Hugging Face's logo

luciagil
/
Human-action-convnext

Image Classification
Transformers
TensorBoard
Safetensors
convnext
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
luciagil commited on
Commit
8ad9a9d
·
verified ·
1 Parent(s): 13762cf

Training in progress, epoch 0

Browse files
Files changed (6) hide show
  1. all_results.json +8 -0
  2. model.safetensors +1 -1
  3. runs/Apr06_14-47-21_a39577a7e444/events.out.tfevents.1712414858.a39577a7e444.25850.4 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +218 -0
  6. training_args.bin +1 -1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.97,
3
+ "total_flos": 7.528934622159176e+17,
4
+ "train_loss": 0.8272387634994637,
5
+ "train_runtime": 368.3522,
6
+ "train_samples_per_second": 82.095,
7
+ "train_steps_per_second": 0.635
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c74e83b09640f3a3b4484416ee014c5c535feb64b2deffdcf8a4dfd12583f1ec
3
  size 111347932
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd577926571470642b62b3c43c656fb6e1fc1ebe21b659db1a9af0aa0b2bade
3
  size 111347932
runs/Apr06_14-47-21_a39577a7e444/events.out.tfevents.1712414858.a39577a7e444.25850.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce8c6e43d4505cb656b6f2376159760ab64b06cde0bc4e5a9ca19c5bc921bc7
3
+ size 7137
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.97,
3
+ "total_flos": 7.528934622159176e+17,
4
+ "train_loss": 0.8272387634994637,
5
+ "train_runtime": 368.3522,
6
+ "train_samples_per_second": 82.095,
7
+ "train_steps_per_second": 0.635
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7916666666666666,
3
+ "best_model_checkpoint": "Human-action-convnext/checkpoint-234",
4
+ "epoch": 2.9714285714285715,
5
+ "eval_steps": 500,
6
+ "global_step": 234,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13,
13
+ "grad_norm": 2.9202792644500732,
14
+ "learning_rate": 2.0833333333333336e-05,
15
+ "loss": 0.985,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.25,
20
+ "grad_norm": 2.8895421028137207,
21
+ "learning_rate": 4.166666666666667e-05,
22
+ "loss": 0.9998,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.38,
27
+ "grad_norm": 3.1696712970733643,
28
+ "learning_rate": 4.8571428571428576e-05,
29
+ "loss": 0.9553,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.51,
34
+ "grad_norm": 3.572809934616089,
35
+ "learning_rate": 4.6190476190476194e-05,
36
+ "loss": 0.9258,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.63,
41
+ "grad_norm": 4.679945945739746,
42
+ "learning_rate": 4.380952380952381e-05,
43
+ "loss": 0.9274,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.76,
48
+ "grad_norm": 5.121299743652344,
49
+ "learning_rate": 4.1428571428571437e-05,
50
+ "loss": 0.8875,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.89,
55
+ "grad_norm": 4.941247940063477,
56
+ "learning_rate": 3.904761904761905e-05,
57
+ "loss": 0.9287,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.99,
62
+ "eval_accuracy": 0.7726190476190476,
63
+ "eval_loss": 0.809448778629303,
64
+ "eval_runtime": 31.5426,
65
+ "eval_samples_per_second": 79.892,
66
+ "eval_steps_per_second": 2.505,
67
+ "step": 78
68
+ },
69
+ {
70
+ "epoch": 1.02,
71
+ "grad_norm": 3.490706205368042,
72
+ "learning_rate": 3.6666666666666666e-05,
73
+ "loss": 0.8684,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 1.14,
78
+ "grad_norm": 3.2836825847625732,
79
+ "learning_rate": 3.428571428571429e-05,
80
+ "loss": 0.8442,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 1.27,
