Hugging Face's logo

kevinoli
/
clip-finetuned-csu-p14-336-e3l37-l

TensorBoard
Safetensors
clip
Model card Files Metrics Community
clip-finetuned-csu-p14-336-e3l37-l
File size: 7,506 Bytes 
6fd5841
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
 
{
  "best_metric": 0.6983720660209656,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l37-l/checkpoint-8500",
  "epoch": 0.9568839356073399,
  "eval_steps": 500,
  "global_step": 8500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.056287290329843524,
      "grad_norm": 96.92656707763672,
      "learning_rate": 2.9437127096701565e-07,
      "loss": 0.3748,
      "step": 500
    },
    {
      "epoch": 0.056287290329843524,
      "eval_loss": 1.2226382493972778,
      "eval_runtime": 131.2779,
      "eval_samples_per_second": 15.037,
      "eval_steps_per_second": 1.882,
      "step": 500
    },
    {
      "epoch": 0.11257458065968705,
      "grad_norm": 402.31158447265625,
      "learning_rate": 2.887425419340313e-07,
      "loss": 0.3057,
      "step": 1000
    },
    {
      "epoch": 0.11257458065968705,
      "eval_loss": 1.0702259540557861,
      "eval_runtime": 131.0109,
      "eval_samples_per_second": 15.067,
      "eval_steps_per_second": 1.885,
      "step": 1000
    },
    {
      "epoch": 0.16886187098953057,
      "grad_norm": 515.0911865234375,
      "learning_rate": 2.831138129010469e-07,
      "loss": 0.2239,
      "step": 1500
    },
    {
      "epoch": 0.16886187098953057,
      "eval_loss": 0.9957238435745239,
      "eval_runtime": 134.8377,
      "eval_samples_per_second": 14.64,
      "eval_steps_per_second": 1.832,
      "step": 1500
    },
    {
      "epoch": 0.2251491613193741,
      "grad_norm": 3.1967105865478516,
      "learning_rate": 2.774850838680626e-07,
      "loss": 0.2229,
      "step": 2000
    },
    {
      "epoch": 0.2251491613193741,
      "eval_loss": 0.9504629373550415,
      "eval_runtime": 129.0169,
      "eval_samples_per_second": 15.3,
      "eval_steps_per_second": 1.914,
      "step": 2000
    },
    {
      "epoch": 0.2814364516492176,
      "grad_norm": 276.22998046875,
      "learning_rate": 2.718563548350782e-07,
      "loss": 0.2098,
      "step": 2500
    },
    {
      "epoch": 0.2814364516492176,
      "eval_loss": 0.9006705284118652,
      "eval_runtime": 129.1816,
      "eval_samples_per_second": 15.281,
      "eval_steps_per_second": 1.912,
      "step": 2500
    },
    {
      "epoch": 0.33772374197906113,
      "grad_norm": 1105.317138671875,
      "learning_rate": 2.6622762580209386e-07,
      "loss": 0.1938,
      "step": 3000
    },
    {
      "epoch": 0.33772374197906113,
      "eval_loss": 0.8782906532287598,
      "eval_runtime": 128.6387,
      "eval_samples_per_second": 15.345,
      "eval_steps_per_second": 1.92,
      "step": 3000
    },
    {
      "epoch": 0.39401103230890466,
      "grad_norm": 0.00043465400813147426,
      "learning_rate": 2.605988967691095e-07,
      "loss": 0.1688,
      "step": 3500
    },
    {
      "epoch": 0.39401103230890466,
      "eval_loss": 0.8405746221542358,
      "eval_runtime": 128.6989,
      "eval_samples_per_second": 15.338,
      "eval_steps_per_second": 1.919,
      "step": 3500
    },
    {
      "epoch": 0.4502983226387482,
      "grad_norm": 0.027426382526755333,
      "learning_rate": 2.549701677361252e-07,
      "loss": 0.1457,
      "step": 4000
    },
    {
      "epoch": 0.4502983226387482,
      "eval_loss": 0.813768208026886,
      "eval_runtime": 128.7209,
      "eval_samples_per_second": 15.336,
      "eval_steps_per_second": 1.919,
      "step": 4000
    },
    {
      "epoch": 0.5065856129685917,
