BhavanaMalla
commited on
Commit
•
52b7bed
1
Parent(s):
a91ab1e
Training in progress, epoch 2, checkpoint
Browse files
last-checkpoint/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 sha256:5e84012a42b7264147f476bfbc794385210e21e46e8f06e1186dd0e341c1f4a7
|
3 |
size 343528508
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 687177914
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eb1e008b66149caf60cd0beacf07bce45c2b33b99af923f68f5cdbea66984e6
|
3 |
size 687177914
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfb9e7e73a1b7c87b7911e42b7dd278d7293e2904e656e34ec0395e13687a9bd
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9563856c890612b67373c91bb13786ca6aa0a94f32246a70ba69f155129ec299
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.74,
|
3 |
"best_model_checkpoint": "image_classification_food101VITmodel/checkpoint-12",
|
4 |
-
"epoch":
|
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,
|
@@ -22,13 +22,43 @@
|
|
22 |
"eval_samples_per_second": 70.563,
|
23 |
"eval_steps_per_second": 4.587,
|
24 |
"step": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 10,
|
28 |
"max_steps": 36,
|
29 |
"num_train_epochs": 3,
|
30 |
"save_steps": 500,
|
31 |
-
"total_flos":
|
32 |
"trial_name": null,
|
33 |
"trial_params": null
|
34 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.74,
|
3 |
"best_model_checkpoint": "image_classification_food101VITmodel/checkpoint-12",
|
4 |
+
"epoch": 2.88,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 36,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
22 |
"eval_samples_per_second": 70.563,
|
23 |
"eval_steps_per_second": 4.587,
|
24 |
"step": 12
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.6,
|
28 |
+
"learning_rate": 2.5e-05,
|
29 |
+
"loss": 3.1492,
|
30 |
+
"step": 20
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.7,
|
35 |
+
"eval_loss": 2.6873395442962646,
|
36 |
+
"eval_runtime": 3.0132,
|
37 |
+
"eval_samples_per_second": 66.375,
|
38 |
+
"eval_steps_per_second": 4.314,
|
39 |
+
"step": 25
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.4,
|
43 |
+
"learning_rate": 9.375000000000001e-06,
|
44 |
+
"loss": 2.6294,
|
45 |
+
"step": 30
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 2.88,
|
49 |
+
"eval_accuracy": 0.715,
|
50 |
+
"eval_loss": 2.5155577659606934,
|
51 |
+
"eval_runtime": 3.1789,
|
52 |
+
"eval_samples_per_second": 62.914,
|
53 |
+
"eval_steps_per_second": 4.089,
|
54 |
+
"step": 36
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 10,
|
58 |
"max_steps": 36,
|
59 |
"num_train_epochs": 3,
|
60 |
"save_steps": 500,
|
61 |
+
"total_flos": 1.786999649992704e+17,
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|