Upload folder using huggingface_hub
Browse files- checkpoint-10164/model.safetensors +1 -1
- checkpoint-10164/optimizer.pt +1 -1
- checkpoint-10164/scheduler.pt +1 -1
- checkpoint-10164/trainer_state.json +85 -85
- checkpoint-10164/training_args.bin +1 -1
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-10164/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343365480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae08e577606eeef2b66632cb52d3ed3f9cdb59bca00aac0af10979498ee66c3e
|
3 |
size 343365480
|
checkpoint-10164/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 686851461
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ff323a157f41953706488c906c873a177bb71114646241f2a8177a740dd2100
|
3 |
size 686851461
|
checkpoint-10164/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:952f08c40c34eff0831c27c192eb47755e3dde00eeb6f959fc4c352e7864c981
|
3 |
size 627
|
checkpoint-10164/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
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":
|
14 |
-
"learning_rate":
|
15 |
-
"loss":
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.39354584809130266,
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate":
|
22 |
-
"loss":
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.5903187721369539,
|
27 |
-
"grad_norm":
|
28 |
-
"learning_rate":
|
29 |
-
"loss":
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.7870916961826053,
|
34 |
-
"grad_norm":
|
35 |
-
"learning_rate":
|
36 |
-
"loss":
|
37 |
"step": 2000
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.9838646202282566,
|
41 |
-
"grad_norm":
|
42 |
-
"learning_rate": 6.
|
43 |
-
"loss":
|
44 |
"step": 2500
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.0,
|
48 |
-
"eval_accuracy": 0.
|
49 |
-
"eval_loss": 1.
|
50 |
-
"eval_model_preparation_time": 0.
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second":
|
53 |
-
"eval_steps_per_second": 2.
|
54 |
"step": 2541
|
55 |
},
|
56 |
{
|
57 |
"epoch": 1.1806375442739079,
|
58 |
-
"grad_norm":
|
59 |
-
"learning_rate":
|
60 |
-
"loss":
|
61 |
"step": 3000
|
62 |
},
|
63 |
{
|
64 |
"epoch": 1.3774104683195592,
|
65 |
-
"grad_norm":
|
66 |
-
"learning_rate": 5.
|
67 |
-
"loss":
|
68 |
"step": 3500
|
69 |
},
|
70 |
{
|
71 |
"epoch": 1.5741833923652107,
|
72 |
-
"grad_norm": 9.
|
73 |
-
"learning_rate":
|
74 |
-
"loss":
|
75 |
"step": 4000
|
76 |
},
|
77 |
{
|
78 |
"epoch": 1.770956316410862,
|
79 |
-
"grad_norm":
|
80 |
-
"learning_rate":
|
81 |
-
"loss":
|
82 |
"step": 4500
|
83 |
},
|
84 |
{
|
85 |
"epoch": 1.9677292404565132,
|
86 |
-
"grad_norm":
|
87 |
-
"learning_rate": 4.
|
88 |
-
"loss":
|
89 |
"step": 5000
|
90 |
},
|
91 |
{
|
92 |
"epoch": 2.0,
|
93 |
-
"eval_accuracy": 0.
|
94 |
-
"eval_loss": 1.
|
95 |
-
"eval_model_preparation_time": 0.
|
96 |
-
"eval_runtime":
|
97 |
-
"eval_samples_per_second":
|
98 |
-
"eval_steps_per_second": 2.
|
99 |
"step": 5082
|
100 |
},
|
101 |
{
|
102 |
"epoch": 2.1645021645021645,
|
103 |
-
"grad_norm":
|
104 |
-
"learning_rate":
|
105 |
-
"loss":
|
106 |
"step": 5500
|
107 |
},
|
108 |
{
|
109 |
"epoch": 2.3612750885478158,
|
110 |
-
"grad_norm":
|
111 |
-
"learning_rate": 3.
|
112 |
-
"loss":
|
113 |
"step": 6000
|
114 |
},
|
115 |
{
|
116 |
"epoch": 2.558048012593467,
|
117 |
-
"grad_norm":
|
118 |
-
"learning_rate":
|
119 |
-
"loss":
|
120 |
"step": 6500
|
121 |
},
|
122 |
{
|
123 |
"epoch": 2.7548209366391183,
|
124 |
-
"grad_norm":
|
125 |
-
"learning_rate": 2.
|
126 |
-
"loss":
|
127 |
"step": 7000
|
128 |
},
|
129 |
{
|
130 |
"epoch": 2.9515938606847696,
|
131 |
-
"grad_norm":
|
132 |
-
"learning_rate": 2.
|
133 |
-
"loss":
|
134 |
"step": 7500
|
135 |
},
|
136 |
{
|
137 |
"epoch": 3.0,
|
138 |
-
"eval_accuracy": 0.
|
139 |
-
"eval_loss": 1.
|
140 |
-
"eval_model_preparation_time": 0.
|
141 |
-
"eval_runtime":
|
142 |
-
"eval_samples_per_second":
|
143 |
-
"eval_steps_per_second": 2.
