Training in progress, step 300
Browse files- all_results.json +9 -9
- config.json +22 -24
- eval_results.json +5 -5
- model.safetensors +2 -2
- runs/Mar29_18-51-27_X5C922065N/events.out.tfevents.1711734830.X5C922065N.77198.1 +3 -0
- runs/Mar29_18-51-27_X5C922065N/events.out.tfevents.1711734965.X5C922065N.77198.2 +3 -0
- train_results.json +4 -4
- trainer_state.json +10 -17
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
"total_flos": 7439897757745152.0,
|
9 |
-
"train_loss":
|
10 |
-
"train_runtime": 7.
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 1.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9583333333333334,
|
4 |
+
"eval_loss": 1.039479374885559,
|
5 |
+
"eval_runtime": 1.0974,
|
6 |
+
"eval_samples_per_second": 21.87,
|
7 |
+
"eval_steps_per_second": 2.734,
|
8 |
"total_flos": 7439897757745152.0,
|
9 |
+
"train_loss": 1.4209961891174316,
|
10 |
+
"train_runtime": 7.3487,
|
11 |
+
"train_samples_per_second": 13.064,
|
12 |
+
"train_steps_per_second": 1.089
|
13 |
}
|
config.json
CHANGED
@@ -9,35 +9,33 @@
|
|
9 |
"hidden_dropout_prob": 0.0,
|
10 |
"hidden_size": 768,
|
11 |
"id2label": {
|
12 |
-
"0": "
|
13 |
-
"1": "
|
14 |
-
"10": "
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"9": "plastic garbage and paper garbage"
|
24 |
},
|
25 |
"image_size": 224,
|
26 |
"initializer_range": 0.02,
|
27 |
"intermediate_size": 3072,
|
28 |
"label2id": {
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"plastic
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"used plastic bottles labels": "11"
|
41 |
},
|
42 |
"layer_norm_eps": 1e-12,
|
43 |
"model_type": "vit",
|
|
|
9 |
"hidden_dropout_prob": 0.0,
|
10 |
"hidden_size": 768,
|
11 |
"id2label": {
|
12 |
+
"0": "aluminium",
|
13 |
+
"1": "batteries",
|
14 |
+
"10": "takeaway cups",
|
15 |
+
"2": "cardboard",
|
16 |
+
"3": "disposable plates",
|
17 |
+
"4": "glass",
|
18 |
+
"5": "hard plastic",
|
19 |
+
"6": "paper",
|
20 |
+
"7": "paper towel",
|
21 |
+
"8": "polystyrene",
|
22 |
+
"9": "soft plastics"
|
|
|
23 |
},
|
24 |
"image_size": 224,
|
25 |
"initializer_range": 0.02,
|
26 |
"intermediate_size": 3072,
|
27 |
"label2id": {
|
28 |
+
"aluminium": "0",
|
29 |
+
"batteries": "1",
|
30 |
+
"cardboard": "2",
|
31 |
+
"disposable plates": "3",
|
32 |
+
"glass": "4",
|
33 |
+
"hard plastic": "5",
|
34 |
+
"paper": "6",
|
35 |
+
"paper towel": "7",
|
36 |
+
"polystyrene": "8",
|
37 |
+
"soft plastics": "9",
|
38 |
+
"takeaway cups": "10"
|
|
|
39 |
},
|
40 |
"layer_norm_eps": 1e-12,
|
41 |
"model_type": "vit",
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9583333333333334,
|
4 |
+
"eval_loss": 1.039479374885559,
|
5 |
+
"eval_runtime": 1.0974,
|
6 |
+
"eval_samples_per_second": 21.87,
|
7 |
+
"eval_steps_per_second": 2.734
|
8 |
}
|
model.safetensors
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:ca8ca01f0c031632e2131270776a232480fdf9bfe32ab7ad11e498d1d677a5a9
|
3 |
+
size 343251660
|
runs/Mar29_18-51-27_X5C922065N/events.out.tfevents.1711734830.X5C922065N.77198.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb92060756fa2c4f538ca77c69a721411f79d55d3f3537b2e74a15d4cca51788
|
3 |
+
size 405
|
runs/Mar29_18-51-27_X5C922065N/events.out.tfevents.1711734965.X5C922065N.77198.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b64f0498695854ebda0c5046adb2a9adece839413b4b4c765764e35204ae4c2a
|
3 |
+
size 12367
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"total_flos": 7439897757745152.0,
|
4 |
-
"train_loss":
|
5 |
-
"train_runtime": 7.
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 1.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"total_flos": 7439897757745152.0,
|
4 |
+
"train_loss": 1.4209961891174316,
|
5 |
+
"train_runtime": 7.3487,
|
6 |
+
"train_samples_per_second": 13.064,
|
7 |
+
"train_steps_per_second": 1.089
|
8 |
}
|
trainer_state.json
CHANGED
@@ -2,36 +2,29 @@
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 4.0,
|
5 |
-
"eval_steps":
|
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": 3.33,
|
13 |
-
"grad_norm": 2.8058300018310547,
|
14 |
-
"learning_rate": 3.3333333333333335e-05,
|
15 |
-
"loss": 2.1093,
|
16 |
-
"step": 10
|
17 |
-
},
|
18 |
{
|
19 |
"epoch": 4.0,
|
20 |
-
"step":
|
21 |
"total_flos": 7439897757745152.0,
|
22 |
-
"train_loss":
|
23 |
-
"train_runtime": 7.
|
24 |
-
"train_samples_per_second":
|
25 |
-
"train_steps_per_second": 1.
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 10,
|
29 |
-
"max_steps":
|
30 |
"num_input_tokens_seen": 0,
|
31 |
"num_train_epochs": 4,
|
32 |
-
"save_steps":
|
33 |
"total_flos": 7439897757745152.0,
|
34 |
-
"train_batch_size":
|
35 |
"trial_name": null,
|
36 |
"trial_params": null
|
37 |
}
|
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 4.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 8,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
{
|
12 |
"epoch": 4.0,
|
13 |
+
"step": 8,
|
14 |
"total_flos": 7439897757745152.0,
|
15 |
+
"train_loss": 1.4209961891174316,
|
16 |
+
"train_runtime": 7.3487,
|
17 |
+
"train_samples_per_second": 13.064,
|
18 |
+
"train_steps_per_second": 1.089
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 10,
|
22 |
+
"max_steps": 8,
|
23 |
"num_input_tokens_seen": 0,
|
24 |
"num_train_epochs": 4,
|
25 |
+
"save_steps": 100,
|
26 |
"total_flos": 7439897757745152.0,
|
27 |
+
"train_batch_size": 16,
|
28 |
"trial_name": null,
|
29 |
"trial_params": null
|
30 |
}
|