Training in progress, step 582, checkpoint
Browse files
checkpoint-582/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 494777904
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52e872b92d65ee9c018cbe1d42112eda9b4a77423cfda063f2ca51977740f1e0
|
3 |
size 494777904
|
checkpoint-582/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 989645754
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e57e18426c03092087f3abcf6a950defc4e6b702756f92df62712d4bd343077c
|
3 |
size 989645754
|
checkpoint-582/trainer_state.json
CHANGED
@@ -10,55 +10,55 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.06891798759476224,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 9.88326321974139e-06,
|
15 |
-
"loss": 0.
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.13783597518952448,
|
20 |
-
"grad_norm":
|
21 |
"learning_rate": 9.53850386931162e-06,
|
22 |
-
"loss": 0.
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.2005513439007581,
|
27 |
-
"eval_accuracy": 0.
|
28 |
-
"eval_loss": 0.
|
29 |
-
"eval_runtime":
|
30 |
-
"eval_samples_per_second":
|
31 |
-
"eval_steps_per_second": 21.
|
32 |
"step": 291
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.2067539627842867,
|
36 |
-
"grad_norm":
|
37 |
"learning_rate": 8.981820387323976e-06,
|
38 |
-
"loss": 0.
|
39 |
"step": 300
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.27567195037904896,
|
43 |
-
"grad_norm":
|
44 |
"learning_rate": 8.239206948702616e-06,
|
45 |
-
"loss": 0.
|
46 |
"step": 400
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.34458993797381116,
|
50 |
-
"grad_norm":
|
51 |
"learning_rate": 7.345339674168113e-06,
|
52 |
-
"loss": 0.
|
53 |
"step": 500
|
54 |
},
|
55 |
{
|
56 |
"epoch": 0.4011026878015162,
|
57 |
-
"eval_accuracy": 0.
|
58 |
-
"eval_loss": 0.
|
59 |
-
"eval_runtime":
|
60 |
-
"eval_samples_per_second": 174.
|
61 |
-
"eval_steps_per_second": 21.
|
62 |
"step": 582
|
63 |
}
|
64 |
],
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.06891798759476224,
|
13 |
+
"grad_norm": 2056.53857421875,
|
14 |
"learning_rate": 9.88326321974139e-06,
|
15 |
+
"loss": 0.6821,
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.13783597518952448,
|
20 |
+
"grad_norm": 1819.6336669921875,
|
21 |
"learning_rate": 9.53850386931162e-06,
|
22 |
+
"loss": 0.6584,
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.2005513439007581,
|
27 |
+
"eval_accuracy": 0.6663206128732011,
|
28 |
+
"eval_loss": 0.6131747961044312,
|
29 |
+
"eval_runtime": 482.559,
|
30 |
+
"eval_samples_per_second": 173.662,
|
31 |
+
"eval_steps_per_second": 21.709,
|
32 |
"step": 291
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.2067539627842867,
|
36 |
+
"grad_norm": 1910.1011962890625,
|
37 |
"learning_rate": 8.981820387323976e-06,
|
38 |
+
"loss": 0.6434,
|
39 |
"step": 300
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.27567195037904896,
|
43 |
+
"grad_norm": 1810.4771728515625,
|
44 |
"learning_rate": 8.239206948702616e-06,
|
45 |
+
"loss": 0.6385,
|
46 |
"step": 400
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.34458993797381116,
|
50 |
+
"grad_norm": 1388.5435791015625,
|
51 |
"learning_rate": 7.345339674168113e-06,
|
52 |
+
"loss": 0.6248,
|
53 |
"step": 500
|
54 |
},
|
55 |
{
|
56 |
"epoch": 0.4011026878015162,
|
57 |
+
"eval_accuracy": 0.6850433163886304,
|
58 |
+
"eval_loss": 0.5890468955039978,
|
59 |
+
"eval_runtime": 481.5926,
|
60 |
+
"eval_samples_per_second": 174.01,
|
61 |
+
"eval_steps_per_second": 21.753,
|
62 |
"step": 582
|
63 |
}
|
64 |
],
|
checkpoint-582/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c006e54ea2fe3388052228de4bb025a6b560f297cbb8ca0c1442b57d9461bbd8
|
3 |
size 5240
|