|
144 |
"step": 7623
|
145 |
},
|
146 |
{
|
147 |
"epoch": 3.1483667847304213,
|
148 |
-
"grad_norm":
|
149 |
-
"learning_rate": 1.
|
150 |
-
"loss":
|
151 |
"step": 8000
|
152 |
},
|
153 |
{
|
154 |
"epoch": 3.3451397087760726,
|
155 |
-
"grad_norm":
|
156 |
-
"learning_rate": 1.
|
157 |
-
"loss":
|
158 |
"step": 8500
|
159 |
},
|
160 |
{
|
161 |
"epoch": 3.541912632821724,
|
162 |
-
"grad_norm":
|
163 |
-
"learning_rate":
|
164 |
-
"loss":
|
165 |
"step": 9000
|
166 |
},
|
167 |
{
|
168 |
"epoch": 3.738685556867375,
|
169 |
-
"grad_norm":
|
170 |
-
"learning_rate": 5.
|
171 |
-
"loss":
|
172 |
"step": 9500
|
173 |
},
|
174 |
{
|
175 |
"epoch": 3.9354584809130264,
|
176 |
-
"grad_norm": 8.
|
177 |
-
"learning_rate": 1.
|
178 |
-
"loss":
|
179 |
"step": 10000
|
180 |
},
|
181 |
{
|
182 |
"epoch": 4.0,
|
183 |
-
"eval_accuracy": 0.
|
184 |
-
"eval_loss": 1.
|
185 |
-
"eval_model_preparation_time": 0.
|
186 |
-
"eval_runtime":
|
187 |
-
"eval_samples_per_second":
|
188 |
-
"eval_steps_per_second": 2.
|
189 |
"step": 10164
|
190 |
}
|
191 |
],
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.0084277391433716,
|
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": 13.16645622253418,
|
14 |
+
"learning_rate": 7.644057741744116e-07,
|
15 |
+
"loss": 0.9682,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.39354584809130266,
|
20 |
+
"grad_norm": 13.873289108276367,
|
21 |
+
"learning_rate": 7.248566343682025e-07,
|
22 |
+
"loss": 0.9558,
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.5903187721369539,
|
27 |
+
"grad_norm": 9.378376960754395,
|
28 |
+
"learning_rate": 6.853074945619932e-07,
|
29 |
+
"loss": 0.9563,
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.7870916961826053,
|
34 |
+
"grad_norm": 13.954855918884277,
|
35 |
+
"learning_rate": 6.45758354755784e-07,
|
36 |
+
"loss": 0.9576,
|
37 |
"step": 2000
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.9838646202282566,
|
41 |
+
"grad_norm": 8.968609809875488,
|
42 |
+
"learning_rate": 6.062092149495747e-07,
|
43 |
+
"loss": 0.9435,
|
44 |
"step": 2500
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.0,
|
48 |
+
"eval_accuracy": 0.7204107617360496,
|
49 |
+
"eval_loss": 1.0221161842346191,
|
50 |
+
"eval_model_preparation_time": 0.0058,
|
51 |
+
"eval_runtime": 1192.8471,
|
52 |
+
"eval_samples_per_second": 90.862,
|
53 |
+
"eval_steps_per_second": 2.839,
|
54 |
"step": 2541
|
55 |
},
|
56 |
{
|
57 |
"epoch": 1.1806375442739079,
|
58 |
+
"grad_norm": 9.562682151794434,
|
59 |
+
"learning_rate": 5.666600751433656e-07,
|
60 |
+
"loss": 0.9435,
|
61 |
"step": 3000
|
62 |
},
|
63 |
{
|
64 |
"epoch": 1.3774104683195592,
|
65 |
+
"grad_norm": 7.73732328414917,
|
66 |
+
"learning_rate": 5.271109353371563e-07,
|
67 |
+
"loss": 0.945,
|
68 |
"step": 3500
|
69 |
},
|
70 |
{
|
71 |
"epoch": 1.5741833923652107,
|
72 |
+
"grad_norm": 9.456089973449707,
|
73 |
+
"learning_rate": 4.875617955309472e-07,
|
74 |
+
"loss": 0.9379,
|
75 |
"step": 4000
|
76 |
},
|
77 |
{
|
78 |
"epoch": 1.770956316410862,
|
79 |
+
"grad_norm": 8.087896347045898,
|
80 |
+
"learning_rate": 4.48012655724738e-07,
|
81 |
+
"loss": 0.93,
|
82 |
"step": 4500
|
83 |
},
|
84 |
{
|
85 |
"epoch": 1.9677292404565132,
|
86 |
+
"grad_norm": 11.194710731506348,
|
87 |
+
"learning_rate": 4.0846351591852876e-07,
|
88 |
+
"loss": 0.9457,
|
89 |
"step": 5000
|
90 |
},
|
91 |
{
|
92 |
"epoch": 2.0,
|
93 |
+
"eval_accuracy": 0.7221822409211692,
|
94 |
+
