End of training
Browse files- README.md +4 -4
- adapter_model.bin +1 -1
README.md
CHANGED
@@ -39,7 +39,7 @@ datasets:
|
|
39 |
system_prompt: ''
|
40 |
debug: null
|
41 |
deepspeed: null
|
42 |
-
device_map:
|
43 |
early_stopping_patience: 1
|
44 |
eval_batch_size: 1
|
45 |
eval_max_new_tokens: 128
|
@@ -118,7 +118,7 @@ xformers_attention: false
|
|
118 |
|
119 |
This model is a fine-tuned version of [Xenova/tiny-random-Phi3ForCausalLM](https://huggingface.co/Xenova/tiny-random-Phi3ForCausalLM) on the None dataset.
|
120 |
It achieves the following results on the evaluation set:
|
121 |
-
- Loss: 10.
|
122 |
|
123 |
## Model description
|
124 |
|
@@ -156,8 +156,8 @@ The following hyperparameters were used during training:
|
|
156 |
| Training Loss | Epoch | Step | Validation Loss |
|
157 |
|:-------------:|:------:|:----:|:---------------:|
|
158 |
| 10.3797 | 0.0026 | 1 | 10.3801 |
|
159 |
-
| 10.
|
160 |
-
| 10.
|
161 |
|
162 |
|
163 |
### Framework versions
|
|
|
39 |
system_prompt: ''
|
40 |
debug: null
|
41 |
deepspeed: null
|
42 |
+
device_map: sequentia
|
43 |
early_stopping_patience: 1
|
44 |
eval_batch_size: 1
|
45 |
eval_max_new_tokens: 128
|
|
|
118 |
|
119 |
This model is a fine-tuned version of [Xenova/tiny-random-Phi3ForCausalLM](https://huggingface.co/Xenova/tiny-random-Phi3ForCausalLM) on the None dataset.
|
120 |
It achieves the following results on the evaluation set:
|
121 |
+
- Loss: 10.3630
|
122 |
|
123 |
## Model description
|
124 |
|
|
|
156 |
| Training Loss | Epoch | Step | Validation Loss |
|
157 |
|:-------------:|:------:|:----:|:---------------:|
|
158 |
| 10.3797 | 0.0026 | 1 | 10.3801 |
|
159 |
+
| 10.3761 | 0.0655 | 25 | 10.3677 |
|
160 |
+
| 10.3705 | 0.1311 | 50 | 10.3630 |
|
161 |
|
162 |
|
163 |
### Framework versions
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 120926
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaf1003f12eacb01b1d6c7fb3da2954f220c70fde3e69b0379bb3d87281a53a9
|
3 |
size 120926
|