BraylonDash
commited on
Commit
•
aa84d88
1
Parent(s):
a7e3cda
Model save
Browse files- README.md +1 -5
- adapter_model.safetensors +1 -1
- all_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +11 -11
- training_args.bin +1 -1
README.md
CHANGED
@@ -2,14 +2,10 @@
|
|
2 |
license: mit
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
-
- generated_from_trainer
|
7 |
- trl
|
8 |
- dpo
|
9 |
- generated_from_trainer
|
10 |
base_model: microsoft/phi-2
|
11 |
-
datasets:
|
12 |
-
- HuggingFaceH4/ultrafeedback_binarized
|
13 |
model-index:
|
14 |
- name: phi-2-gpo-test-longest-iter-0
|
15 |
results: []
|
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
# phi-2-gpo-test-longest-iter-0
|
22 |
|
23 |
-
This model is a fine-tuned version of [
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
2 |
license: mit
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
8 |
base_model: microsoft/phi-2
|
|
|
|
|
9 |
model-index:
|
10 |
- name: phi-2-gpo-test-longest-iter-0
|
11 |
results: []
|
|
|
16 |
|
17 |
# phi-2-gpo-test-longest-iter-0
|
18 |
|
19 |
+
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41977616
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c99237b61ddbcc12b02ca16d9318ff7a9125e77add338ae7faccac130d33f3ad
|
3 |
size 41977616
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 30567,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"train_loss": 0.0011036931537091732,
|
4 |
+
"train_runtime": 3.0822,
|
5 |
"train_samples": 30567,
|
6 |
+
"train_samples_per_second": 0.649,
|
7 |
+
"train_steps_per_second": 0.649
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 30567,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"train_loss": 0.0011036931537091732,
|
4 |
+
"train_runtime": 3.0822,
|
5 |
"train_samples": 30567,
|
6 |
+
"train_samples_per_second": 0.649,
|
7 |
+
"train_steps_per_second": 0.649
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 100,
|
6 |
"global_step": 2,
|
7 |
"is_hyper_param_search": false,
|
@@ -11,11 +11,11 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"learning_rate": 5e-06,
|
14 |
-
"logits/chosen":
|
15 |
-
"logits/rejected": 0.
|
16 |
-
"logps/chosen": -
|
17 |
-
"logps/rejected": -
|
18 |
-
"loss": 0.
|
19 |
"rewards/accuracies": 0.0,
|
20 |
"rewards/chosen": 0.0,
|
21 |
"rewards/margins": 0.0,
|
@@ -23,13 +23,13 @@
|
|
23 |
"step": 1
|
24 |
},
|
25 |
{
|
26 |
-
"epoch":
|
27 |
"step": 2,
|
28 |
"total_flos": 0.0,
|
29 |
-
"train_loss": 0.
|
30 |
-
"train_runtime":
|
31 |
-
"train_samples_per_second":
|
32 |
-
"train_steps_per_second": 0.
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 10,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 100,
|
6 |
"global_step": 2,
|
7 |
"is_hyper_param_search": false,
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"learning_rate": 5e-06,
|
14 |
+
"logits/chosen": 0.785413920879364,
|
15 |
+
"logits/rejected": 0.9495257139205933,
|
16 |
+
"logps/chosen": -93.63787078857422,
|
17 |
+
"logps/rejected": -77.81773376464844,
|
18 |
+
"loss": 0.0011,
|
19 |
"rewards/accuracies": 0.0,
|
20 |
"rewards/chosen": 0.0,
|
21 |
"rewards/margins": 0.0,
|
|
|
23 |
"step": 1
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 2.0,
|
27 |
"step": 2,
|
28 |
"total_flos": 0.0,
|
29 |
+
"train_loss": 0.0011036931537091732,
|
30 |
+
"train_runtime": 3.0822,
|
31 |
+
"train_samples_per_second": 0.649,
|
32 |
+
"train_steps_per_second": 0.649
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 10,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22abc2e60df559c1c10cf59282f459875a7647c8d066a3c469953dc85674676a
|
3 |
size 5880
|