End of training
Browse files- README.md +51 -51
- config.json +1 -1
- final_checkpoint/config.json +1 -1
- final_checkpoint/model-00001-of-00003.safetensors +1 -1
- final_checkpoint/model-00002-of-00003.safetensors +1 -1
- final_checkpoint/model-00003-of-00003.safetensors +1 -1
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- tokenizer.json +1 -6
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: tsavage68/
|
4 |
tags:
|
5 |
- trl
|
6 |
- dpo
|
@@ -15,17 +15,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# UTI_M2_1000steps_1e6rate_01beta_CSFTDPO
|
17 |
|
18 |
-
This model is a fine-tuned version of [tsavage68/
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Rewards/chosen:
|
22 |
-
- Rewards/rejected:
|
23 |
-
- Rewards/accuracies: 0.
|
24 |
-
- Rewards/margins:
|
25 |
-
- Logps/rejected:
|
26 |
-
- Logps/chosen:
|
27 |
-
- Logits/rejected: -
|
28 |
-
- Logits/chosen: -
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -59,46 +59,46 @@ The following hyperparameters were used during training:
|
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
61 |
|:-------------:|:-------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
-
| 0.
|
98 |
-
| 0.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.
|
102 |
|
103 |
|
104 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: tsavage68/UTI_M2_1000steps_1e7rate_SFT
|
4 |
tags:
|
5 |
- trl
|
6 |
- dpo
|
|
|
15 |
|
16 |
# UTI_M2_1000steps_1e6rate_01beta_CSFTDPO
|
17 |
|
18 |
+
This model is a fine-tuned version of [tsavage68/UTI_M2_1000steps_1e7rate_SFT](https://huggingface.co/tsavage68/UTI_M2_1000steps_1e7rate_SFT) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.6931
|
21 |
+
- Rewards/chosen: 0.0
|
22 |
+
- Rewards/rejected: 0.0
|
23 |
+
- Rewards/accuracies: 0.0
|
24 |
+
- Rewards/margins: 0.0
|
25 |
+
- Logps/rejected: 0.0
|
26 |
+
- Logps/chosen: 0.0
|
27 |
+
- Logits/rejected: -2.7147
|
28 |
+
- Logits/chosen: -2.7147
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
61 |
|:-------------:|:-------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
62 |
+
| 0.6931 | 0.3333 | 25 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
63 |
+
| 0.6931 | 0.6667 | 50 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
64 |
+
| 0.6931 | 1.0 | 75 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
65 |
+
| 0.6931 | 1.3333 | 100 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
66 |
+
| 0.6931 | 1.6667 | 125 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
67 |
+
| 0.6931 | 2.0 | 150 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
68 |
+
| 0.6931 | 2.3333 | 175 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
69 |
+
| 0.6931 | 2.6667 | 200 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
70 |
+
| 0.6931 | 3.0 | 225 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
71 |
+
| 0.6931 | 3.3333 | 250 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
72 |
+
| 0.6931 | 3.6667 | 275 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
73 |
+
| 0.6931 | 4.0 | 300 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
74 |
+
| 0.6931 | 4.3333 | 325 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
75 |
+
| 0.6931 | 4.6667 | 350 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
76 |
+
| 0.6931 | 5.0 | 375 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
77 |
+
| 0.6931 | 5.3333 | 400 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
78 |
+
| 0.6931 | 5.6667 | 425 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
79 |
+
| 0.6931 | 6.0 | 450 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
80 |
+
| 0.6931 | 6.3333 | 475 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
81 |
+
| 0.6931 | 6.6667 | 500 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
82 |
+
| 0.6931 | 7.0 | 525 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
83 |
+
| 0.6931 | 7.3333 | 550 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
84 |
+
| 0.6931 | 7.6667 | 575 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
85 |
+
| 0.6931 | 8.0 | 600 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
86 |
+
| 0.6931 | 8.3333 | 625 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
87 |
+
| 0.6931 | 8.6667 | 650 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
88 |
+
| 0.6931 | 9.0 | 675 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
89 |
+
| 0.6931 | 9.3333 | 700 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
90 |
+
| 0.6931 | 9.6667 | 725 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
91 |
+
| 0.6931 | 10.0 | 750 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
92 |
+
| 0.6931 | 10.3333 | 775 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
93 |
+
| 0.6931 | 10.6667 | 800 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
94 |
+
| 0.6931 | 11.0 | 825 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
95 |
+
| 0.6931 | 11.3333 | 850 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
96 |
+
| 0.6931 | 11.6667 | 875 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
97 |
+
| 0.6931 | 12.0 | 900 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
98 |
+
| 0.6931 | 12.3333 | 925 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
99 |
+
| 0.6931 | 12.6667 | 950 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
100 |
+
| 0.6931 | 13.0 | 975 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
101 |
+
| 0.6931 | 13.3333 | 1000 | 0.6931 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -2.7147 | -2.7147 |
|
102 |
|
103 |
|
104 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "tsavage68/
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "tsavage68/UTI_M2_1000steps_1e7rate_SFT",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
final_checkpoint/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "tsavage68/
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "tsavage68/UTI_M2_1000steps_1e7rate_SFT",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
final_checkpoint/model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aa2e9687a5e5d24a999a996e9fe4c2bc1cf34ad347da5dc5c7e0adffcb14982
|
3 |
size 4943162240
|
final_checkpoint/model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:268bb18cc8bbff53c912fa3961a6281dd5c163edd1b8e5c85c9b12e87e4e3a63
|
3 |
size 4999819232
|
final_checkpoint/model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbc021dcf68d9e7ddaab0ead255721e73b7f652e3bfd34985bba6c029e0b729c
|
3 |
size 4540516256
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aa2e9687a5e5d24a999a996e9fe4c2bc1cf34ad347da5dc5c7e0adffcb14982
|
3 |
size 4943162240
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:268bb18cc8bbff53c912fa3961a6281dd5c163edd1b8e5c85c9b12e87e4e3a63
|
3 |
size 4999819232
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbc021dcf68d9e7ddaab0ead255721e73b7f652e3bfd34985bba6c029e0b729c
|
3 |
size 4540516256
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 100,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
tokenizer_config.json
CHANGED
@@ -33,7 +33,7 @@
|
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": true,
|
36 |
-
"max_length":
|
37 |
"model_max_length": 1000000000000000019884624838656,
|
38 |
"pad_token": "</s>",
|
39 |
"sp_model_kwargs": {},
|
|
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": true,
|
36 |
+
"max_length": 1024,
|
37 |
"model_max_length": 1000000000000000019884624838656,
|
38 |
"pad_token": "</s>",
|
39 |
"sp_model_kwargs": {},
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4667
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85d41aa2220d703aa4ec988f9e436865de293d1cc91617442bb8b97d5013ae5c
|
3 |
size 4667
|