      "grad_norm": 0.0012935090344399214,
      "learning_rate": 2.4934143870314085e-07,
      "loss": 0.179,
      "step": 4500
    },
    {
      "epoch": 0.5065856129685917,
      "eval_loss": 0.7965527176856995,
      "eval_runtime": 128.3969,
      "eval_samples_per_second": 15.374,
      "eval_steps_per_second": 1.924,
      "step": 4500
    },
    {
      "epoch": 0.5628729032984352,
      "grad_norm": 0.0017458726651966572,
      "learning_rate": 2.4371270967015646e-07,
      "loss": 0.1224,
      "step": 5000
    },
    {
      "epoch": 0.5628729032984352,
      "eval_loss": 0.7788484692573547,
      "eval_runtime": 128.4939,
      "eval_samples_per_second": 15.363,
      "eval_steps_per_second": 1.922,
      "step": 5000
    },
    {
      "epoch": 0.6191601936282788,
      "grad_norm": 65.76844787597656,
      "learning_rate": 2.380839806371721e-07,
      "loss": 0.1551,
      "step": 5500
    },
    {
      "epoch": 0.6191601936282788,
      "eval_loss": 0.7626588344573975,
      "eval_runtime": 128.7302,
      "eval_samples_per_second": 15.334,
      "eval_steps_per_second": 1.919,
      "step": 5500
    },
    {
      "epoch": 0.6754474839581223,
      "grad_norm": 5.014094829559326,
      "learning_rate": 2.3245525160418776e-07,
      "loss": 0.1721,
      "step": 6000
    },
    {
      "epoch": 0.6754474839581223,
      "eval_loss": 0.7464810609817505,
      "eval_runtime": 128.749,
      "eval_samples_per_second": 15.332,
      "eval_steps_per_second": 1.918,
      "step": 6000
    },
    {
      "epoch": 0.7317347742879657,
      "grad_norm": 0.0022696161177009344,
      "learning_rate": 2.268265225712034e-07,
      "loss": 0.1532,
      "step": 6500
    },
    {
      "epoch": 0.7317347742879657,
      "eval_loss": 0.7335842251777649,
      "eval_runtime": 128.8165,
      "eval_samples_per_second": 15.324,
      "eval_steps_per_second": 1.917,
      "step": 6500
    },
    {
      "epoch": 0.7880220646178093,
      "grad_norm": 5.508715730684344e-06,
      "learning_rate": 2.2119779353821906e-07,
      "loss": 0.1991,
      "step": 7000
    },
    {
      "epoch": 0.7880220646178093,
      "eval_loss": 0.7244272232055664,
      "eval_runtime": 128.9211,
      "eval_samples_per_second": 15.312,
      "eval_steps_per_second": 1.916,
      "step": 7000
    },
    {
      "epoch": 0.8443093549476528,
      "grad_norm": 0.30320531129837036,
      "learning_rate": 2.155690645052347e-07,
      "loss": 0.1551,
      "step": 7500
    },
    {
      "epoch": 0.8443093549476528,
      "eval_loss": 0.718368411064148,
      "eval_runtime": 128.8149,
      "eval_samples_per_second": 15.324,
      "eval_steps_per_second": 1.917,
      "step": 7500
    },
    {
      "epoch": 0.9005966452774964,
      "grad_norm": 1.9788849385804497e-05,
      "learning_rate": 2.0994033547225037e-07,
      "loss": 0.1439,
      "step": 8000
    },
    {
      "epoch": 0.9005966452774964,
      "eval_loss": 0.7040167450904846,
      "eval_runtime": 128.4921,
      "eval_samples_per_second": 15.363,
      "eval_steps_per_second": 1.922,
      "step": 8000
    },
    {
      "epoch": 0.9568839356073399,
      "grad_norm": 1.0750063665909693e-06,
      "learning_rate": 2.04311606439266e-07,
      "loss": 0.1361,
      "step": 8500
    },
    {
      "epoch": 0.9568839356073399,
      "eval_loss": 0.6983720660209656,
      "eval_runtime": 128.5929,
      "eval_samples_per_second": 15.351,
      "eval_steps_per_second": 1.921,
      "step": 8500
    }
  ],
  "logging_steps": 500,
  "max_steps": 26649,
  "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": 3058665502412520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}