Training in progress, step 50
Browse files- README.md +4 -4
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
|
20 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 3.
|
23 |
- Accuracy: 0.5853
|
24 |
|
25 |
## Model description
|
@@ -44,10 +44,10 @@ The following hyperparameters were used during training:
|
|
44 |
- eval_batch_size: 16
|
45 |
- seed: 0
|
46 |
- distributed_type: multi-GPU
|
47 |
-
- num_devices:
|
48 |
- gradient_accumulation_steps: 2
|
49 |
-
- total_train_batch_size:
|
50 |
-
- total_eval_batch_size:
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
- training_steps: 1
|
|
|
19 |
|
20 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 3.1608
|
23 |
- Accuracy: 0.5853
|
24 |
|
25 |
## Model description
|
|
|
44 |
- eval_batch_size: 16
|
45 |
- seed: 0
|
46 |
- distributed_type: multi-GPU
|
47 |
+
- num_devices: 2
|
48 |
- gradient_accumulation_steps: 2
|
49 |
+
- total_train_batch_size: 32
|
50 |
+
- total_eval_batch_size: 32
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
- training_steps: 1
|
adapter_config.json
CHANGED
@@ -19,10 +19,10 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
22 |
"v_proj",
|
23 |
-
"down_proj",
|
24 |
"gate_proj",
|
25 |
-
"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
"v_proj",
|
|
|
24 |
"gate_proj",
|
25 |
+
"down_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 205555592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f94acb29af39cdd30b52d2b5cb2480192add2d5503cfe540910288eec22993d
|
3 |
size 205555592
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943163992
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:706b9414e303b804b2b4a33561b9f74287ad622cdf1c029d9624b2648d1c5dad
|
3 |
size 4943163992
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999821144
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b8d2339fc0094554e8bde54863832035b1e719d7a4fcbf130cefbd53425f623
|
3 |
size 4999821144
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540517840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:097515acca12bf753d19048b5c2b1ff6615e2d2b5857cbd9cb0be6ef01507d1f
|
3 |
size 4540517840
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef8e4f6cf1e1d9dcb165a9211d12ec220baecf11a6d9f322934f4a72d264cd25
|
3 |
size 6008
|