End of training
Browse files- README.md +16 -4
- all_results.json +16 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1733515979.ki-g0009.1456862.1 +3 -0
- train_results.json +9 -0
- trainer_state.json +0 -0
README.md
CHANGED
|
@@ -2,11 +2,23 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
model-index:
|
| 8 |
- name: bert_tiny_lda_book
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -14,10 +26,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# bert_tiny_lda_book
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 3.
|
| 20 |
-
- Accuracy: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- gokulsrinivasagan/processed_book_corpus-ld
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: bert_tiny_lda_book
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Masked Language Modeling
|
| 14 |
+
type: fill-mask
|
| 15 |
+
dataset:
|
| 16 |
+
name: gokulsrinivasagan/processed_book_corpus-ld
|
| 17 |
+
type: gokulsrinivasagan/processed_book_corpus-ld
|
| 18 |
+
metrics:
|
| 19 |
+
- name: Accuracy
|
| 20 |
+
type: accuracy
|
| 21 |
+
value: 0.6827213137673483
|
| 22 |
---
|
| 23 |
|
| 24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 26 |
|
| 27 |
# bert_tiny_lda_book
|
| 28 |
|
| 29 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the gokulsrinivasagan/processed_book_corpus-ld dataset.
|
| 30 |
It achieves the following results on the evaluation set:
|
| 31 |
+
- Loss: 3.3915
|
| 32 |
+
- Accuracy: 0.6827
|
| 33 |
|
| 34 |
## Model description
|
| 35 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"eval_accuracy": 0.6827213137673483,
|
| 4 |
+
"eval_loss": 3.3915183544158936,
|
| 5 |
+
"eval_runtime": 139.4499,
|
| 6 |
+
"eval_samples": 120706,
|
| 7 |
+
"eval_samples_per_second": 865.587,
|
| 8 |
+
"eval_steps_per_second": 5.414,
|
| 9 |
+
"perplexity": 29.711029913259157,
|
| 10 |
+
"total_flos": 3.038176470544589e+18,
|
| 11 |
+
"train_loss": 4.100663753765192,
|
| 12 |
+
"train_runtime": 96704.9936,
|
| 13 |
+
"train_samples": 2277342,
|
| 14 |
+
"train_samples_per_second": 588.734,
|
| 15 |
+
"train_steps_per_second": 3.68
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"eval_accuracy": 0.6827213137673483,
|
| 4 |
+
"eval_loss": 3.3915183544158936,
|
| 5 |
+
"eval_runtime": 139.4499,
|
| 6 |
+
"eval_samples": 120706,
|
| 7 |
+
"eval_samples_per_second": 865.587,
|
| 8 |
+
"eval_steps_per_second": 5.414,
|
| 9 |
+
"perplexity": 29.711029913259157
|
| 10 |
+
}
|
logs/events.out.tfevents.1733515979.ki-g0009.1456862.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba6ac4fe2770fe36b2fbcff1a2ca80171fd07690772edf4e961d59844610738b
|
| 3 |
+
size 417
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"total_flos": 3.038176470544589e+18,
|
| 4 |
+
"train_loss": 4.100663753765192,
|
| 5 |
+
"train_runtime": 96704.9936,
|
| 6 |
+
"train_samples": 2277342,
|
| 7 |
+
"train_samples_per_second": 588.734,
|
| 8 |
+
"train_steps_per_second": 3.68
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|