Hugging Face's logo

robertellis-digica
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
robertellis-digica commited on
Commit
f63e19b
·
verified ·
1 Parent(s): 5c236fe

Training in progress, epoch 0

Browse files
Files changed (7) hide show
  1. all_results.json +8 -0
  2. model.safetensors +1 -1
  3. runs/Dec13_12-03-40_2fa76351bb1a/events.out.tfevents.1734096022.2fa76351bb1a.6043.1 +2 -2
  4. runs/Dec13_14-41-40_2fa76351bb1a/events.out.tfevents.1734100919.2fa76351bb1a.6043.2 +3 -0
  5. test_results.json +8 -0
  6. trainer_state.json +194 -0
  7. training_args.bin +1 -1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.22972972972973,
3
+ "eval_accuracy": 0.9354838709677419,
4
+ "eval_loss": 0.3937394320964813,
5
+ "eval_runtime": 67.6788,
6
+ "eval_samples_per_second": 2.29,
7
+ "eval_steps_per_second": 0.296
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e14b522f48c10c4848af066e36a19bc8306a4a309f93048ba97710be41de8720
3
  size 344961984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc53442228f91f3d0342ecbdc518301bc3d00e698ddcd0ede2a5ad22aa79bd5
3
  size 344961984
runs/Dec13_12-03-40_2fa76351bb1a/events.out.tfevents.1734096022.2fa76351bb1a.6043.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc07aa1b905d5ad4b68bd8b50754006cca09a9aca01f524dca2cd4bd34eaa926
3
- size 411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:389e1f13268fdf80f01bdb624271d2f1ede218b474ccf1d1fb5698106d2df20d
3
+ size 734
runs/Dec13_14-41-40_2fa76351bb1a/events.out.tfevents.1734100919.2fa76351bb1a.6043.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4eaff13256d46b1844e6db56b64d13d7b98ec23a8e4014fb7dad76d189b2eb4
3
+ size 6696
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.22972972972973,
3
+ "eval_accuracy": 0.9354838709677419,
4
+ "eval_loss": 0.3937394320964813,
5
+ "eval_runtime": 67.6788,
6
+ "eval_samples_per_second": 2.29,
7
+ "eval_steps_per_second": 0.296
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8428571428571429,
3
+ "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
4
+ "epoch": 3.22972972972973,
5
+ "eval_steps": 500,
6
+ "global_step": 148,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06756756756756757,
13
+ "grad_norm": 8.218301773071289,
14
+ "learning_rate": 3.3333333333333335e-05,
15
+ "loss": 2.355,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.13513513513513514,
20
+ "grad_norm": 7.125568389892578,
21
+ "learning_rate": 4.81203007518797e-05,
22
+ "loss": 2.2296,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.20270270270270271,
27
+ "grad_norm": 7.601614475250244,
28
+ "learning_rate": 4.43609022556391e-05,
29
+ "loss": 2.1381,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.25675675675675674,
34
+ "eval_accuracy": 0.5428571428571428,
35
+ "eval_loss": 1.8478083610534668,
36
+ "eval_runtime": 29.2478,
37
+ "eval_samples_per_second": 2.393,
38
+ "eval_steps_per_second": 0.308,
39
+ "step": 38
40
+ },
41
+ {
42
+ "epoch": 1.0135135135135136,
43
+ "grad_norm": 9.502254486083984,
44
+ "learning_rate": 4.0601503759398494e-05,
45
+ "loss": 1.9897,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 1.0810810810810811,
50
+ "grad_norm": 9.743173599243164,
51
+ "learning_rate": 3.6842105263157895e-05,
52
+ "loss": 1.6464,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.1486486486486487,
57
+ "grad_norm": 9.88233757019043,
58
+ "learning_rate": 3.3082706766917295e-05,
59
+ "loss": 1.3069,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.2162162162162162,
64
+ "grad_norm": 7.763911247253418,
65
+ "learning_rate": 2.9323308270676693e-05,
66
