HorcruxNo13
commited on
Commit
•
dba613d
1
Parent(s):
b5ca258
Training in progress, epoch 1
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +67 -0
- training_args.bin +1 -1
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 2.32376605913088e+17,
|
4 |
+
"train_loss": 3.054683963457743,
|
5 |
+
"train_runtime": 175.6001,
|
6 |
+
"train_samples_per_second": 17.084,
|
7 |
+
"train_steps_per_second": 0.137
|
8 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343130249
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8dca2f33100b0c793032eab623a608267124b6599da1e88ff2db2542afdaea9
|
3 |
size 343130249
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 2.32376605913088e+17,
|
4 |
+
"train_loss": 3.054683963457743,
|
5 |
+
"train_runtime": 175.6001,
|
6 |
+
"train_samples_per_second": 17.084,
|
7 |
+
"train_steps_per_second": 0.137
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7333333333333333,
|
3 |
+
"best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k/checkpoint-8",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 24,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.7333333333333333,
|
14 |
+
"eval_loss": 3.1590805053710938,
|
15 |
+
"eval_runtime": 3.4474,
|
16 |
+
"eval_samples_per_second": 69.617,
|
17 |
+
"eval_steps_per_second": 2.321,
|
18 |
+
"step": 8
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.25,
|
22 |
+
"learning_rate": 0.03333333333333333,
|
23 |
+
"loss": 5.12,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"eval_accuracy": 0.26666666666666666,
|
29 |
+
"eval_loss": 2.633744716644287,
|
30 |
+
"eval_runtime": 3.2534,
|
31 |
+
"eval_samples_per_second": 73.768,
|
32 |
+
"eval_steps_per_second": 2.459,
|
33 |
+
"step": 16
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 2.5,
|
37 |
+
"learning_rate": 0.009523809523809525,
|
38 |
+
"loss": 1.8305,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 3.0,
|
43 |
+
"eval_accuracy": 0.7333333333333333,
|
44 |
+
"eval_loss": 0.6371921300888062,
|
45 |
+
"eval_runtime": 3.6339,
|
46 |
+
"eval_samples_per_second": 66.045,
|
47 |
+
"eval_steps_per_second": 2.202,
|
48 |
+
"step": 24
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"step": 24,
|
53 |
+
"total_flos": 2.32376605913088e+17,
|
54 |
+
"train_loss": 3.054683963457743,
|
55 |
+
"train_runtime": 175.6001,
|
56 |
+
"train_samples_per_second": 17.084,
|
57 |
+
"train_steps_per_second": 0.137
|
58 |
+
}
|
59 |
+
],
|
60 |
+
"logging_steps": 10,
|
61 |
+
"max_steps": 24,
|
62 |
+
"num_train_epochs": 3,
|
63 |
+
"save_steps": 500,
|
64 |
+
"total_flos": 2.32376605913088e+17,
|
65 |
+
"trial_name": null,
|
66 |
+
"trial_params": null
|
67 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:def589636faafdfc1f083571043dcbf0c33f8c8afbf5c2797dbb1df6693ed670
|
3 |
size 4091
|