Commit
•
8d9286c
1
Parent(s):
1464f66
End of training
Browse files
README.md
CHANGED
@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- eval_loss:
|
21 |
-
- eval_accuracy: 0.
|
22 |
-
- eval_runtime:
|
23 |
-
- eval_samples_per_second:
|
24 |
-
- eval_steps_per_second: 6.
|
25 |
-
- epoch:
|
26 |
-
- step:
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- eval_loss: 1.9754
|
21 |
+
- eval_accuracy: 0.7336
|
22 |
+
- eval_runtime: 156.8793
|
23 |
+
- eval_samples_per_second: 96.571
|
24 |
+
- eval_steps_per_second: 6.036
|
25 |
+
- epoch: 8.45
|
26 |
+
- step: 8000
|
27 |
|
28 |
## Model description
|
29 |
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343528508
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b20edeb0fe7d3b161c0a46a58cae188fa221d032d8c7766255b9a02137a73c09
|
3 |
size 343528508
|
runs/Feb05_03-08-58_983d148b451b/events.out.tfevents.1707102539.983d148b451b.26.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a033a1a586ec82c34e1ea9c30d4c0e829e843a9fd4da33e9e4e02374982ce418
|
3 |
+
size 13141
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "food-image-classification/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -112,6 +112,21 @@
|
|
112 |
"eval_samples_per_second": 97.367,
|
113 |
"eval_steps_per_second": 6.086,
|
114 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
115 |
}
|
116 |
],
|
117 |
"logging_steps": 1000,
|
@@ -119,7 +134,7 @@
|
|
119 |
"num_input_tokens_seen": 0,
|
120 |
"num_train_epochs": 500,
|
121 |
"save_steps": 1000,
|
122 |
-
"total_flos": 3.
|
123 |
"train_batch_size": 16,
|
124 |
"trial_name": null,
|
125 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7070627062706271,
|
3 |
+
"best_model_checkpoint": "food-image-classification/checkpoint-7000",
|
4 |
+
"epoch": 8.447729672650475,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 8000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
112 |
"eval_samples_per_second": 97.367,
|
113 |
"eval_steps_per_second": 6.086,
|
114 |
"step": 7000
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 8.45,
|
118 |
+
"learning_rate": 8.447729672650476e-06,
|
119 |
+
"loss": 2.1397,
|
120 |
+
"step": 8000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 8.45,
|
124 |
+
"eval_accuracy": 0.7335973597359736,
|
125 |
+
"eval_loss": 1.975380539894104,
|
126 |
+
"eval_runtime": 156.8793,
|
127 |
+
"eval_samples_per_second": 96.571,
|
128 |
+
"eval_steps_per_second": 6.036,
|
129 |
+
"step": 8000
|
130 |
}
|
131 |
],
|
132 |
"logging_steps": 1000,
|
|
|
134 |
"num_input_tokens_seen": 0,
|
135 |
"num_train_epochs": 500,
|
136 |
"save_steps": 1000,
|
137 |
+
"total_flos": 3.970613944525455e+19,
|
138 |
"train_batch_size": 16,
|
139 |
"trial_name": null,
|
140 |
"trial_params": null
|