End of training
Browse files- README.md +5 -5
- adapter_config.json +5 -5
- adapter_model.bin +1 -1
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -114,7 +114,7 @@ xformers_attention: null
|
|
114 |
|
115 |
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.6](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.6) on the None dataset.
|
116 |
It achieves the following results on the evaluation set:
|
117 |
-
- Loss: 5.
|
118 |
|
119 |
## Model description
|
120 |
|
@@ -153,10 +153,10 @@ The following hyperparameters were used during training:
|
|
153 |
| Training Loss | Epoch | Step | Validation Loss |
|
154 |
|:-------------:|:------:|:----:|:---------------:|
|
155 |
| 7.6743 | 0.0028 | 1 | 7.1293 |
|
156 |
-
| 7.
|
157 |
-
| 7.
|
158 |
-
| 5.
|
159 |
-
| 5.
|
160 |
|
161 |
|
162 |
### Framework versions
|
|
|
114 |
|
115 |
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.6](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.6) on the None dataset.
|
116 |
It achieves the following results on the evaluation set:
|
117 |
+
- Loss: 5.1046
|
118 |
|
119 |
## Model description
|
120 |
|
|
|
153 |
| Training Loss | Epoch | Step | Validation Loss |
|
154 |
|:-------------:|:------:|:----:|:---------------:|
|
155 |
| 7.6743 | 0.0028 | 1 | 7.1293 |
|
156 |
+
| 7.7426 | 0.0141 | 5 | 7.0973 |
|
157 |
+
| 7.0417 | 0.0283 | 10 | 6.3321 |
|
158 |
+
| 5.7705 | 0.0424 | 15 | 5.4978 |
|
159 |
+
| 5.6954 | 0.0565 | 20 | 5.1046 |
|
160 |
|
161 |
|
162 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"up_proj",
|
24 |
-
"o_proj",
|
25 |
-
"gate_proj",
|
26 |
"v_proj",
|
27 |
-
"
|
28 |
"down_proj",
|
29 |
-
"
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
23 |
"v_proj",
|
24 |
+
"up_proj",
|
25 |
"down_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"o_proj",
|
28 |
+
"q_proj",
|
29 |
+
"k_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 101036698
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75d6d99a911e1898887876a012bb5f063d98f1d0f108c408c15a9a760ccc085a
|
3 |
size 101036698
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100966336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6937250c3c124f08bcfec45cd4a325f3405cb3f1f96296f7ad31bd5500713d84
|
3 |
size 100966336
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b55d7424e01d2da7c827809f0e75e814ca3307809331f5d1880db7934ea6a65
|
3 |
size 6712
|