scottsuk0306
commited on
Commit
•
0fe2f8c
1
Parent(s):
c3773fa
Model save
Browse files- README.md +4 -21
- all_results.json +4 -4
- config.json +1 -1
- 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
- tokenizer_config.json +0 -1
- train_results.json +4 -4
- trainer_state.json +20 -20
README.md
CHANGED
@@ -2,28 +2,14 @@
|
|
2 |
license: cc-by-nc-4.0
|
3 |
base_model: sfairXC/FsfairX-LLaMA3-RM-v0.1
|
4 |
tags:
|
5 |
-
- easylm
|
6 |
-
- alignment-handbook
|
7 |
- trl
|
8 |
- reward-trainer
|
|
|
|
|
9 |
- generated_from_trainer
|
10 |
-
datasets:
|
11 |
-
- helpsteer-rm
|
12 |
-
metrics:
|
13 |
-
- accuracy
|
14 |
model-index:
|
15 |
- name: easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
|
16 |
-
results:
|
17 |
-
- task:
|
18 |
-
name: Text Classification
|
19 |
-
type: text-classification
|
20 |
-
dataset:
|
21 |
-
name: helpsteer-rm
|
22 |
-
type: helpsteer-rm
|
23 |
-
metrics:
|
24 |
-
- name: Accuracy
|
25 |
-
type: accuracy
|
26 |
-
value: 0.6189111747851003
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,10 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
# easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
|
33 |
|
34 |
-
This model is a fine-tuned version of [sfairXC/FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) on
|
35 |
-
It achieves the following results on the evaluation set:
|
36 |
-
- Loss: 0.6558
|
37 |
-
- Accuracy: 0.6189
|
38 |
|
39 |
## Model description
|
40 |
|
|
|
2 |
license: cc-by-nc-4.0
|
3 |
base_model: sfairXC/FsfairX-LLaMA3-RM-v0.1
|
4 |
tags:
|
|
|
|
|
5 |
- trl
|
6 |
- reward-trainer
|
7 |
+
- easylm
|
8 |
+
- alignment-handbook
|
9 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
10 |
model-index:
|
11 |
- name: easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
|
12 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
17 |
|
18 |
# easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
|
19 |
|
20 |
+
This model is a fine-tuned version of [sfairXC/FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) on an unknown dataset.
|
|
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
all_results.json
CHANGED
@@ -7,9 +7,9 @@
|
|
7 |
"eval_samples_per_second": 58.504,
|
8 |
"eval_steps_per_second": 7.376,
|
9 |
"total_flos": 0.0,
|
10 |
-
"train_loss": 0.
|
11 |
-
"train_runtime":
|
12 |
"train_samples": 6666,
|
13 |
-
"train_samples_per_second":
|
14 |
-
"train_steps_per_second": 1.
|
15 |
}
|
|
|
7 |
"eval_samples_per_second": 58.504,
|
8 |
"eval_steps_per_second": 7.376,
|
9 |
"total_flos": 0.0,
|
10 |
+
"train_loss": 0.7041080118083268,
|
11 |
+
"train_runtime": 641.2149,
|
12 |
"train_samples": 6666,
|
13 |
+
"train_samples_per_second": 10.396,
|
14 |
+
"train_steps_per_second": 1.301
|
15 |
}
|
config.json
CHANGED
@@ -31,6 +31,6 @@
|
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
"transformers_version": "4.43.3",
|
34 |
-
"use_cache":
|
35 |
"vocab_size": 128257
|
36 |
}
|
|
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
"transformers_version": "4.43.3",
|
34 |
+
"use_cache": false,
|
35 |
"vocab_size": 128257
|
36 |
}
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976706864
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f9b22e371184aacf60c8753ab4b3bf18b8091bd6600809c9d9a01574cf15ac6
|
3 |
size 4976706864
|
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 sha256:9fb9476172104f9cbf563c96804d75d9910295c5f44b62b4815cefd5928c837a
|
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 sha256:4be2c3efd182a08c5d23dddabf93c35c1ecb0316e338e60b7db71fabb06ce02e
|
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 117473824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:816c0d28901233ff0b5b13c507ffdcb6f99a08574fb73c407351aa7ee9ea847a
|
3 |
size 117473824
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_eos_token": true,
|
3 |
"added_tokens_decoder": {
|
4 |
"128000": {
|
5 |
"content": "<|begin_of_text|>",
|
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"128000": {
|
4 |
"content": "<|begin_of_text|>",
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 6666,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 1.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.7041080118083268,
|
5 |
+
"train_runtime": 641.2149,
|
6 |
"train_samples": 6666,
|
7 |
+
"train_samples_per_second": 10.396,
|
8 |
+
"train_steps_per_second": 1.301
|
9 |
}
|
trainer_state.json
CHANGED
@@ -10,68 +10,68 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.11990407673860912,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 1.929887378670186e-05,
|
15 |
-
"loss": 0.
