🍻 cheers
Browse files- README.md +3 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Mar29_22-22-11_46bea10b934f/events.out.tfevents.1711755183.46bea10b934f.8755.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +247 -0
README.md
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: facebook/convnext-tiny-224
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- accuracy
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# akram-convNeXt-flipkarts
|
17 |
|
18 |
-
This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
- Accuracy: 0.8734
|
22 |
|
23 |
## Model description
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: facebook/convnext-tiny-224
|
4 |
tags:
|
5 |
+
- image-classification
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
8 |
- accuracy
|
|
|
16 |
|
17 |
# akram-convNeXt-flipkarts
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the flipkarts_images dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.4581
|
22 |
- Accuracy: 0.8734
|
23 |
|
24 |
## Model description
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.8734177215189873,
|
4 |
+
"eval_loss": 0.45813843607902527,
|
5 |
+
"eval_runtime": 46.7016,
|
6 |
+
"eval_samples_per_second": 3.383,
|
7 |
+
"eval_steps_per_second": 0.428,
|
8 |
+
"total_flos": 8.966780447204966e+16,
|
9 |
+
"train_loss": 0.2551893559949739,
|
10 |
+
"train_runtime": 4113.2929,
|
11 |
+
"train_samples_per_second": 0.867,
|
12 |
+
"train_steps_per_second": 0.054
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.8734177215189873,
|
4 |
+
"eval_loss": 0.45813843607902527,
|
5 |
+
"eval_runtime": 46.7016,
|
6 |
+
"eval_samples_per_second": 3.383,
|
7 |
+
"eval_steps_per_second": 0.428
|
8 |
+
}
|
runs/Mar29_22-22-11_46bea10b934f/events.out.tfevents.1711755183.46bea10b934f.8755.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c5f7789608c2ba9eff5a9309b0efd0cfd6eebfefccd1f770c8c2c2e3f3a6f47
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"total_flos": 8.966780447204966e+16,
|
4 |
+
"train_loss": 0.2551893559949739,
|
5 |
+
"train_runtime": 4113.2929,
|
6 |
+
"train_samples_per_second": 0.867,
|
7 |
+
"train_steps_per_second": 0.054
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,247 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.45813843607902527,
|
3 |
+
"best_model_checkpoint": "akram-convNeXt-flipkarts/checkpoint-192",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 32,
|
6 |
+
"global_step": 224,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.18,
|
13 |
+
"grad_norm": 5.786337852478027,
|
14 |
+
"learning_rate": 0.00019107142857142858,
|
15 |
+
"loss": 0.4817,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.36,
|
20 |
+
"grad_norm": 3.83489727973938,
|
21 |
+
"learning_rate": 0.00018214285714285714,
|
22 |
+
"loss": 0.3841,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.54,
|
27 |
+
"grad_norm": 5.209750652313232,
|
28 |
+
"learning_rate": 0.00017321428571428574,
|
29 |
+
"loss": 0.3777,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.57,
|
34 |
+
"eval_accuracy": 0.8227848101265823,
|
35 |
+
"eval_loss": 0.5408539772033691,
|
36 |
+
"eval_runtime": 43.884,
|
37 |
+
"eval_samples_per_second": 3.6,
|
38 |
+
"eval_steps_per_second": 0.456,
|
39 |
+
"step": 32
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.71,
|
43 |
+
"grad_norm": 7.569049835205078,
|
44 |
+
"learning_rate": 0.00016428571428571428,
|
45 |
+
"loss": 0.4523,
|
46 |
+
"step": 40
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.89,
|
50 |
+
"grad_norm": 3.3220114707946777,
|
51 |
+
"learning_rate": 0.00015535714285714287,
|
52 |
+
"loss": 0.2812,
|
53 |
+
"step": 50
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.07,
|
57 |
+
"grad_norm": 2.3158109188079834,
|
58 |
+
"learning_rate": 0.00014642857142857141,
|
59 |
+
"loss": 0.131,
|
60 |
+
"step": 60
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.14,
|
64 |
+
"eval_accuracy": 0.8417721518987342,
|
65 |
+
"eval_loss": 0.5632613897323608,
|
66 |
+
"eval_runtime": 39.0388,
|
67 |
+
"eval_samples_per_second": 4.047,
|
68 |
+
"eval_steps_per_second": 0.512,
|
69 |
+
"step": 64
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 1.25,
|
73 |
+
"grad_norm": 1.282313585281372,
|
74 |
+
"learning_rate": 0.0001375,
|
75 |
+
"loss": 0.177,
|
76 |
+
"step": 70
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 1.43,
|
80 |
+
"grad_norm": 0.194750115275383,
|
81 |
+
"learning_rate": 0.00012857142857142858,
|
82 |
+
"loss": 0.1291,
|
83 |
+
"step": 80
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.61,
|
87 |
+
"grad_norm": 4.554263591766357,
|
88 |
+
"learning_rate": 0.00011964285714285714,
|
89 |
+
"loss": 0.1426,
|
90 |
+
"step": 90
