dima806 commited on
Commit
c04934a
1 Parent(s): a2e6951

Delete checkpoint-8260

Browse files
checkpoint-8260/config.json DELETED
@@ -1,42 +0,0 @@
1
- {
2
- "_name_or_path": "dima806/facial_emotions_image_detection",
3
- "architectures": [
4
- "ViTForImageClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.0,
7
- "encoder_stride": 16,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.0,
10
- "hidden_size": 768,
11
- "id2label": {
12
- "0": "sad",
13
- "1": "disgust",
14
- "2": "angry",
15
- "3": "neutral",
16
- "4": "fear",
17
- "5": "surprise",
18
- "6": "happy"
19
- },
20
- "image_size": 224,
21
- "initializer_range": 0.02,
22
- "intermediate_size": 3072,
23
- "label2id": {
24
- "angry": 2,
25
- "disgust": 1,
26
- "fear": 4,
27
- "happy": 6,
28
- "neutral": 3,
29
- "sad": 0,
30
- "surprise": 5
31
- },
32
- "layer_norm_eps": 1e-12,
33
- "model_type": "vit",
34
- "num_attention_heads": 12,
35
- "num_channels": 3,
36
- "num_hidden_layers": 12,
37
- "patch_size": 16,
38
- "problem_type": "single_label_classification",
39
- "qkv_bias": true,
40
- "torch_dtype": "float32",
41
- "transformers_version": "4.38.2"
42
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-8260/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f72147d8a29312deea5ae0d340746fbe8fc362064e914b8980d130c3ad13be7
3
- size 343239356
 
 
 
 
checkpoint-8260/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:021125416bb55e11c6010c3b710e051e1a11bb22b8aea77a226bf4ebe56b3264
3
- size 686599173
 
 
 
 
checkpoint-8260/preprocessor_config.json DELETED
@@ -1,22 +0,0 @@
1
- {
2
- "do_normalize": true,
3
- "do_rescale": true,
4
- "do_resize": true,
5
- "image_mean": [
6
- 0.5,
7
- 0.5,
8
- 0.5
9
- ],
10
- "image_processor_type": "ViTImageProcessor",
11
- "image_std": [
12
- 0.5,
13
- 0.5,
14
- 0.5
15
- ],
16
- "resample": 2,
17
- "rescale_factor": 0.00392156862745098,
18
- "size": {
19
- "height": 224,
20
- "width": 224
21
- }
22
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-8260/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f8e98d47324b714e529ce23a82ab10ec68b0405c6b8f1e915890f7160bb5da7
3
- size 14575
 
 
 
 
checkpoint-8260/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:174ba982eed656afb325f046c7be8c9915f2cb62f97b22dd5331356dee085c3a
3
- size 627
 
 
 
