Hugging Face's logo

kevinoli
/
clip-finetuned-csu-p14-336-e6l56-l

Zero-Shot Image Classification
Transformers
TensorBoard
Safetensors
clip
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
clip-finetuned-csu-p14-336-e6l56-l
File size: 4,353 Bytes 
ca7e6d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.0961644649505615,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e6l56-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": 0.49671515822410583,
      "learning_rate": 4.923237533775486e-06,
      "loss": 0.2159,
      "step": 500
    },
    {
      "epoch": 0.09211495946941783,
      "eval_loss": 1.4818799495697021,
      "eval_runtime": 72.2844,
      "eval_samples_per_second": 16.698,
      "eval_steps_per_second": 2.089,
      "step": 500
    },
    {
      "epoch": 0.18422991893883567,
      "grad_norm": 0.0015633106231689453,
      "learning_rate": 4.846475067550971e-06,
      "loss": 0.2648,
      "step": 1000
    },
    {
      "epoch": 0.18422991893883567,
      "eval_loss": 1.4225908517837524,
      "eval_runtime": 73.6999,
      "eval_samples_per_second": 16.377,
      "eval_steps_per_second": 2.049,
      "step": 1000
    },
    {
      "epoch": 0.2763448784082535,
      "grad_norm": 0.047471947968006134,
      "learning_rate": 4.769712601326456e-06,
      "loss": 0.328,
      "step": 1500
    },
    {
      "epoch": 0.2763448784082535,
      "eval_loss": 1.412400245666504,
      "eval_runtime": 74.9915,
      "eval_samples_per_second": 16.095,
      "eval_steps_per_second": 2.014,
      "step": 1500
    },
    {
      "epoch": 0.36845983787767134,
      "grad_norm": 3.9284778208248383e-10,
      "learning_rate": 4.692950135101941e-06,
      "loss": 0.1813,
      "step": 2000
    },
    {
      "epoch": 0.36845983787767134,
      "eval_loss": 1.2844351530075073,
      "eval_runtime": 74.7649,
      "eval_samples_per_second": 16.144,
      "eval_steps_per_second": 2.02,
      "step": 2000
    },
    {
      "epoch": 0.46057479734708917,
      "grad_norm": 514.6055297851562,
      "learning_rate": 4.616187668877426e-06,
      "loss": 0.4836,
      "step": 2500
    },
    {
      "epoch": 0.46057479734708917,
      "eval_loss": 1.301351547241211,
      "eval_runtime": 74.7994,
      "eval_samples_per_second": 16.136,
      "eval_steps_per_second": 2.019,
      "step": 2500
    },
    {
      "epoch": 0.552689756816507,
      "grad_norm": 127.98405456542969,
      "learning_rate": 4.5394252026529115e-06,
      "loss": 0.2803,
      "step": 3000
    },
    {
      "epoch": 0.552689756816507,
      "eval_loss": 1.1920161247253418,
      "eval_runtime": 75.5447,
      "eval_samples_per_second": 15.977,
      "eval_steps_per_second": 1.999,
      "step": 3000
    },
    {
      "epoch": 0.6448047162859248,
      "grad_norm": 0.048586923629045486,
      "learning_rate": 4.462662736428396e-06,
      "loss": 0.2056,
      "step": 3500
    },
    {
      "epoch": 0.6448047162859248,
      "eval_loss": 1.1428992748260498,
      "eval_runtime": 75.7202,
      "eval_samples_per_second": 15.94,
      "eval_steps_per_second": 1.994,
      "step": 3500
    },
    {
      "epoch": 0.7369196757553427,
      "grad_norm": 228.63064575195312,
      "learning_rate": 4.385900270203882e-06,
      "loss": 0.2174,
      "step": 4000
    },
    {
      "epoch": 0.7369196757553427,
      "eval_loss": 1.1957736015319824,
      "eval_runtime": 74.1933,
      "eval_samples_per_second": 16.268,
      "eval_steps_per_second": 2.035,
      "step": 4000
    },
    {
      "epoch": 0.8290346352247605,
      "grad_norm": 226.2799530029297,
      "learning_rate": 4.3091378039793666e-06,
      "loss": 0.2236,
      "step": 4500
    },
    {
      "epoch": 0.8290346352247605,
      "eval_loss": 1.0961644649505615,
      "eval_runtime": 74.6968,
      "eval_samples_per_second": 16.159,
      "eval_steps_per_second": 2.022,
      "step": 4500
    }
  ],
  "logging_steps": 500,
  "max_steps": 32568,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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
}