Model save
Browse files- README.md +1 -1
- all_results.json +5 -5
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- train_results.json +5 -5
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -35,7 +35,7 @@ The following hyperparameters were used during training:
|
|
35 |
- learning_rate: 1e-06
|
36 |
- train_batch_size: 2
|
37 |
- eval_batch_size: 8
|
38 |
-
- seed:
|
39 |
- distributed_type: multi-GPU
|
40 |
- num_devices: 8
|
41 |
- gradient_accumulation_steps: 8
|
|
|
35 |
- learning_rate: 1e-06
|
36 |
- train_batch_size: 2
|
37 |
- eval_batch_size: 8
|
38 |
+
- seed: 3
|
39 |
- distributed_type: multi-GPU
|
40 |
- num_devices: 8
|
41 |
- gradient_accumulation_steps: 8
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second": 8.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
+
"train_loss": 0.11590367368682951,
|
4 |
+
"train_runtime": 24766.7088,
|
5 |
+
"train_samples": 106682,
|
6 |
+
"train_samples_per_second": 8.615,
|
7 |
+
"train_steps_per_second": 0.067
|
8 |
}
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3489fcaec81823ca8ae60e4455bb4632a4b4e86e4b8a920a3533de4f1482436e
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ebdc8cfbfe9010ea09e753efce060c7a93f352e7a3742747bb6e04afa768130
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea5399d071d1636e27fbee607807a2231bf69ac74f9997d515ea28fdc2b5b54f
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38702b95a0f22b50e9667d98ca314733d2fc34909db10f2ad9f44cbca40397fa
|
3 |
size 1168138808
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second": 8.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
+
"train_loss": 0.11590367368682951,
|
4 |
+
"train_runtime": 24766.7088,
|
5 |
+
"train_samples": 106682,
|
6 |
+
"train_samples_per_second": 8.615,
|
7 |
+
"train_steps_per_second": 0.067
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a874454b0be106b09135ca7d876005da005cccf11147d71834b9b4e2669c3e1
|
3 |
size 6648
|