End of training
Browse files- README.md +3 -2
- chat_template.jinja +24 -0
- config.json +7 -1
- model.safetensors +2 -2
- runs/Mar01_20-10-48_df9c3a37a31c/events.out.tfevents.1772395950.df9c3a37a31c.88.0 +3 -0
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -27,14 +27,15 @@ print(output["score"])
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
-
|
|
|
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with Reward.
|
| 34 |
|
| 35 |
### Framework versions
|
| 36 |
|
| 37 |
-
- TRL: 0.
|
| 38 |
- Transformers: 4.57.1
|
| 39 |
- Pytorch: 2.8.0+cu126
|
| 40 |
- Datasets: 4.4.2
|
|
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
+
|
| 31 |
+
|
| 32 |
|
| 33 |
|
| 34 |
This model was trained with Reward.
|
| 35 |
|
| 36 |
### Framework versions
|
| 37 |
|
| 38 |
+
- TRL: 0.29.0
|
| 39 |
- Transformers: 4.57.1
|
| 40 |
- Pytorch: 2.8.0+cu126
|
| 41 |
- Datasets: 4.4.2
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- for message in messages -%}
|
| 2 |
+
{%- set content = message.content if message.content is string else "" -%}
|
| 3 |
+
{%- if message.role == "user" -%}
|
| 4 |
+
{{ "<|im_start|>" + message.role + "
|
| 5 |
+
" + content + "<|im_end|>
|
| 6 |
+
" }}
|
| 7 |
+
{%- elif message.role == "assistant" -%}
|
| 8 |
+
{% generation %}
|
| 9 |
+
{{ "<|im_start|>assistant
|
| 10 |
+
" + content.lstrip("
|
| 11 |
+
") + "<|im_end|>
|
| 12 |
+
" }}
|
| 13 |
+
{% endgeneration %}
|
| 14 |
+
{%- endif -%}
|
| 15 |
+
{%- endfor -%}
|
| 16 |
+
{# ───── generation prompt ───── #}
|
| 17 |
+
{%- if add_generation_prompt -%}
|
| 18 |
+
|
| 19 |
+
{{ "<|im_start|>assistant
|
| 20 |
+
" + "<think>
|
| 21 |
+
|
| 22 |
+
</think>
|
| 23 |
+
" }}
|
| 24 |
+
{%- endif -%}
|
config.json
CHANGED
|
@@ -13,8 +13,14 @@
|
|
| 13 |
"head_dim": 256,
|
| 14 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
"hidden_size": 640,
|
|
|
|
|
|
|
|
|
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
"intermediate_size": 2048,
|
|
|
|
|
|
|
|
|
|
| 18 |
"layer_types": [
|
| 19 |
"sliding_attention",
|
| 20 |
"sliding_attention",
|
|
@@ -50,5 +56,5 @@
|
|
| 50 |
"transformers_version": "4.57.1",
|
| 51 |
"use_bidirectional_attention": false,
|
| 52 |
"use_cache": true,
|
| 53 |
-
"vocab_size":
|
| 54 |
}
|
|
|
|
| 13 |
"head_dim": 256,
|
| 14 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
"hidden_size": 640,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "LABEL_0"
|
| 18 |
+
},
|
| 19 |
"initializer_range": 0.02,
|
| 20 |
"intermediate_size": 2048,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0
|
| 23 |
+
},
|
| 24 |
"layer_types": [
|
| 25 |
"sliding_attention",
|
| 26 |
"sliding_attention",
|
|
|
|
| 56 |
"transformers_version": "4.57.1",
|
| 57 |
"use_bidirectional_attention": false,
|
| 58 |
"use_cache": true,
|
| 59 |
+
"vocab_size": 262147
|
| 60 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64388433a90441a8ad7fac8ddb0580075d9e01b1870e8a3ef61ae97c5ae27116
|
| 3 |
+
size 1072429584
|
runs/Mar01_20-10-48_df9c3a37a31c/events.out.tfevents.1772395950.df9c3a37a31c.88.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ec92990c1870e3fef93372dd68510e12033d2ecf36bea52fe9f8cc14e1348ca
|
| 3 |
+
size 43238
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca59eb1c06f1689cc0023b60fa26ad801750128409443858acc2f28d661fd513
|
| 3 |
+
size 6033
|