Commit
•
9f2543d
1
Parent(s):
97cf2b3
update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,23 +2,11 @@
|
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
datasets:
|
| 6 |
-
- AlekseyKorshuk/dalio-synthetic-io
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: dalio-synthetic-io-1.3b
|
| 11 |
-
results:
|
| 12 |
-
- task:
|
| 13 |
-
name: Causal Language Modeling
|
| 14 |
-
type: text-generation
|
| 15 |
-
dataset:
|
| 16 |
-
name: AlekseyKorshuk/dalio-synthetic-io
|
| 17 |
-
type: AlekseyKorshuk/dalio-synthetic-io
|
| 18 |
-
metrics:
|
| 19 |
-
- name: Accuracy
|
| 20 |
-
type: accuracy
|
| 21 |
-
value: 0.06360215784940387
|
| 22 |
---
|
| 23 |
|
| 24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -26,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 26 |
|
| 27 |
# dalio-synthetic-io-1.3b
|
| 28 |
|
| 29 |
-
This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on
|
| 30 |
It achieves the following results on the evaluation set:
|
| 31 |
-
- Loss: 2.
|
| 32 |
- Accuracy: 0.0636
|
| 33 |
|
| 34 |
## Model description
|
|
@@ -58,7 +46,7 @@ The following hyperparameters were used during training:
|
|
| 58 |
- total_eval_batch_size: 16
|
| 59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
- lr_scheduler_type: cosine
|
| 61 |
-
- num_epochs:
|
| 62 |
|
| 63 |
### Training results
|
| 64 |
|
|
@@ -67,41 +55,22 @@ The following hyperparameters were used during training:
|
|
| 67 |
| 2.6941 | 0.05 | 1 | 2.6543 | 0.0622 |
|
| 68 |
| 2.6914 | 0.11 | 2 | 2.6543 | 0.0622 |
|
| 69 |
| 2.6003 | 0.16 | 3 | 2.6016 | 0.0627 |
|
| 70 |
-
| 2.5603 | 0.21 | 4 | 2.5703 | 0.
|
| 71 |
-
| 2.
|
| 72 |
-
| 2.5439 | 0.32 | 6 | 2.
|
| 73 |
-
| 2.
|
| 74 |
-
| 2.
|
| 75 |
-
| 2.
|
| 76 |
-
| 2.
|
| 77 |
-
| 2.
|
| 78 |
-
| 2.
|
| 79 |
-
| 2.
|
| 80 |
-
| 2.
|
| 81 |
-
| 2.
|
| 82 |
-
| 2.
|
| 83 |
-
| 2.
|
| 84 |
-
| 2.
|
| 85 |
-
| 2.
|
| 86 |
-
| 2.115 | 1.05 | 20 | 2.4805 | 0.0632 |
|
| 87 |
-
| 2.0885 | 1.11 | 21 | 2.4805 | 0.0635 |
|
| 88 |
-
| 1.9777 | 1.16 | 22 | 2.4805 | 0.0635 |
|
| 89 |
-
| 2.1053 | 1.21 | 23 | 2.4805 | 0.0634 |
|
| 90 |
-
| 1.9324 | 1.26 | 24 | 2.4824 | 0.0636 |
|
| 91 |
-
| 1.9122 | 1.32 | 25 | 2.4883 | 0.0637 |
|
| 92 |
-
| 2.1058 | 1.37 | 26 | 2.4961 | 0.0639 |
|
| 93 |
-
| 1.9803 | 1.42 | 27 | 2.5020 | 0.0639 |
|
| 94 |
-
| 1.6486 | 1.47 | 28 | 2.5098 | 0.0638 |
|
| 95 |
-
| 1.8983 | 1.53 | 29 | 2.5156 | 0.0636 |
|
| 96 |
-
| 1.8105 | 1.58 | 30 | 2.5215 | 0.0634 |
|
| 97 |
-
| 1.9916 | 1.63 | 31 | 2.5234 | 0.0634 |
|
| 98 |
-
| 1.886 | 1.68 | 32 | 2.5254 | 0.0635 |
|
| 99 |
-
| 1.8013 | 1.74 | 33 | 2.5273 | 0.0634 |
|
| 100 |
-
| 1.8435 | 1.79 | 34 | 2.5254 | 0.0634 |
|
| 101 |
-
| 2.1229 | 1.84 | 35 | 2.5234 | 0.0635 |
|
| 102 |
-
| 1.8739 | 1.89 | 36 | 2.5234 | 0.0636 |
|
| 103 |
-
| 1.7528 | 1.95 | 37 | 2.5234 | 0.0637 |
|
| 104 |
-
| 1.9462 | 2.0 | 38 | 2.5215 | 0.0636 |
|
| 105 |
|
| 106 |
|
| 107 |
### Framework versions
|
|
|
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
model-index:
|
| 8 |
- name: dalio-synthetic-io-1.3b
|
| 9 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 14 |
|
| 15 |
# dalio-synthetic-io-1.3b
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.4961
|
| 20 |
- Accuracy: 0.0636
|
| 21 |
|
| 22 |
## Model description
|
|
|
|
| 46 |
- total_eval_batch_size: 16
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: cosine
|
| 49 |
+
- num_epochs: 1.0
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
|
|
|
| 55 |
| 2.6941 | 0.05 | 1 | 2.6543 | 0.0622 |
|
| 56 |
| 2.6914 | 0.11 | 2 | 2.6543 | 0.0622 |
|
| 57 |
| 2.6003 | 0.16 | 3 | 2.6016 | 0.0627 |
|
| 58 |
+
| 2.5603 | 0.21 | 4 | 2.5703 | 0.0626 |
|
| 59 |
+
| 2.606 | 0.26 | 5 | 2.5508 | 0.0629 |
|
| 60 |
+
| 2.5439 | 0.32 | 6 | 2.5449 | 0.0629 |
|
| 61 |
+
| 2.4449 | 0.37 | 7 | 2.5469 | 0.0629 |
|
| 62 |
+
| 2.5422 | 0.42 | 8 | 2.5469 | 0.0630 |
|
| 63 |
+
| 2.6101 | 0.47 | 9 | 2.5410 | 0.0632 |
|
| 64 |
+
| 2.4482 | 0.53 | 10 | 2.5352 | 0.0630 |
|
| 65 |
+
| 2.501 | 0.58 | 11 | 2.5293 | 0.0631 |
|
| 66 |
+
| 2.5967 | 0.63 | 12 | 2.5215 | 0.0634 |
|
| 67 |
+
| 2.4998 | 0.68 | 13 | 2.5137 | 0.0635 |
|
| 68 |
+
| 2.5957 | 0.74 | 14 | 2.5098 | 0.0636 |
|
| 69 |
+
| 2.5967 | 0.79 | 15 | 2.5039 | 0.0639 |
|
| 70 |
+
| 2.5022 | 0.84 | 16 | 2.5 | 0.0637 |
|
| 71 |
+
| 2.4314 | 0.89 | 17 | 2.4980 | 0.0637 |
|
| 72 |
+
| 2.6279 | 0.95 | 18 | 2.4961 | 0.0636 |
|
| 73 |
+
| 2.571 | 1.0 | 19 | 2.4961 | 0.0636 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
|
| 75 |
|
| 76 |
### Framework versions
|