 
checkpoint-8260/trainer_state.json DELETED
@@ -1,196 +0,0 @@
1
- {
2
- "best_metric": 0.32018494606018066,
3
- "best_model_checkpoint": "facial_emotions_image_detection/checkpoint-8260",
4
- "epoch": 7.0,
5
- "eval_steps": 500,
6
- "global_step": 8260,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.42,
13
- "grad_norm": 13.829694747924805,
14
- "learning_rate": 2.856230031948882e-06,
15
- "loss": 0.399,
16
- "step": 500
17
- },
18
- {
19
- "epoch": 0.85,
20
- "grad_norm": 10.43336296081543,
21
- "learning_rate": 2.696485623003195e-06,
22
- "loss": 0.3907,
23
- "step": 1000
24
- },
25
- {
26
- "epoch": 1.0,
27
- "eval_accuracy": 0.8980532379817243,
28
- "eval_loss": 0.331790030002594,
29
- "eval_runtime": 228.9339,
30
- "eval_samples_per_second": 109.944,
31
- "eval_steps_per_second": 13.746,
32
- "step": 1180
33
- },
34
- {
35
- "epoch": 1.27,
36
- "grad_norm": 13.529434204101562,
37
- "learning_rate": 2.536741214057508e-06,
38
- "loss": 0.3646,
39
- "step": 1500
40
- },
41
- {
42
- "epoch": 1.69,
43
- "grad_norm": 13.766672134399414,
44
- "learning_rate": 2.376996805111821e-06,
45
- "loss": 0.3674,
46
- "step": 2000
47
- },
48
- {
49
- "epoch": 2.0,
50
- "eval_accuracy": 0.8970997218911403,
51
- "eval_loss": 0.33308491110801697,
52
- "eval_runtime": 226.1763,
53
- "eval_samples_per_second": 111.285,
54
- "eval_steps_per_second": 13.914,
55
- "step": 2360
56
- },
57
- {
58
- "epoch": 2.12,
59
- "grad_norm": 15.129395484924316,
60
- "learning_rate": 2.217252396166134e-06,
61
- "loss": 0.3738,
62
- "step": 2500
63
- },
64
- {
65
- "epoch": 2.54,
66
- "grad_norm": 15.538688659667969,
67
- "learning_rate": 2.057507987220447e-06,
68
- "loss": 0.3534,
69
- "step": 3000
70
- },
71
- {
72
- "epoch": 2.97,
73
- "grad_norm": 15.868049621582031,
74
- "learning_rate": 1.8977635782747604e-06,
75
- "loss": 0.3467,
76
- "step": 3500
77
- },
78
- {
79
- "epoch": 3.0,
80
- "eval_accuracy": 0.8961064759634485,
81
- "eval_loss": 0.33278992772102356,
82
- "eval_runtime": 228.0713,
83
- "eval_samples_per_second": 110.36,
84
- "eval_steps_per_second": 13.798,
85
- "step": 3540
86
- },
87
- {
88
- "epoch": 3.39,
89
- "grad_norm": 12.208673477172852,
90
- "learning_rate": 1.7380191693290735e-06,
91
- "loss": 0.3321,
92
- "step": 4000
93
- },
94
- {
95
- "epoch": 3.81,
96
- "grad_norm": 12.523385047912598,
97
- "learning_rate": 1.5782747603833867e-06,
98
- "loss": 0.322,
99
- "step": 4500
100
- },
101
- {
102
- "epoch": 4.0,
103
- "eval_accuracy": 0.8984505363528009,
104
- "eval_loss": 0.3272715210914612,
105
- "eval_runtime": 226.7446,
106
- "eval_samples_per_second": 111.006,
107
- "eval_steps_per_second": 13.879,
108
- "step": 4720
109
- },
110
- {
111
- "epoch": 4.24,
112
- "grad_norm": 15.311544418334961,
113
- "learning_rate": 1.4185303514376998e-06,
114
- "loss": 0.3288,
115
- "step": 5000
116
- },
117
- {
118
- "epoch": 4.66,
119
- "grad_norm": 13.10958194732666,
120
- "learning_rate": 1.2587859424920128e-06,
121
- "loss": 0.3182,
122
- "step": 5500
123
- },
124
- {
125
- "epoch": 5.0,
126
- "eval_accuracy": 0.9007548669050457,
127
- "eval_loss": 0.3223397731781006,
128
- "eval_runtime": 225.1518,
129
- "eval_samples_per_second": 111.791,
130
- "eval_steps_per_second": 13.977,
131
- "step": 5900
132
- },
133
- {
134
- "epoch": 5.08,
135
- "grad_norm": 10.398481369018555,
136
- "learning_rate": 1.0990415335463259e-06,
137
- "loss": 0.2982,
138
- "step": 6000
139
- },
140
- {
141
- "epoch": 5.51,
142
- "grad_norm": 20.114734649658203,
143
- "learning_rate": 9.39297124600639e-07,
144
- "loss": 0.2946,
145
- "step": 6500
146
- },
147
- {
148
- "epoch": 5.93,
149
- "grad_norm": 20.724897384643555,
150
- "learning_rate": 7.795527156549522e-07,
151
- "loss": 0.3081,
152
- "step": 7000
153
- },
154
- {
155
- "epoch": 6.0,
156
- "eval_accuracy": 0.9009137862534764,
157
- "eval_loss": 0.3215692341327667,
158
- "eval_runtime": 224.6793,
159
- "eval_samples_per_second": 112.026,
160
- "eval_steps_per_second": 14.007,
161
- "step": 7080
162
- },
163
- {
164
- "epoch": 6.36,
165
- "grad_norm": 13.87393856048584,
166
- "learning_rate": 6.198083067092652e-07,
167
- "loss": 0.296,
168
- "step": 7500
169
- },
170
- {
171
- "epoch": 6.78,
172
- "grad_norm": 8.323355674743652,
173
- "learning_rate": 4.600638977635783e-07,
174
- "loss": 0.2816,
175
- "step": 8000
176
- },
177
- {
178
- "epoch": 7.0,
179
- "eval_accuracy": 0.9007945967421533,
180
- "eval_loss": 0.32018494606018066,
181
- "eval_runtime": 228.3984,
182
- "eval_samples_per_second": 110.202,
183
- "eval_steps_per_second": 13.779,
184
- "step": 8260
185
- }
186
- ],
187
- "logging_steps": 500,
188
- "max_steps": 9440,
189
- "num_input_tokens_seen": 0,
190
- "num_train_epochs": 8,
191
- "save_steps": 500,
192
- "total_flos": 2.047980331630782e+19,
193
- "train_batch_size": 32,
194
- "trial_name": null,
195
- "trial_params": null
196
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-8260/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aed0ae0ffe8257f753cc0f49d86497faa8177f98b33415d52fbb46521f7d625c
3
- size 4411