"eval_loss": 1.0146400928497314,
|
95 |
+
"eval_model_preparation_time": 0.0058,
|
96 |
+
"eval_runtime": 1188.9777,
|
97 |
+
"eval_samples_per_second": 91.157,
|
98 |
+
"eval_steps_per_second": 2.849,
|
99 |
"step": 5082
|
100 |
},
|
101 |
{
|
102 |
"epoch": 2.1645021645021645,
|
103 |
+
"grad_norm": 9.790952682495117,
|
104 |
+
"learning_rate": 3.6891437611231956e-07,
|
105 |
+
"loss": 0.9299,
|
106 |
"step": 5500
|
107 |
},
|
108 |
{
|
109 |
"epoch": 2.3612750885478158,
|
110 |
+
"grad_norm": 7.579208850860596,
|
111 |
+
"learning_rate": 3.293652363061103e-07,
|
112 |
+
"loss": 0.9283,
|
113 |
"step": 6000
|
114 |
},
|
115 |
{
|
116 |
"epoch": 2.558048012593467,
|
117 |
+
"grad_norm": 8.789483070373535,
|
118 |
+
"learning_rate": 2.898160964999011e-07,
|
119 |
+
"loss": 0.9476,
|
120 |
"step": 6500
|
121 |
},
|
122 |
{
|
123 |
"epoch": 2.7548209366391183,
|
124 |
+
"grad_norm": 10.544241905212402,
|
125 |
+
"learning_rate": 2.502669566936919e-07,
|
126 |
+
"loss": 0.9228,
|
127 |
"step": 7000
|
128 |
},
|
129 |
{
|
130 |
"epoch": 2.9515938606847696,
|
131 |
+
"grad_norm": 8.694629669189453,
|
132 |
+
"learning_rate": 2.1071781688748268e-07,
|
133 |
+
"loss": 0.9256,
|
134 |
"step": 7500
|
135 |
},
|
136 |
{
|
137 |
"epoch": 3.0,
|
138 |
+
"eval_accuracy": 0.7234462651313847,
|
139 |
+
"eval_loss": 1.0090746879577637,
|
140 |
+
"eval_model_preparation_time": 0.0058,
|
141 |
+
"eval_runtime": 1192.9376,
|
142 |
+
"eval_samples_per_second": 90.855,
|
143 |
+
"eval_steps_per_second": 2.839,
|
144 |
"step": 7623
|
145 |
},
|
146 |
{
|
147 |
"epoch": 3.1483667847304213,
|
148 |
+
"grad_norm": 9.106084823608398,
|
149 |
+
"learning_rate": 1.7116867708127348e-07,
|
150 |
+
"loss": 0.9313,
|
151 |
"step": 8000
|
152 |
},
|
153 |
{
|
154 |
"epoch": 3.3451397087760726,
|
155 |
+
"grad_norm": 14.434243202209473,
|
156 |
+
"learning_rate": 1.3161953727506426e-07,
|
157 |
+
"loss": 0.9245,
|
158 |
"step": 8500
|
159 |
},
|
160 |
{
|
161 |
"epoch": 3.541912632821724,
|
162 |
+
"grad_norm": 6.294890880584717,
|
163 |
+
"learning_rate": 9.207039746885504e-08,
|
164 |
+
"loss": 0.9135,
|
165 |
"step": 9000
|
166 |
},
|
167 |
{
|
168 |
"epoch": 3.738685556867375,
|
169 |
+
"grad_norm": 9.335221290588379,
|
170 |
+
"learning_rate": 5.2521257662645836e-08,
|
171 |
+
"loss": 0.9349,
|
172 |
"step": 9500
|
173 |
},
|
174 |
{
|
175 |
"epoch": 3.9354584809130264,
|
176 |
+
"grad_norm": 8.591920852661133,
|
177 |
+
"learning_rate": 1.297211785643662e-08,
|
178 |
+
"loss": 0.913,
|
179 |
"step": 10000
|
180 |
},
|
181 |
{
|
182 |
"epoch": 4.0,
|
183 |
+
"eval_accuracy": 0.723907587835843,
|
184 |
+
"eval_loss": 1.0084277391433716,
|
185 |
+
"eval_model_preparation_time": 0.0058,
|
186 |
+
"eval_runtime": 1186.2416,
|
187 |
+
"eval_samples_per_second": 91.368,
|
188 |
+
"eval_steps_per_second": 2.855,
|
189 |
"step": 10164
|
190 |
}
|
191 |
],
|
checkpoint-10164/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4667
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad3477ddc7ea3a5c3236c20065dd22f24f5262766b2c91e1cd0f8c8389a1871c
|
3 |
size 4667
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343365480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae08e577606eeef2b66632cb52d3ed3f9cdb59bca00aac0af10979498ee66c3e
|
3 |
size 343365480
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4667
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad3477ddc7ea3a5c3236c20065dd22f24f5262766b2c91e1cd0f8c8389a1871c
|
3 |
size 4667
|