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.23980815347721823,
|
20 |
-
"grad_norm":
|
21 |
"learning_rate": 1.729381074020218e-05,
|
22 |
-
"loss": 0.
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.3597122302158273,
|
27 |
-
"grad_norm":
|
28 |
"learning_rate": 1.4265971312744252e-05,
|
29 |
-
"loss": 0.
|
30 |
"step": 300
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.47961630695443647,
|
34 |
-
"grad_norm":
|
35 |
"learning_rate": 1.0639935022777741e-05,
|
36 |
-
"loss": 0.
|
37 |
"step": 400
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.5995203836930456,
|
41 |
-
"grad_norm":
|
42 |
"learning_rate": 6.924163688955825e-06,
|
43 |
-
"loss": 0.
|
44 |
"step": 500
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.7194244604316546,
|
48 |
-
"grad_norm": 4.
|
49 |
"learning_rate": 3.6397022482313804e-06,
|
50 |
-
"loss": 0.
|
51 |
"step": 600
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.8393285371702638,
|
55 |
-
"grad_norm":
|
56 |
"learning_rate": 1.2471151031361795e-06,
|
57 |
-
"loss": 0.
|
58 |
"step": 700
|
59 |
},
|
60 |
{
|
61 |
"epoch": 0.9592326139088729,
|
62 |
-
"grad_norm": 12.
|
63 |
"learning_rate": 8.190336667550869e-08,
|
64 |
-
"loss": 0.
|
65 |
"step": 800
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.0,
|
69 |
"step": 834,
|
70 |
"total_flos": 0.0,
|
71 |
-
"train_loss": 0.
|
72 |
-
"train_runtime":
|
73 |
-
"train_samples_per_second":
|
74 |
-
"train_steps_per_second": 1.
|
75 |
}
|
76 |
],
|
77 |
"logging_steps": 100,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.11990407673860912,
|
13 |
+
"grad_norm": 33.553314208984375,
|
14 |
"learning_rate": 1.929887378670186e-05,
|
15 |
+
"loss": 0.7732,
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.23980815347721823,
|
20 |
+
"grad_norm": 5.416075706481934,
|
21 |
"learning_rate": 1.729381074020218e-05,
|
22 |
+
"loss": 0.7018,
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.3597122302158273,
|
27 |
+
"grad_norm": 5.061486721038818,
|
28 |
"learning_rate": 1.4265971312744252e-05,
|
29 |
+
"loss": 0.7014,
|
30 |
"step": 300
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.47961630695443647,
|
34 |
+
"grad_norm": 3.992720603942871,
|
35 |
"learning_rate": 1.0639935022777741e-05,
|
36 |
+
"loss": 0.6841,
|
37 |
"step": 400
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.5995203836930456,
|
41 |
+
"grad_norm": 4.914097785949707,
|
42 |
"learning_rate": 6.924163688955825e-06,
|
43 |
+
"loss": 0.7251,
|
44 |
"step": 500
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.7194244604316546,
|
48 |
+
"grad_norm": 4.0411577224731445,
|
49 |
"learning_rate": 3.6397022482313804e-06,
|
50 |
+
"loss": 0.6829,
|
51 |
"step": 600
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.8393285371702638,
|
55 |
+
"grad_norm": 5.131595611572266,
|
56 |
"learning_rate": 1.2471151031361795e-06,
|
57 |
+
"loss": 0.6744,
|
58 |
"step": 700
|
59 |
},
|
60 |
{
|
61 |
"epoch": 0.9592326139088729,
|
62 |
+
"grad_norm": 12.620176315307617,
|
63 |
"learning_rate": 8.190336667550869e-08,
|
64 |
+
"loss": 0.6864,
|
65 |
"step": 800
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.0,
|
69 |
"step": 834,
|
70 |
"total_flos": 0.0,
|
71 |
+
"train_loss": 0.7041080118083268,
|
72 |
+
"train_runtime": 641.2149,
|
73 |
+
"train_samples_per_second": 10.396,
|
74 |
+
"train_steps_per_second": 1.301
|
75 |
}
|
76 |
],
|
77 |
"logging_steps": 100,
|