Hugging Face's logo

kevinoli
/
clip-finetuned-csu-p14-336-e3l56-l

Zero-Shot Image Classification
Transformers
TensorBoard
Safetensors
clip
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
clip-finetuned-csu-p14-336-e3l56-l
File size: 4,344 Bytes 
0d1c386
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.1064503192901611,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l56-l/checkpoint-4500",
  "epoch": 0.8290346352247605,
  "eval_steps": 500,
  "global_step": 4500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09211495946941783,
      "grad_norm": 18.028329849243164,
      "learning_rate": 4.846475067550971e-06,
      "loss": 0.2253,
      "step": 500
    },
    {
      "epoch": 0.09211495946941783,
      "eval_loss": 1.4693936109542847,
      "eval_runtime": 74.2802,
      "eval_samples_per_second": 16.249,
      "eval_steps_per_second": 2.033,
      "step": 500
    },
    {
      "epoch": 0.18422991893883567,
      "grad_norm": 0.4609026312828064,
      "learning_rate": 4.692950135101941e-06,
      "loss": 0.2544,
      "step": 1000
    },
    {
      "epoch": 0.18422991893883567,
      "eval_loss": 1.5420819520950317,
      "eval_runtime": 74.0766,
      "eval_samples_per_second": 16.294,
      "eval_steps_per_second": 2.038,
      "step": 1000
    },
    {
      "epoch": 0.2763448784082535,
      "grad_norm": 71.96737670898438,
      "learning_rate": 4.5394252026529115e-06,
      "loss": 0.3236,
      "step": 1500
    },
    {
      "epoch": 0.2763448784082535,
      "eval_loss": 1.4642689228057861,
      "eval_runtime": 74.2336,
      "eval_samples_per_second": 16.259,
      "eval_steps_per_second": 2.034,
      "step": 1500
    },
    {
      "epoch": 0.36845983787767134,
      "grad_norm": 6.366127069945549e-10,
      "learning_rate": 4.385900270203882e-06,
      "loss": 0.1888,
      "step": 2000
    },
    {
      "epoch": 0.36845983787767134,
      "eval_loss": 1.3193777799606323,
      "eval_runtime": 76.1214,
      "eval_samples_per_second": 15.856,
      "eval_steps_per_second": 1.984,
      "step": 2000
    },
    {
      "epoch": 0.46057479734708917,
      "grad_norm": 452.8532409667969,
      "learning_rate": 4.232375337754851e-06,
      "loss": 0.2563,
      "step": 2500
    },
    {
      "epoch": 0.46057479734708917,
      "eval_loss": 1.37644362449646,
      "eval_runtime": 76.3265,
      "eval_samples_per_second": 15.814,
      "eval_steps_per_second": 1.978,
      "step": 2500
    },
    {
      "epoch": 0.552689756816507,
      "grad_norm": 0.0002858435327652842,
      "learning_rate": 4.078850405305822e-06,
      "loss": 0.2794,
      "step": 3000
    },
    {
      "epoch": 0.552689756816507,
      "eval_loss": 1.3007307052612305,
      "eval_runtime": 76.3512,
      "eval_samples_per_second": 15.809,
      "eval_steps_per_second": 1.978,
      "step": 3000
    },
    {
      "epoch": 0.6448047162859248,
      "grad_norm": 0.324462890625,
      "learning_rate": 3.925325472856792e-06,
      "loss": 0.1749,
      "step": 3500
    },
    {
      "epoch": 0.6448047162859248,
      "eval_loss": 1.3360542058944702,
      "eval_runtime": 74.5379,
      "eval_samples_per_second": 16.193,
      "eval_steps_per_second": 2.026,
      "step": 3500
    },
    {
      "epoch": 0.7369196757553427,
      "grad_norm": 76.63452911376953,
      "learning_rate": 3.7718005404077624e-06,
      "loss": 0.2672,
      "step": 4000
    },
    {
      "epoch": 0.7369196757553427,
      "eval_loss": 1.268362283706665,
      "eval_runtime": 76.6253,
      "eval_samples_per_second": 15.752,
      "eval_steps_per_second": 1.971,
      "step": 4000
    },
    {
      "epoch": 0.8290346352247605,
      "grad_norm": 1.9390699863433838,
      "learning_rate": 3.6182756079587327e-06,
      "loss": 0.218,
      "step": 4500
    },
    {
      "epoch": 0.8290346352247605,
      "eval_loss": 1.1064503192901611,
      "eval_runtime": 75.0503,
      "eval_samples_per_second": 16.083,
      "eval_steps_per_second": 2.012,
      "step": 4500
    }
  ],
  "logging_steps": 500,
  "max_steps": 16284,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1619632097372520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}