wish6424/Mixtral-8x7B-prostate-sum-test
Browse files- README.md +8 -11
- adapter_config.json +6 -6
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -20,7 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -40,21 +45,13 @@ More information needed
|
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
- learning_rate: 2.5e-05
|
| 43 |
-
- train_batch_size:
|
| 44 |
- eval_batch_size: 8
|
| 45 |
- seed: 42
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- lr_scheduler_warmup_steps: 0.03
|
| 49 |
-
- training_steps:
|
| 50 |
-
|
| 51 |
-
### Training results
|
| 52 |
-
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
-
| 1.2988 | 0.83 | 10 | 1.4094 |
|
| 56 |
-
| 1.3009 | 1.67 | 20 | 1.3804 |
|
| 57 |
-
|
| 58 |
|
| 59 |
### Framework versions
|
| 60 |
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- eval_loss: 0.9034
|
| 24 |
+
- eval_runtime: 1.0713
|
| 25 |
+
- eval_samples_per_second: 0.933
|
| 26 |
+
- eval_steps_per_second: 0.933
|
| 27 |
+
- epoch: 41.67
|
| 28 |
+
- step: 250
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 45 |
|
| 46 |
The following hyperparameters were used during training:
|
| 47 |
- learning_rate: 2.5e-05
|
| 48 |
+
- train_batch_size: 4
|
| 49 |
- eval_batch_size: 8
|
| 50 |
- seed: 42
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: linear
|
| 53 |
- lr_scheduler_warmup_steps: 0.03
|
| 54 |
+
- training_steps: 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
### Framework versions
|
| 57 |
|
adapter_config.json
CHANGED
|
@@ -19,14 +19,14 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"lm_head",
|
| 23 |
"up_proj",
|
| 24 |
-
"o_proj",
|
| 25 |
-
"down_proj",
|
| 26 |
-
"gate_proj",
|
| 27 |
"v_proj",
|
| 28 |
-
"
|
| 29 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_rslora": false
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
| 22 |
"up_proj",
|
|
|
|
|
|
|
|
|
|
| 23 |
"v_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"lm_head",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_rslora": false
|
adapter_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:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
|
| 3 |
+
size 48
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab72c733dc6e47c7b384d00f452f5d4378116cc3fb8c04b2a7a452a0404da25a
|
| 3 |
size 4728
|