Hugging Face's logo

kevinoli
/
clip-finetuned-csu-p14-336-e3l58-l

Zero-Shot Image Classification
Transformers
TensorBoard
Safetensors
clip
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
clip-finetuned-csu-p14-336-e3l58-l
File size: 5,891 Bytes 
02de15f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
 
{
  "best_metric": 1.0182703733444214,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l58-l/checkpoint-6500",
  "epoch": 1.1974944731024317,
  "eval_steps": 500,
  "global_step": 6500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09211495946941783,
      "grad_norm": 19.808820724487305,
      "learning_rate": 4.84647506755097e-08,
      "loss": 0.3758,
      "step": 500
    },
    {
      "epoch": 0.09211495946941783,
      "eval_loss": 1.418845295906067,
      "eval_runtime": 75.2377,
      "eval_samples_per_second": 16.042,
      "eval_steps_per_second": 2.007,
      "step": 500
    },
    {
      "epoch": 0.18422991893883567,
      "grad_norm": 76.37991333007812,
      "learning_rate": 4.69295013510194e-08,
      "loss": 0.4108,
      "step": 1000
    },
    {
      "epoch": 0.18422991893883567,
      "eval_loss": 1.3513683080673218,
      "eval_runtime": 74.9686,
      "eval_samples_per_second": 16.1,
      "eval_steps_per_second": 2.014,
      "step": 1000
    },
    {
      "epoch": 0.2763448784082535,
      "grad_norm": 0.5795987844467163,
      "learning_rate": 4.539425202652911e-08,
      "loss": 0.4335,
      "step": 1500
    },
    {
      "epoch": 0.2763448784082535,
      "eval_loss": 1.2895005941390991,
      "eval_runtime": 76.713,
      "eval_samples_per_second": 15.734,
      "eval_steps_per_second": 1.968,
      "step": 1500
    },
    {
      "epoch": 0.36845983787767134,
      "grad_norm": 0.1463615745306015,
      "learning_rate": 4.385900270203881e-08,
      "loss": 0.3436,
      "step": 2000
    },
    {
      "epoch": 0.36845983787767134,
      "eval_loss": 1.2414860725402832,
      "eval_runtime": 76.9749,
      "eval_samples_per_second": 15.68,
      "eval_steps_per_second": 1.962,
      "step": 2000
    },
    {
      "epoch": 0.46057479734708917,
      "grad_norm": 323.8576354980469,
      "learning_rate": 4.232375337754851e-08,
      "loss": 0.366,
      "step": 2500
    },
    {
      "epoch": 0.46057479734708917,
      "eval_loss": 1.1949334144592285,
      "eval_runtime": 77.0381,
      "eval_samples_per_second": 15.668,
      "eval_steps_per_second": 1.96,
      "step": 2500
    },
    {
      "epoch": 0.552689756816507,
      "grad_norm": 339.28533935546875,
      "learning_rate": 4.078850405305821e-08,
      "loss": 0.3191,
      "step": 3000
    },
    {
      "epoch": 0.552689756816507,
      "eval_loss": 1.1560280323028564,
      "eval_runtime": 77.0026,
      "eval_samples_per_second": 15.675,
      "eval_steps_per_second": 1.961,
      "step": 3000
    },
    {
      "epoch": 0.6448047162859248,
      "grad_norm": 60.27859878540039,
      "learning_rate": 3.925325472856792e-08,
      "loss": 0.2779,
      "step": 3500
    },
    {
      "epoch": 0.6448047162859248,
      "eval_loss": 1.1233855485916138,
      "eval_runtime": 76.9006,
      "eval_samples_per_second": 15.696,
      "eval_steps_per_second": 1.964,
      "step": 3500
    },
    {
      "epoch": 0.7369196757553427,
      "grad_norm": 18.268455505371094,
      "learning_rate": 3.7718005404077616e-08,
      "loss": 0.2942,
      "step": 4000
    },
    {
      "epoch": 0.7369196757553427,
      "eval_loss": 1.0993207693099976,
      "eval_runtime": 77.2834,
      "eval_samples_per_second": 15.618,
      "eval_steps_per_second": 1.954,
      "step": 4000
    },
    {
      "epoch": 0.8290346352247605,
      "grad_norm": 505.22723388671875,
      "learning_rate": 3.6182756079587324e-08,
      "loss": 0.2615,
      "step": 4500
    },
    {
      "epoch": 0.8290346352247605,
      "eval_loss": 1.080470085144043,
      "eval_runtime": 77.1214,
      "eval_samples_per_second": 15.651,
      "eval_steps_per_second": 1.958,
      "step": 4500
    },
    {
      "epoch": 0.9211495946941783,
      "grad_norm": 1.2971173524856567,
      "learning_rate": 3.4647506755097025e-08,
      "loss": 0.2715,
      "step": 5000
    },
    {
      "epoch": 0.9211495946941783,
      "eval_loss": 1.0614728927612305,
      "eval_runtime": 77.2982,
      "eval_samples_per_second": 15.615,
      "eval_steps_per_second": 1.953,
      "step": 5000
    },
    {
      "epoch": 1.013264554163596,
      "grad_norm": 0.17611829936504364,
      "learning_rate": 3.3112257430606727e-08,
      "loss": 0.2509,
      "step": 5500
    },
    {
      "epoch": 1.013264554163596,
      "eval_loss": 1.0461839437484741,
      "eval_runtime": 75.3494,
      "eval_samples_per_second": 16.019,
      "eval_steps_per_second": 2.004,
      "step": 5500
    },
    {
      "epoch": 1.105379513633014,
      "grad_norm": 228.2562713623047,
      "learning_rate": 3.1577008106116435e-08,
      "loss": 0.2653,
      "step": 6000
    },
    {
      "epoch": 1.105379513633014,
      "eval_loss": 1.0305675268173218,
      "eval_runtime": 77.0542,
      "eval_samples_per_second": 15.664,
      "eval_steps_per_second": 1.96,
      "step": 6000
    },
    {
      "epoch": 1.1974944731024317,
      "grad_norm": 432.4784240722656,
      "learning_rate": 3.0041758781626136e-08,
      "loss": 0.2199,
      "step": 6500
    },
    {
      "epoch": 1.1974944731024317,
      "eval_loss": 1.0182703733444214,
      "eval_runtime": 76.296,
      "eval_samples_per_second": 15.82,
      "eval_steps_per_second": 1.979,
      "step": 6500
    }
  ],
  "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": 2339148799892520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}