Hugging Face's logo

aisuko
/
calculator

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
aisuko commited on
Commit
2b9b492
·
verified ·
1 Parent(s): 4d97fc7

**kwargs

Browse files
Files changed (11) hide show
  1. README.md +11 -11
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. runs/Dec06_23-06-28_default/events.out.tfevents.1733526389.default.1802.0 +3 -0
  5. runs/Dec06_23-08-25_default/events.out.tfevents.1733526505.default.2093.0 +3 -0
  6. runs/Dec06_23-12-46_default/events.out.tfevents.1733526766.default.2379.0 +3 -0
  7. runs/Dec06_23-14-02_default/events.out.tfevents.1733526842.default.2799.0 +3 -0
  8. runs/Dec06_23-21-30_default/events.out.tfevents.1733527290.default.3178.0 +3 -0
  9. runs/Dec06_23-48-58_default/events.out.tfevents.1733528939.default.3685.0 +3 -0
  10. runs/Dec06_23-48-58_default/events.out.tfevents.1733530992.default.3685.1 +3 -0
  11. training_args.bin +1 -1
README.md CHANGED
@@ -16,9 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.7111
20
- - Exact Match Ratio: 0.0
21
- - Sequence Accuracy: 0.0
22
 
23
  ## Model description
24
 
@@ -38,20 +36,22 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
- - train_batch_size: 8
42
- - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
- - num_epochs: 3
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss | Exact Match Ratio | Sequence Accuracy |
51
- |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:-----------------:|
52
- | 1.3755 | 1.0 | 500 | 0.7111 | 0.0 | 0.0 |
53
- | 1.1658 | 2.0 | 1000 | 1.0461 | 0.0 | 0.0 |
54
- | 1.0217 | 3.0 | 1500 | 0.7995 | 0.0 | 0.0 |
 
 
55
 
56
 
57
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.6422
 
 
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 2e-05
39
+ - train_batch_size: 24
40
+ - eval_batch_size: 24
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 5
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | 2.7655 | 1.0 | 167 | 0.6422 |
51
+ | 0.6496 | 2.0 | 334 | 0.6717 |
52
+ | 0.6479 | 3.0 | 501 | 0.6706 |
53
+ | 0.8804 | 4.0 | 668 | 0.8621 |
54
+ | 0.8283 | 5.0 | 835 | 0.7388 |
55
 
56
 
57
  ### Framework versions
adapter_config.json CHANGED
@@ -26,10 +26,10 @@
26
  "rank_pattern": {},
27
  "revision": null,
28
  "target_modules": [
29
- "qkv_proj",
30
- "down_proj",
31
  "gate_up_proj",
32
- "o_proj"
 
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
 
26
  "rank_pattern": {},
27
  "revision": null,
28
  "target_modules": [
29
+ "o_proj",
 
30
  "gate_up_proj",
31
+ "qkv_proj",
32
+ "down_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23ff80ac0881d0b146286fe51c47ae8c659ded1fb958af8712edcd2195100df7
3
  size 888703384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede0c3d8772bde5cc0c9aa4f9d1561ba9ebfd4d0f82db956ba7f9390d6cc51a6
3
  size 888703384
runs/Dec06_23-06-28_default/events.out.tfevents.1733526389.default.1802.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9a5d43eb280fd8beff8228d2e6ec2a0139be91899afd4ef38a82acaf869d7b
3
+ size 8409
runs/Dec06_23-08-25_default/events.out.tfevents.1733526505.default.2093.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e236dee036aefa0ce4549cbcf592eaf6248c4443da7a804c2b1e8fc0f5edf49
3
+ size 8409
runs/Dec06_23-12-46_default/events.out.tfevents.1733526766.default.2379.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3557c21060c159f2af6aafaf68aeb01e25308c9c92d40ed5187c473982aa5f57
3
+ size 8409
runs/Dec06_23-14-02_default/events.out.tfevents.1733526842.default.2799.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a8c7065dabef127ba142558025ece4cf211acbf74e40e879b5890046c8bc1d
3
+ size 8409
runs/Dec06_23-21-30_default/events.out.tfevents.1733527290.default.3178.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e5fe9e880333d6bf698e4927acbe3a5e6fec7141eb1d36438b57794bda4cd6
3
+ size 10210
runs/Dec06_23-48-58_default/events.out.tfevents.1733528939.default.3685.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a04fcc2a4f0b5e530e08e15396abc827c8d66216adf29635177305d43b528d
3
+ size 11173
runs/Dec06_23-48-58_default/events.out.tfevents.1733530992.default.3685.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a973a7f924f8a5d30127df64e0edee7517b5fee3dd5780911436da399417a7e
3
+ size 359
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12510a0bc410ceb3b1133e6fd17f26c3a9340e3895a0abf3208ec5cf3e778526
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d668e3c511e10a8a666786c1b9ffdbe2254bb587205cb613b44ff9aab8b28d70
3
  size 5304