Hugging Face's logo

Alibaba-NLP
/
WebWatcher-32B

TensorBoard
Safetensors
qwen2_5_vl
Model card Files
xet
Metrics Community
1
WebWatcher-32B
File size: 3,448 Bytes 
3a27430
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9533678756476682,
  "eval_steps": 500,
  "global_step": 144,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 1.8093507425794213,
      "learning_rate": 3e-06,
      "loss": 0.9129,
      "step": 10
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 0.7996825526135815,
      "learning_rate": 4.98814758473309e-06,
      "loss": 0.7274,
      "step": 20
    },
    {
      "epoch": 0.6217616580310881,
      "grad_norm": 0.5373843764254267,
      "learning_rate": 4.856095207084287e-06,
      "loss": 0.6513,
      "step": 30
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 0.4621175956467346,
      "learning_rate": 4.584994544724695e-06,
      "loss": 0.6373,
      "step": 40
    },
    {
      "epoch": 1.0207253886010363,
      "grad_norm": 0.47882928868708474,
      "learning_rate": 4.190844985952257e-06,
      "loss": 0.5683,
      "step": 50
    },
    {
      "epoch": 1.2279792746113989,
      "grad_norm": 0.4492344877710059,
      "learning_rate": 3.6969078233930235e-06,
      "loss": 0.6012,
      "step": 60
    },
    {
      "epoch": 1.4352331606217616,
      "grad_norm": 0.4358797089748146,
      "learning_rate": 3.132333455979202e-06,
      "loss": 0.5866,
      "step": 70
    },
    {
      "epoch": 1.6424870466321244,
      "grad_norm": 0.41894841115210807,
      "learning_rate": 2.530441037004994e-06,
      "loss": 0.5958,
      "step": 80
    },
    {
      "epoch": 1.849740932642487,
      "grad_norm": 0.4253754435893472,
      "learning_rate": 1.9267520972587754e-06,
      "loss": 0.5755,
      "step": 90
    },
    {
      "epoch": 2.0414507772020727,
      "grad_norm": 0.40951381645086515,
      "learning_rate": 1.3568941917384038e-06,
      "loss": 0.5319,
      "step": 100
    },
    {
      "epoch": 2.2487046632124352,
      "grad_norm": 0.41726111462999993,
      "learning_rate": 8.544982891981304e-07,
      "loss": 0.5579,
      "step": 110
    },
    {
      "epoch": 2.4559585492227978,
      "grad_norm": 0.4374441335411058,
      "learning_rate": 4.4921399305122264e-07,
      "loss": 0.5555,
      "step": 120
    },
    {
      "epoch": 2.6632124352331608,
      "grad_norm": 0.4146727228301452,
      "learning_rate": 1.649597281686302e-07,
      "loss": 0.5625,
      "step": 130
    },
    {
      "epoch": 2.8704663212435233,
      "grad_norm": 0.4451658295553321,
      "learning_rate": 1.851116126993402e-08,
      "loss": 0.5588,
      "step": 140
    },
    {
      "epoch": 2.9533678756476682,
      "step": 144,
      "total_flos": 887572825899008.0,
      "train_loss": 0.6164978990952173,
      "train_runtime": 16386.6242,
      "train_samples_per_second": 1.127,
      "train_steps_per_second": 0.009
    }
  ],
  "logging_steps": 10,
  "max_steps": 144,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 887572825899008.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}