dima806 commited on
Commit
a82256d
1 Parent(s): 31fcaa3

Upload folder using huggingface_hub

Browse files
checkpoint-10164/config.json CHANGED
@@ -120,5 +120,5 @@
120
  "problem_type": "single_label_classification",
121
  "qkv_bias": true,
122
  "torch_dtype": "float32",
123
- "transformers_version": "4.43.3"
124
  }
 
120
  "problem_type": "single_label_classification",
121
  "qkv_bias": true,
122
  "torch_dtype": "float32",
123
+ "transformers_version": "4.43.4"
124
  }
checkpoint-10164/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3a3b372e31df38748987435df2ea69465e5e4c83db458e0fac6563ddd192b1e
3
  size 343365480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a2d129e6ba0d4113eade43c1b58eb17e357e0f6b6a428b367f1cf3b8592b6b5
3
  size 343365480
checkpoint-10164/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2ca3017d58d7ac3c69a7a111ec51921ac9e6fec103c9fc6f46162f42f15cadb
3
  size 686851461
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b6d29967cfae1ea01210432b9b6c3576033934a676b1b24534c0cac46c942a
3
  size 686851461
checkpoint-10164/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 1.265008568763733,
3
  "best_model_checkpoint": "cat_breed_image_detection/checkpoint-10164",
4
  "epoch": 4.0,
5
  "eval_steps": 500,
@@ -10,182 +10,182 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.19677292404565133,
13
- "grad_norm": 9.472394943237305,
14
  "learning_rate": 8.599564959462131e-07,
15
- "loss": 1.2504,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 0.39354584809130266,
20
- "grad_norm": 13.004825592041016,
21
  "learning_rate": 8.154637136642278e-07,
22
- "loss": 1.2416,
23
  "step": 1000
24
  },
25
  {
26
  "epoch": 0.5903187721369539,
27
- "grad_norm": 7.997884273529053,
28
  "learning_rate": 7.709709313822424e-07,
29
- "loss": 1.2367,
30
  "step": 1500
31
  },
32
  {
33
  "epoch": 0.7870916961826053,
34
- "grad_norm": 8.67659854888916,
35
  "learning_rate": 7.26478149100257e-07,
36
- "loss": 1.2441,
37
  "step": 2000
38
  },
39
  {
40
  "epoch": 0.9838646202282566,
41
- "grad_norm": 10.490302085876465,
42
  "learning_rate": 6.819853668182716e-07,
43
- "loss": 1.2106,
44
  "step": 2500
45
  },
46
  {
47
  "epoch": 1.0,
48
- "eval_accuracy": 0.6619519486271036,
49
- "eval_loss": 1.2953426837921143,
50
  "eval_model_preparation_time": 0.0055,
51
- "eval_runtime": 1207.1956,
52
- "eval_samples_per_second": 89.782,
53
- "eval_steps_per_second": 2.806,
54
  "step": 2541
55
  },
56
  {
57
  "epoch": 1.1806375442739079,
58
- "grad_norm": 9.106962203979492,
59
  "learning_rate": 6.374925845362863e-07,
60
- "loss": 1.2229,
61
  "step": 3000
62
  },
63
  {
64
  "epoch": 1.3774104683195592,
65
- "grad_norm": 6.981090068817139,
66
  "learning_rate": 5.929998022543009e-07,
67
- "loss": 1.2177,
68
  "step": 3500
69
  },
70
  {
71
  "epoch": 1.5741833923652107,
72
- "grad_norm": 13.470215797424316,
73
  "learning_rate": 5.485070199723155e-07,
74
- "loss": 1.1995,
75
  "step": 4000
76
  },
77
  {
78