+ "loss": 0.9543,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 1.2567567567567568,
71
+ "eval_accuracy": 0.6571428571428571,
72
+ "eval_loss": 0.9674364328384399,
73
+ "eval_runtime": 29.3573,
74
+ "eval_samples_per_second": 2.384,
75
+ "eval_steps_per_second": 0.307,
76
+ "step": 76
77
+ },
78
+ {
79
+ "epoch": 2.027027027027027,
80
+ "grad_norm": 8.281584739685059,
81
+ "learning_rate": 2.556390977443609e-05,
82
+ "loss": 0.8358,
83
+ "step": 80
84
+ },
85
+ {
86
+ "epoch": 2.0945945945945947,
87
+ "grad_norm": 18.204240798950195,
88
+ "learning_rate": 2.1804511278195487e-05,
89
+ "loss": 0.6852,
90
+ "step": 90
91
+ },
92
+ {
93
+ "epoch": 2.1621621621621623,
94
+ "grad_norm": 10.050329208374023,
95
+ "learning_rate": 1.8045112781954888e-05,
96
+ "loss": 0.6309,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 2.22972972972973,
101
+ "grad_norm": 4.531847953796387,
102
+ "learning_rate": 1.4285714285714285e-05,
103
+ "loss": 0.4914,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 2.2567567567567566,
108
+ "eval_accuracy": 0.7428571428571429,
109
+ "eval_loss": 0.6266418695449829,
110
+ "eval_runtime": 30.3275,
111
+ "eval_samples_per_second": 2.308,
112
+ "eval_steps_per_second": 0.297,
113
+ "step": 114
114
+ },
115
+ {
116
+ "epoch": 3.0405405405405403,
117
+ "grad_norm": 3.251669406890869,
118
+ "learning_rate": 1.0526315789473684e-05,
119
+ "loss": 0.42,
120
+ "step": 120
121
+ },
122
+ {
123
+ "epoch": 3.108108108108108,
124
+ "grad_norm": 3.1868138313293457,
125
+ "learning_rate": 6.766917293233083e-06,
126
+ "loss": 0.3493,
127
+ "step": 130
128
+ },
129
+ {
130
+ "epoch": 3.175675675675676,
131
+ "grad_norm": 9.545303344726562,
132
+ "learning_rate": 3.007518796992481e-06,
133
+ "loss": 0.3415,
134
+ "step": 140
135
+ },
136
+ {
137
+ "epoch": 3.22972972972973,
138
+ "eval_accuracy": 0.8428571428571429,
139
+ "eval_loss": 0.4506227374076843,
140
+ "eval_runtime": 30.195,
141
+ "eval_samples_per_second": 2.318,
142
+ "eval_steps_per_second": 0.298,
143
+ "step": 148
144
+ },
145
+ {
146
+ "epoch": 3.22972972972973,
147
+ "step": 148,
148
+ "total_flos": 1.460491890402263e+18,
149
+ "train_loss": 1.1224354151132945,
150
+ "train_runtime": 3980.8054,
151
+ "train_samples_per_second": 0.297,
152
+ "train_steps_per_second": 0.037
153
+ },
154
+ {
155
+ "epoch": 3.22972972972973,
156
+ "eval_accuracy": 0.9354838709677419,
157
+ "eval_loss": 0.39373940229415894,
158
+ "eval_runtime": 67.6876,
159
+ "eval_samples_per_second": 2.29,
160
+ "eval_steps_per_second": 0.295,
161
+ "step": 148
162
+ },
163
+ {
164
+ "epoch": 3.22972972972973,
165
+ "eval_accuracy": 0.9354838709677419,
166
+ "eval_loss": 0.3937394320964813,
167
+ "eval_runtime": 67.6788,
168
+ "eval_samples_per_second": 2.29,
169
+ "eval_steps_per_second": 0.296,
170
+ "step": 148
171
+ }
172
+ ],
173
+ "logging_steps": 10,
174
+ "max_steps": 148,
175
+ "num_input_tokens_seen": 0,
176
+ "num_train_epochs": 9223372036854775807,
177
+ "save_steps": 500,
178
+ "stateful_callbacks": {
179
+ "TrainerControl": {
180
+ "args": {
181
+ "should_epoch_stop": false,
182
+ "should_evaluate": false,
183
+ "should_log": false,
184
+ "should_save": true,
185
+ "should_training_stop": true
186
+ },
187
+ "attributes": {}
188
+ }
189
+ },
190
+ "total_flos": 1.460491890402263e+18,
191
+ "train_batch_size": 8,
192
+ "trial_name": null,
193
+ "trial_params": null
194
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4aed410fb4f4e0e04ecbcc518081ced5f2cf3bf9bbe6e1567b271268179b8542
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e451c97dd5655c3a31b18f7af3fce04db2f5804fec41215afbb6ba1323eb615
3
  size 5368