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 1.71,
|
94 |
+
"eval_accuracy": 0.8291139240506329,
|
95 |
+
"eval_loss": 0.5170620083808899,
|
96 |
+
"eval_runtime": 38.7538,
|
97 |
+
"eval_samples_per_second": 4.077,
|
98 |
+
"eval_steps_per_second": 0.516,
|
99 |
+
"step": 96
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 1.79,
|
103 |
+
"grad_norm": 2.037961721420288,
|
104 |
+
"learning_rate": 0.00011071428571428572,
|
105 |
+
"loss": 0.2537,
|
106 |
+
"step": 100
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 1.96,
|
110 |
+
"grad_norm": 3.5785367488861084,
|
111 |
+
"learning_rate": 0.00010178571428571428,
|
112 |
+
"loss": 0.3462,
|
113 |
+
"step": 110
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 2.14,
|
117 |
+
"grad_norm": 3.6267411708831787,
|
118 |
+
"learning_rate": 9.285714285714286e-05,
|
119 |
+
"loss": 0.2413,
|
120 |
+
"step": 120
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 2.29,
|
124 |
+
"eval_accuracy": 0.8607594936708861,
|
125 |
+
"eval_loss": 0.47749054431915283,
|
126 |
+
"eval_runtime": 38.2656,
|
127 |
+
"eval_samples_per_second": 4.129,
|
128 |
+
"eval_steps_per_second": 0.523,
|
129 |
+
"step": 128
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 2.32,
|
133 |
+
"grad_norm": 18.910554885864258,
|
134 |
+
"learning_rate": 8.392857142857144e-05,
|
135 |
+
"loss": 0.2646,
|
136 |
+
"step": 130
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 2.5,
|
140 |
+
"grad_norm": 6.847780227661133,
|
141 |
+
"learning_rate": 7.500000000000001e-05,
|
142 |
+
"loss": 0.2463,
|
143 |
+
"step": 140
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 2.68,
|
147 |
+
"grad_norm": 5.892199993133545,
|
148 |
+
"learning_rate": 6.607142857142857e-05,
|
149 |
+
"loss": 0.3724,
|
150 |
+
"step": 150
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 2.86,
|
154 |
+
"grad_norm": 0.5983772277832031,
|
155 |
+
"learning_rate": 5.714285714285714e-05,
|
156 |
+
"loss": 0.1852,
|
157 |
+
"step": 160
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 2.86,
|
161 |
+
"eval_accuracy": 0.8607594936708861,
|
162 |
+
"eval_loss": 0.4647924304008484,
|
163 |
+
"eval_runtime": 37.8434,
|
164 |
+
"eval_samples_per_second": 4.175,
|
165 |
+
"eval_steps_per_second": 0.528,
|
166 |
+
"step": 160
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 3.04,
|
170 |
+
"grad_norm": 5.2921462059021,
|
171 |
+
"learning_rate": 4.8214285714285716e-05,
|
172 |
+
"loss": 0.3187,
|
173 |
+
"step": 170
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 3.21,
|
177 |
+
"grad_norm": 6.326498985290527,
|
178 |
+
"learning_rate": 3.928571428571429e-05,
|
179 |
+
"loss": 0.1574,
|
180 |
+
"step": 180
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 3.39,
|
184 |
+
"grad_norm": 8.077910423278809,
|
185 |
+
"learning_rate": 3.0357142857142857e-05,
|
186 |
+
"loss": 0.2165,
|
187 |
+
"step": 190
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 3.43,
|
191 |
+
"eval_accuracy": 0.8734177215189873,
|
192 |
+
"eval_loss": 0.45813843607902527,
|
193 |
+
"eval_runtime": 39.2858,
|
194 |
+
"eval_samples_per_second": 4.022,
|
195 |
+
"eval_steps_per_second": 0.509,
|
196 |
+
"step": 192
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 3.57,
|
200 |
+
"grad_norm": 1.3805155754089355,
|
201 |
+
"learning_rate": 2.1428571428571428e-05,
|
202 |
+
"loss": 0.1937,
|
203 |
+
"step": 200
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 3.75,
|
207 |
+
"grad_norm": 0.4734901785850525,
|
208 |
+
"learning_rate": 1.25e-05,
|
209 |
+
"loss": 0.134,
|
210 |
+
"step": 210
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 3.93,
|
214 |
+
"grad_norm": 4.029452323913574,
|
215 |
+
"learning_rate": 3.5714285714285714e-06,
|
216 |
+
"loss": 0.1529,
|
217 |
+
"step": 220
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 4.0,
|
221 |
+
"eval_accuracy": 0.8734177215189873,
|
222 |
+
"eval_loss": 0.4617495834827423,
|
223 |
+
"eval_runtime": 40.3868,
|
224 |
+
"eval_samples_per_second": 3.912,
|
225 |
+
"eval_steps_per_second": 0.495,
|
226 |
+
"step": 224
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 4.0,
|
230 |
+
"step": 224,
|
231 |
+
"total_flos": 8.966780447204966e+16,
|
232 |
+
"train_loss": 0.2551893559949739,
|
233 |
+
"train_runtime": 4113.2929,
|
234 |
+
"train_samples_per_second": 0.867,
|
235 |
+
"train_steps_per_second": 0.054
|
236 |
+
}
|
237 |
+
],
|
238 |
+
"logging_steps": 10,
|
239 |
+
"max_steps": 224,
|
240 |
+
"num_input_tokens_seen": 0,
|
241 |
+
"num_train_epochs": 4,
|
242 |
+
"save_steps": 32,
|
243 |
+
"total_flos": 8.966780447204966e+16,
|
244 |
+
"train_batch_size": 16,
|
245 |
+
"trial_name": null,
|
246 |
+
"trial_params": null
|
247 |
+
}
|