kyryl-georgian
commited on
Commit
•
c36e568
1
Parent(s):
5e13998
End of training
Browse files- README.md +1 -1
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- all_results.json +8 -8
- eval_results.json +4 -4
- train_results.json +4 -4
- trainer_state.json +4 -4
- training_args.bin +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 2.
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.0264
|
20 |
|
21 |
## Model description
|
22 |
|
adapter_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "SEQ_2_SEQ_LM"
|
26 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"q",
|
23 |
+
"v"
|
24 |
],
|
25 |
"task_type": "SEQ_2_SEQ_LM"
|
26 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2765880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a03d4e539a82a040feeccde74e5633e843d346b85beb2c43cae043affb618b03
|
3 |
size 2765880
|
all_results.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
-
"eval_loss": 2.
|
4 |
-
"eval_runtime": 13.
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second": 37.
|
7 |
-
"train_loss": 2.
|
8 |
-
"train_runtime": 0.
|
9 |
-
"train_samples_per_second": 0.
|
10 |
-
"train_steps_per_second": 1.
|
11 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
+
"eval_loss": 2.0264487266540527,
|
4 |
+
"eval_runtime": 13.1026,
|
5 |
+
"eval_samples_per_second": 599.65,
|
6 |
+
"eval_steps_per_second": 37.55,
|
7 |
+
"train_loss": 2.772763967514038,
|
8 |
+
"train_runtime": 0.7537,
|
9 |
+
"train_samples_per_second": 0.133,
|
10 |
+
"train_steps_per_second": 1.327
|
11 |
}
|
eval_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
-
"eval_loss": 2.
|
4 |
-
"eval_runtime": 13.
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second": 37.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
+
"eval_loss": 2.0264487266540527,
|
4 |
+
"eval_runtime": 13.1026,
|
5 |
+
"eval_samples_per_second": 599.65,
|
6 |
+
"eval_steps_per_second": 37.55
|
7 |
}
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
-
"train_loss": 2.
|
4 |
-
"train_runtime": 0.
|
5 |
-
"train_samples_per_second": 0.
|
6 |
-
"train_steps_per_second": 1.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
+
"train_loss": 2.772763967514038,
|
4 |
+
"train_runtime": 0.7537,
|
5 |
+
"train_samples_per_second": 0.133,
|
6 |
+
"train_steps_per_second": 1.327
|
7 |
}
|
trainer_state.json
CHANGED
@@ -12,10 +12,10 @@
|
|
12 |
"epoch": 0.02,
|
13 |
"step": 1,
|
14 |
"total_flos": 517012193280.0,
|
15 |
-
"train_loss": 2.
|
16 |
-
"train_runtime": 0.
|
17 |
-
"train_samples_per_second": 0.
|
18 |
-
"train_steps_per_second": 1.
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
|
|
12 |
"epoch": 0.02,
|
13 |
"step": 1,
|
14 |
"total_flos": 517012193280.0,
|
15 |
+
"train_loss": 2.772763967514038,
|
16 |
+
"train_runtime": 0.7537,
|
17 |
+
"train_samples_per_second": 0.133,
|
18 |
+
"train_steps_per_second": 1.327
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9e0d9736052cdde0edd1a81958c16b8f65bde9254be336df08c495d757cdab3
|
3 |
size 5112
|