Commit
•
776fb1c
1
Parent(s):
8e62039
update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,34 +2,22 @@
|
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
datasets:
|
| 6 |
-
- AlekseyKorshuk/dalio-handwritten-io
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
model-index:
|
| 10 |
-
- name:
|
| 11 |
-
results:
|
| 12 |
-
- task:
|
| 13 |
-
name: Causal Language Modeling
|
| 14 |
-
type: text-generation
|
| 15 |
-
dataset:
|
| 16 |
-
name: AlekseyKorshuk/dalio-handwritten-io
|
| 17 |
-
type: AlekseyKorshuk/dalio-handwritten-io
|
| 18 |
-
metrics:
|
| 19 |
-
- name: Accuracy
|
| 20 |
-
type: accuracy
|
| 21 |
-
value: 0.06414321574844761
|
| 22 |
---
|
| 23 |
|
| 24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 25 |
should probably proofread and complete it, then remove this comment. -->
|
| 26 |
|
| 27 |
-
#
|
| 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.
|
| 33 |
|
| 34 |
## Model description
|
| 35 |
|
|
@@ -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 |
|
|
@@ -67,53 +55,33 @@ The following hyperparameters were used during training:
|
|
| 67 |
| 2.9219 | 0.1 | 1 | 2.6484 | 0.0529 |
|
| 68 |
| 2.6938 | 0.2 | 2 | 2.6484 | 0.0529 |
|
| 69 |
| 2.6365 | 0.3 | 3 | 2.5508 | 0.0560 |
|
| 70 |
-
| 2.5088 | 0.4 | 4 | 2.5332 | 0.
|
| 71 |
-
| 2.
|
| 72 |
-
| 2.
|
| 73 |
-
| 2.
|
| 74 |
-
| 2.
|
| 75 |
-
| 2.
|
| 76 |
-
| 2.
|
| 77 |
-
| 2.
|
| 78 |
-
|
|
| 79 |
-
| 1.
|
| 80 |
-
| 1.
|
| 81 |
-
| 1.
|
| 82 |
-
| 1.
|
| 83 |
-
| 2.
|
| 84 |
-
| 1.
|
| 85 |
-
| 1.
|
| 86 |
-
| 1.
|
| 87 |
-
| 1.
|
| 88 |
-
| 1.
|
| 89 |
-
| 1.
|
| 90 |
-
| 1.
|
| 91 |
-
| 1.
|
| 92 |
-
| 1.
|
| 93 |
-
| 1.
|
| 94 |
-
| 1.
|
| 95 |
-
| 1.
|
| 96 |
-
|
|
| 97 |
-
| 0.6635 | 3.1 | 31 | 2.4512 | 0.0628 |
|
| 98 |
-
| 0.9996 | 3.2 | 32 | 2.4434 | 0.0635 |
|
| 99 |
-
| 0.9029 | 3.3 | 33 | 2.4473 | 0.0637 |
|
| 100 |
-
| 0.8329 | 3.4 | 34 | 2.4551 | 0.0637 |
|
| 101 |
-
| 0.8012 | 3.5 | 35 | 2.4648 | 0.0639 |
|
| 102 |
-
| 0.5814 | 3.6 | 36 | 2.4902 | 0.0640 |
|
| 103 |
-
| 1.0688 | 3.7 | 37 | 2.5098 | 0.0638 |
|
| 104 |
-
| 0.8688 | 3.8 | 38 | 2.5176 | 0.0635 |
|
| 105 |
-
| 0.7341 | 3.9 | 39 | 2.5195 | 0.0638 |
|
| 106 |
-
| 0.7102 | 4.0 | 40 | 2.5195 | 0.0640 |
|
| 107 |
-
| 0.7079 | 4.1 | 41 | 2.5195 | 0.0641 |
|
| 108 |
-
| 0.7656 | 4.2 | 42 | 2.5195 | 0.0643 |
|
| 109 |
-
| 0.6377 | 4.3 | 43 | 2.5273 | 0.0645 |
|
| 110 |
-
| 0.5898 | 4.4 | 44 | 2.5352 | 0.0641 |
|
| 111 |
-
