 0.0975,
      "step": 13
    },
    {
      "epoch": 0.03204930662557781,
      "eval_loss": 0.04013116657733917,
      "eval_runtime": 19.4505,
      "eval_samples_per_second": 140.511,
      "eval_steps_per_second": 17.583,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.499584945717248e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}