  "epoch": 1.770956316410862,
79
- "grad_norm": 8.636761665344238,
80
  "learning_rate": 5.040142376903302e-07,
81
- "loss": 1.2087,
82
  "step": 4500
83
  },
84
  {
85
  "epoch": 1.9677292404565132,
86
- "grad_norm": 9.918224334716797,
87
  "learning_rate": 4.5952145540834485e-07,
88
- "loss": 1.2103,
89
  "step": 5000
90
  },
91
  {
92
  "epoch": 2.0,
93
- "eval_accuracy": 0.6657993799822852,
94
- "eval_loss": 1.2781411409378052,
95
  "eval_model_preparation_time": 0.0055,
96
- "eval_runtime": 1214.5435,
97
- "eval_samples_per_second": 89.238,
98
- "eval_steps_per_second": 2.789,
99
  "step": 5082
100
  },
101
  {
102
  "epoch": 2.1645021645021645,
103
- "grad_norm": 9.103760719299316,
104
  "learning_rate": 4.150286731263595e-07,
105
- "loss": 1.2016,
106
  "step": 5500
107
  },
108
  {
109
  "epoch": 2.3612750885478158,
110
- "grad_norm": 9.183661460876465,
111
  "learning_rate": 3.705358908443741e-07,
112
- "loss": 1.1993,
113
  "step": 6000
114
  },
115
  {
116
  "epoch": 2.558048012593467,
117
- "grad_norm": 7.494422912597656,
118
  "learning_rate": 3.2604310856238877e-07,
119
- "loss": 1.2033,
120
  "step": 6500
121
  },
122
  {
123
  "epoch": 2.7548209366391183,
124
- "grad_norm": 9.207113265991211,
125
  "learning_rate": 2.815503262804034e-07,
126
- "loss": 1.1868,
127
  "step": 7000
128
  },
129
  {
130
  "epoch": 2.9515938606847696,
131
- "grad_norm": 8.814680099487305,
132
  "learning_rate": 2.37057543998418e-07,
133
- "loss": 1.1994,
134
  "step": 7500
135
  },
136
  {
137
  "epoch": 3.0,
138
- "eval_accuracy": 0.6672848390906407,
139
- "eval_loss": 1.2696255445480347,
140
  "eval_model_preparation_time": 0.0055,
141
- "eval_runtime": 1228.8502,
142
- "eval_samples_per_second": 88.2,
143
- "eval_steps_per_second": 2.756,
144
  "step": 7623
145
  },
146
  {
147
  "epoch": 3.1483667847304213,
148
- "grad_norm": 10.587736129760742,
149
  "learning_rate": 1.9256476171643265e-07,
150
- "loss": 1.1888,
151
  "step": 8000
152
  },
153
  {
154
  "epoch": 3.3451397087760726,
155
- "grad_norm": 7.582997798919678,
156
  "learning_rate": 1.4807197943444728e-07,
157
- "loss": 1.1889,
158
  "step": 8500
159
  },
160
  {
161
  "epoch": 3.541912632821724,
162
- "grad_norm": 12.2061128616333,
163
  "learning_rate": 1.0357919715246192e-07,
164
- "loss": 1.1898,
165
  "step": 9000
166
  },
167
  {
168
  "epoch": 3.738685556867375,
169
- "grad_norm": 8.521767616271973,
170
  "learning_rate": 5.9086414870476566e-08,
171
- "loss": 1.1845,
172
  "step": 9500
173
  },
174
  {
175
  "epoch": 3.9354584809130264,
176
- "grad_norm": 11.329971313476562,
177
  "learning_rate": 1.4593632588491198e-08,
178
- "loss": 1.1925,
179
  "step": 10000
180
  },
181
  {
182
  "epoch": 4.0,
183
- "eval_accuracy": 0.6685027310304104,
184
- "eval_loss": 1.265008568763733,
185
  "eval_model_preparation_time": 0.0055,
186
- "eval_runtime": 1388.927,
187
- "eval_samples_per_second": 78.034,
188
- "eval_steps_per_second": 2.439,
189
  "step": 10164
190
  }
191
  ],
 
