Hugging Face's logo

andrewatef
/
Qwen2.5-FTV02

Safetensors
Model card Files Community
Qwen2.5-FTV02
File size: 3,199 Bytes 
c94d46d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2731707317073171,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01951219512195122,
      "grad_norm": 0.14488260447978973,
      "learning_rate": 0.00019934683213585893,
      "loss": 0.6356,
      "step": 10
    },
    {
      "epoch": 0.03902439024390244,
      "grad_norm": 0.1634250283241272,
      "learning_rate": 0.00019804049640757677,
      "loss": 0.4368,
      "step": 20
    },
    {
      "epoch": 0.05853658536585366,
      "grad_norm": 0.1504327356815338,
      "learning_rate": 0.0001967341606792946,
      "loss": 0.407,
      "step": 30
    },
    {
      "epoch": 0.07804878048780488,
      "grad_norm": 0.16282524168491364,
      "learning_rate": 0.00019542782495101242,
      "loss": 0.3788,
      "step": 40
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.17505913972854614,
      "learning_rate": 0.00019412148922273026,
      "loss": 0.3705,
      "step": 50
    },
    {
      "epoch": 0.11707317073170732,
      "grad_norm": 0.18271876871585846,
      "learning_rate": 0.00019281515349444807,
      "loss": 0.3654,
      "step": 60
    },
    {
      "epoch": 0.13658536585365855,
      "grad_norm": 0.1547907590866089,
      "learning_rate": 0.0001915088177661659,
      "loss": 0.3845,
      "step": 70
    },
    {
      "epoch": 0.15609756097560976,
      "grad_norm": 0.1806977242231369,
      "learning_rate": 0.00019020248203788375,
      "loss": 0.362,
      "step": 80
    },
    {
      "epoch": 0.17560975609756097,
      "grad_norm": 0.16502083837985992,
      "learning_rate": 0.00018889614630960156,
      "loss": 0.3436,
      "step": 90
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.15947739779949188,
      "learning_rate": 0.0001875898105813194,
      "loss": 0.3221,
      "step": 100
    },
    {
      "epoch": 0.2146341463414634,
      "grad_norm": 0.16028478741645813,
      "learning_rate": 0.00018628347485303724,
      "loss": 0.3291,
      "step": 110
    },
    {
      "epoch": 0.23414634146341465,
      "grad_norm": 0.16755621135234833,
      "learning_rate": 0.00018497713912475508,
      "loss": 0.3454,
      "step": 120
    },
    {
      "epoch": 0.25365853658536586,
      "grad_norm": 0.17687192559242249,
      "learning_rate": 0.00018367080339647292,
      "loss": 0.3265,
      "step": 130
    },
    {
      "epoch": 0.2731707317073171,
      "grad_norm": 0.12853658199310303,
      "learning_rate": 0.00018236446766819073,
      "loss": 0.3136,
      "step": 140
    }
  ],
  "logging_steps": 10,
  "max_steps": 1536,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9383900027387904.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}