End of training
Browse files- README.md +2 -0
- all_results.json +12 -12
- eval_results.json +4 -4
- test_results.json +4 -4
- tokenizer.json +16 -2
- train_results.json +4 -4
- trainer_state.json +9 -9
README.md
CHANGED
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# clip-finetuned
|
16 |
|
17 |
This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on the imagefolder dataset.
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
15 |
# clip-finetuned
|
16 |
|
17 |
This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on the imagefolder dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 3.5183
|
20 |
|
21 |
## Model description
|
22 |
|
all_results.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
-
"eval_loss": 3.
|
4 |
-
"eval_runtime": 2.
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second": 0.
|
7 |
-
"test_loss": 3.
|
8 |
-
"test_runtime":
|
9 |
-
"test_samples_per_second":
|
10 |
-
"test_steps_per_second":
|
11 |
-
"train_loss": 1.
|
12 |
-
"train_runtime":
|
13 |
-
"train_samples_per_second":
|
14 |
-
"train_steps_per_second":
|
15 |
}
|
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
+
"eval_loss": 3.5183489322662354,
|
4 |
+
"eval_runtime": 2.3671,
|
5 |
+
"eval_samples_per_second": 21.546,
|
6 |
+
"eval_steps_per_second": 0.845,
|
7 |
+
"test_loss": 3.517756462097168,
|
8 |
+
"test_runtime": 1.5745,
|
9 |
+
"test_samples_per_second": 64.781,
|
10 |
+
"test_steps_per_second": 2.54,
|
11 |
+
"train_loss": 1.2736186100886417,
|
12 |
+
"train_runtime": 133.9465,
|
13 |
+
"train_samples_per_second": 30.684,
|
14 |
+
"train_steps_per_second": 0.971
|
15 |
}
|
eval_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
-
"eval_loss": 3.
|
4 |
-
"eval_runtime": 2.
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second": 0.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
+
"eval_loss": 3.5183489322662354,
|
4 |
+
"eval_runtime": 2.3671,
|
5 |
+
"eval_samples_per_second": 21.546,
|
6 |
+
"eval_steps_per_second": 0.845
|
7 |
}
|
test_results.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"test_loss": 3.
|
3 |
-
"test_runtime":
|
4 |
-
"test_samples_per_second":
|
5 |
-
"test_steps_per_second":
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"test_loss": 3.517756462097168,
|
3 |
+
"test_runtime": 1.5745,
|
4 |
+
"test_samples_per_second": 64.781,
|
5 |
+
"test_steps_per_second": 2.54
|
6 |
}
|
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 49406,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 77,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 77
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 49407,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "<|endoftext|>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 49406,
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples_per_second":
|
6 |
-
"train_steps_per_second":
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
+
"train_loss": 1.2736186100886417,
|
4 |
+
"train_runtime": 133.9465,
|
5 |
+
"train_samples_per_second": 30.684,
|
6 |
+
"train_steps_per_second": 0.971
|
7 |
}
|
trainer_state.json
CHANGED
@@ -3,27 +3,27 @@
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 10.0,
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 10.0,
|
13 |
-
"step":
|
14 |
-
"total_flos":
|
15 |
-
"train_loss": 1.
|
16 |
-
"train_runtime":
|
17 |
-
"train_samples_per_second":
|
18 |
-
"train_steps_per_second":
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
-
"max_steps":
|
23 |
"num_input_tokens_seen": 0,
|
24 |
"num_train_epochs": 10,
|
25 |
"save_steps": 500,
|
26 |
-
"total_flos":
|
27 |
"train_batch_size": 32,
|
28 |
"trial_name": null,
|
29 |
"trial_params": null
|
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 10.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 130,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 10.0,
|
13 |
+
"step": 130,
|
14 |
+
"total_flos": 239066361640260.0,
|
15 |
+
"train_loss": 1.2736186100886417,
|
16 |
+
"train_runtime": 133.9465,
|
17 |
+
"train_samples_per_second": 30.684,
|
18 |
+
"train_steps_per_second": 0.971
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
+
"max_steps": 130,
|
23 |
"num_input_tokens_seen": 0,
|
24 |
"num_train_epochs": 10,
|
25 |
"save_steps": 500,
|
26 |
+
"total_flos": 239066361640260.0,
|
27 |
"train_batch_size": 32,
|
28 |
"trial_name": null,
|
29 |
"trial_params": null
|