1
  {
2
+ "best_metric": 1.1233651638031006,
3
  "best_model_checkpoint": "cat_breed_image_detection/checkpoint-10164",
4
  "epoch": 4.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.19677292404565133,
13
+ "grad_norm": 11.85600471496582,
14
  "learning_rate": 8.599564959462131e-07,
15
+ "loss": 1.0931,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 0.39354584809130266,
20
+ "grad_norm": 6.796216011047363,
21
  "learning_rate": 8.154637136642278e-07,
22
+ "loss": 1.0952,
23
  "step": 1000
24
  },
25
  {
26
  "epoch": 0.5903187721369539,
27
+ "grad_norm": 8.564379692077637,
28
  "learning_rate": 7.709709313822424e-07,
29
+ "loss": 1.0814,
30
  "step": 1500
31
  },
32
  {
33
  "epoch": 0.7870916961826053,
34
+ "grad_norm": 11.41899299621582,
35
  "learning_rate": 7.26478149100257e-07,
36
+ "loss": 1.0954,
37
  "step": 2000
38
  },
39
  {
40
  "epoch": 0.9838646202282566,
41
+ "grad_norm": 8.380097389221191,
42
  "learning_rate": 6.819853668182716e-07,
43
+ "loss": 1.084,
44
  "step": 2500
45
  },
46
  {
47
  "epoch": 1.0,
48
+ "eval_accuracy": 0.6954347505166815,
49
+ "eval_loss": 1.1442592144012451,
50
  "eval_model_preparation_time": 0.0055,
51
+ "eval_runtime": 1212.3183,
52
+ "eval_samples_per_second": 89.402,
53
+ "eval_steps_per_second": 2.794,
54
  "step": 2541
55
  },
56
  {
57
  "epoch": 1.1806375442739079,
58
+ "grad_norm": 8.583738327026367,
59
  "learning_rate": 6.374925845362863e-07,
60
+ "loss": 1.0785,
61
  "step": 3000
62
  },
63
  {
64
  "epoch": 1.3774104683195592,
65
+ "grad_norm": 6.957513809204102,
66
  "learning_rate": 5.929998022543009e-07,
67
+ "loss": 1.056,
68
  "step": 3500
69
  },
70
  {
71
  "epoch": 1.5741833923652107,
72
+ "grad_norm": 10.452813148498535,
73
  "learning_rate": 5.485070199723155e-07,
74
+ "loss": 1.0648,
75
  "step": 4000
76
  },
77
  {
78
  "epoch": 1.770956316410862,
79
+ "grad_norm": 10.482475280761719,
80
  "learning_rate": 5.040142376903302e-07,
81
+ "loss": 1.0748,
82
  "step": 4500
83
  },
84
  {
85
  "epoch": 1.9677292404565132,
86
+ "grad_norm": 10.342619895935059,
87
  "learning_rate": 4.5952145540834485e-07,
88
+ "loss": 1.0596,
89
  "step": 5000
90
  },
91
  {
92
  "epoch": 2.0,
93
+ "eval_accuracy": 0.6959514319456747,
94
+ "eval_loss": 1.1350406408309937,
95
  "eval_model_preparation_time": 0.0055,
96
+ "eval_runtime": 1195.5546,
97
+ "eval_samples_per_second": 90.656,
98
+ "eval_steps_per_second": 2.833,
99
  "step": 5082
100
  },
101
  {
102
  "epoch": 2.1645021645021645,
103
+ "grad_norm": 16.03907012939453,
104
  "learning_rate": 4.150286731263595e-07,
105
+ "loss": 1.0565,
106
  "step": 5500
107
  },
108
  {
109
  "epoch": 2.3612750885478158,
110
+ "grad_norm": 10.92419147491455,
111
  "learning_rate": 3.705358908443741e-07,
112
+ "loss": 1.0416,
113
  "step": 6000
114
  },
115
  {
116
  "epoch": 2.558048012593467,
117
+ "grad_norm": 12.578429222106934,
118
  "learning_rate": 3.2604310856238877e-07,
119
+ "loss": 1.053,
120
  "step": 6500
121
  },
122
  {
123
  "epoch": 2.7548209366391183,
124
+ "grad_norm": 8.39530086517334,
125
  "learning_rate": 2.815503262804034e-07,
126
+ "loss": 1.0507,
127
  "step": 7000
128
  },
129
  {
130
  "epoch": 2.9515938606847696,
131
+ "grad_norm": 10.037232398986816,
132
  "learning_rate": 2.37057543998418e-07,
133
+ "loss": 1.0628,
134
  "step": 7500
135
  },
136
  {
137
  "epoch": 3.0,
138
+ "eval_accuracy": 0.6984887068201948,
139
+ "eval_loss": 1.1276220083236694,
140
  "eval_model_preparation_time": 0.0055,
141
+ "eval_runtime": 1193.5846,
142
+ "eval_samples_per_second": 90.805,
143
+ "eval_steps_per_second": 2.838,
144
  "step": 7623
145
  },
146
  {
147
  "epoch": 3.1483667847304213,
148
+ "grad_norm": 12.347983360290527,
149
  "learning_rate": 1.9256476171643265e-07,
150
+ "loss": 1.0436,
151
  "step": 8000
152
  },
153
  {
154
  "epoch": 3.3451397087760726,
155
+ "grad_norm": 12.989178657531738,
156
  "learning_rate": 1.4807197943444728e-07,
157
+ "loss": 1.0538,
158
  "step": 8500
159
  },
160
  {
161
  "epoch": 3.541912632821724,
162
+ "grad_norm": 8.557451248168945,
163
  "learning_rate": 1.0357919715246192e-07,
164
+ "loss": 1.0416,
165
  "step": 9000
166
  },
167
  {
168
  "epoch": 3.738685556867375,
169
+ "grad_norm": 9.772086143493652,
170
  "learning_rate": 5.9086414870476566e-08,
171
+ "loss": 1.0454,
172
  "step": 9500
173
  },
174
  {
175
  "epoch": 3.9354584809130264,
176
+ "grad_norm": 9.701172828674316,
177
  "learning_rate": 1.4593632588491198e-08,
178
+ "loss": 1.044,
179
  "step": 10000
180
  },
181
  {
182
  "epoch": 4.0,
183
+ "eval_accuracy": 0.7001217891939769,
184
+ "eval_loss": 1.1233651638031006,
185
  "eval_model_preparation_time": 0.0055,
186
+ "eval_runtime": 1202.0319,
187
+ "eval_samples_per_second": 90.167,
188
+ "eval_steps_per_second": 2.818,
189
  "step": 10164
190
  }
191
  ],
config.json CHANGED
@@ -120,5 +120,5 @@
120
  "problem_type": "single_label_classification",
121
  "qkv_bias": true,
122
  "torch_dtype": "float32",
123
- "transformers_version": "4.43.3"
124
  }
 
120
  "problem_type": "single_label_classification",
121
  "qkv_bias": true,
122
  "torch_dtype": "float32",
123
+ "transformers_version": "4.43.4"
124
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6074319abb8cfbc31e72b4d45ee17ea03f9710df791d1661ee9ba1a74a785027
3
  size 343365480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a2d129e6ba0d4113eade43c1b58eb17e357e0f6b6a428b367f1cf3b8592b6b5
3
  size 343365480
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aa9f0c7be17c246a85b35b1cacecee4f5b32627bf237df20128bcfe78dfeb2a
3
  size 4667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6e2b24c2bb418666641ee5942c486949ee0d8efdf7de643fb67fbd8451ce35
3
  size 4667