85
+ "grad_norm": 3.463827610015869,
86
+ "learning_rate": 3.19047619047619e-05,
87
+ "loss": 0.8199,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 1.4,
92
+ "grad_norm": 4.105288982391357,
93
+ "learning_rate": 2.9523809523809526e-05,
94
+ "loss": 0.7896,
95
+ "step": 110
96
+ },
97
+ {
98
+ "epoch": 1.52,
99
+ "grad_norm": 3.594646692276001,
100
+ "learning_rate": 2.714285714285714e-05,
101
+ "loss": 0.8322,
102
+ "step": 120
103
+ },
104
+ {
105
+ "epoch": 1.65,
106
+ "grad_norm": 4.090346813201904,
107
+ "learning_rate": 2.4761904761904762e-05,
108
+ "loss": 0.7476,
109
+ "step": 130
110
+ },
111
+ {
112
+ "epoch": 1.78,
113
+ "grad_norm": 4.468383312225342,
114
+ "learning_rate": 2.2380952380952384e-05,
115
+ "loss": 0.7725,
116
+ "step": 140
117
+ },
118
+ {
119
+ "epoch": 1.9,
120
+ "grad_norm": 4.0550055503845215,
121
+ "learning_rate": 2e-05,
122
+ "loss": 0.8263,
123
+ "step": 150
124
+ },
125
+ {
126
+ "epoch": 1.99,
127
+ "eval_accuracy": 0.7876984126984127,
128
+ "eval_loss": 0.7395461201667786,
129
+ "eval_runtime": 32.7967,
130
+ "eval_samples_per_second": 76.837,
131
+ "eval_steps_per_second": 2.409,
132
+ "step": 157
133
+ },
134
+ {
135
+ "epoch": 2.03,
136
+ "grad_norm": 3.7557804584503174,
137
+ "learning_rate": 1.761904761904762e-05,
138
+ "loss": 0.7784,
139
+ "step": 160
140
+ },
141
+ {
142
+ "epoch": 2.16,
143
+ "grad_norm": 3.753110647201538,
144
+ "learning_rate": 1.5238095238095241e-05,
145
+ "loss": 0.7744,
146
+ "step": 170
147
+ },
148
+ {
149
+ "epoch": 2.29,
150
+ "grad_norm": 3.3746166229248047,
151
+ "learning_rate": 1.2857142857142857e-05,
152
+ "loss": 0.7588,
153
+ "step": 180
154
+ },
155
+ {
156
+ "epoch": 2.41,
157
+ "grad_norm": 3.5075440406799316,
158
+ "learning_rate": 1.0476190476190477e-05,
159
+ "loss": 0.7543,
160
+ "step": 190
161
+ },
162
+ {
163
+ "epoch": 2.54,
164
+ "grad_norm": 3.45804762840271,
165
+ "learning_rate": 8.095238095238097e-06,
166
+ "loss": 0.7179,
167
+ "step": 200
168
+ },
169
+ {
170
+ "epoch": 2.67,
171
+ "grad_norm": 4.391757965087891,
172
+ "learning_rate": 5.7142857142857145e-06,
173
+ "loss": 0.665,
174
+ "step": 210
175
+ },
176
+ {
177
+ "epoch": 2.79,
178
+ "grad_norm": 3.0836093425750732,
179
+ "learning_rate": 3.3333333333333333e-06,
180
+ "loss": 0.7787,
181
+ "step": 220
182
+ },
183
+ {
184
+ "epoch": 2.92,
185
+ "grad_norm": 4.827792644500732,
186
+ "learning_rate": 9.523809523809526e-07,
187
+ "loss": 0.7472,
188
+ "step": 230
189
+ },
190
+ {
191
+ "epoch": 2.97,
192
+ "eval_accuracy": 0.7916666666666666,
193
+ "eval_loss": 0.7180711627006531,
194
+ "eval_runtime": 32.3605,
195
+ "eval_samples_per_second": 77.873,
196
+ "eval_steps_per_second": 2.441,
197
+ "step": 234
198
+ },
199
+ {
200
+ "epoch": 2.97,
201
+ "step": 234,
202
+ "total_flos": 7.528934622159176e+17,
203
+ "train_loss": 0.8272387634994637,
204
+ "train_runtime": 368.3522,
205
+ "train_samples_per_second": 82.095,
206
+ "train_steps_per_second": 0.635
207
+ }
208
+ ],
209
+ "logging_steps": 10,
210
+ "max_steps": 234,
211
+ "num_input_tokens_seen": 0,
212
+ "num_train_epochs": 3,
213
+ "save_steps": 500,
214
+ "total_flos": 7.528934622159176e+17,
215
+ "train_batch_size": 32,
216
+ "trial_name": null,
217
+ "trial_params": null
218
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4ace3d1b526f952b6d18a7d39a9d7fa0e1b2e0f2fda05242756ca15e81b144a
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6a2032b2d03dd93f6f420ba6c0ec82022b62953a81c39f7a481acc27155e71
3
  size 4920