| 0.5958 | 4.5 | 45 | 2.5430 | 0.0641 |
|
| 112 |
-
| 0.7048 | 4.6 | 46 | 2.5488 | 0.0640 |
|
| 113 |
-
| 0.5435 | 4.7 | 47 | 2.5527 | 0.0641 |
|
| 114 |
-
| 0.4769 | 4.8 | 48 | 2.5527 | 0.0640 |
|
| 115 |
-
| 0.6583 | 4.9 | 49 | 2.5547 | 0.0642 |
|
| 116 |
-
| 0.7168 | 5.0 | 50 | 2.5547 | 0.0641 |
|
| 117 |
|
| 118 |
|
| 119 |
### Framework versions
|
|
|
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
model-index:
|
| 8 |
+
- name: dalio-handwritten-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
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
+
# dalio-handwritten-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: 2.3789
|
| 20 |
+
- Accuracy: 0.0614
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 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: 3.0
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
|
|
|
| 55 |
| 2.9219 | 0.1 | 1 | 2.6484 | 0.0529 |
|
| 56 |
| 2.6938 | 0.2 | 2 | 2.6484 | 0.0529 |
|
| 57 |
| 2.6365 | 0.3 | 3 | 2.5508 | 0.0560 |
|
| 58 |
+
| 2.5088 | 0.4 | 4 | 2.5332 | 0.0562 |
|
| 59 |
+
| 2.7307 | 0.5 | 5 | 2.5176 | 0.0565 |
|
| 60 |
+
| 2.969 | 0.6 | 6 | 2.4941 | 0.0571 |
|
| 61 |
+
| 2.7283 | 0.7 | 7 | 2.4883 | 0.0567 |
|
| 62 |
+
| 2.6157 | 0.8 | 8 | 2.4766 | 0.0578 |
|
| 63 |
+
| 2.6406 | 0.9 | 9 | 2.4590 | 0.0583 |
|
| 64 |
+
| 2.5701 | 1.0 | 10 | 2.4375 | 0.0587 |
|
| 65 |
+
| 2.2017 | 1.1 | 11 | 2.4238 | 0.0587 |
|
| 66 |
+
| 2.0039 | 1.2 | 12 | 2.4219 | 0.0586 |
|
| 67 |
+
| 1.8981 | 1.3 | 13 | 2.4160 | 0.0589 |
|
| 68 |
+
| 1.7683 | 1.4 | 14 | 2.4160 | 0.0595 |
|
| 69 |
+
| 1.6746 | 1.5 | 15 | 2.4121 | 0.0600 |
|
| 70 |
+
| 1.8051 | 1.6 | 16 | 2.4102 | 0.0600 |
|
| 71 |
+
| 2.0457 | 1.7 | 17 | 2.4043 | 0.0602 |
|
| 72 |
+
| 1.8257 | 1.8 | 18 | 2.4004 | 0.0606 |
|
| 73 |
+
| 1.744 | 1.9 | 19 | 2.3887 | 0.0607 |
|
| 74 |
+
| 1.8232 | 2.0 | 20 | 2.3887 | 0.0607 |
|
| 75 |
+
| 1.4741 | 2.1 | 21 | 2.3828 | 0.0610 |
|
| 76 |
+
| 1.651 | 2.2 | 22 | 2.3770 | 0.0608 |
|
| 77 |
+
| 1.3732 | 2.3 | 23 | 2.3730 | 0.0610 |
|
| 78 |
+
| 1.3151 | 2.4 | 24 | 2.3730 | 0.0610 |
|
| 79 |
+
| 1.5302 | 2.5 | 25 | 2.3730 | 0.0610 |
|
| 80 |
+
| 1.2539 | 2.6 | 26 | 2.375 | 0.0612 |
|
| 81 |
+
| 1.6211 | 2.7 | 27 | 2.3770 | 0.0612 |
|
| 82 |
+
| 1.6047 | 2.8 | 28 | 2.3770 | 0.0613 |
|
| 83 |
+
| 1.1953 | 2.9 | 29 | 2.3789 | 0.0614 |
|
| 84 |
+
| 1.1621 | 3.0 | 30 | 2.3789 | 0.0614 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
|
| 87 |
### Framework versions
|