End of training
Browse files- README.md +15 -3
- all_results.json +16 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1733794275.ki-g0009.1814023.1 +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_100_v1_book
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -14,9 +26,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# bert_tiny_lda_100_v1_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: 4.
|
| 20 |
- Accuracy: 0.6766
|
| 21 |
|
| 22 |
## Model description
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- gokulsrinivasagan/processed_book_corpus-ld-100
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: bert_tiny_lda_100_v1_book
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Masked Language Modeling
|
| 14 |
+
type: fill-mask
|
| 15 |
+
dataset:
|
| 16 |
+
name: gokulsrinivasagan/processed_book_corpus-ld-100
|
| 17 |
+
type: gokulsrinivasagan/processed_book_corpus-ld-100
|
| 18 |
+
metrics:
|
| 19 |
+
- name: Accuracy
|
| 20 |
+
type: accuracy
|
| 21 |
+
value: 0.6765868602733887
|
| 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_100_v1_book
|
| 28 |
|
| 29 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the gokulsrinivasagan/processed_book_corpus-ld-100 dataset.
|
| 30 |
It achieves the following results on the evaluation set:
|
| 31 |
+
- Loss: 4.9524
|
| 32 |
- Accuracy: 0.6766
|
| 33 |
|
| 34 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"eval_accuracy": 0.6765868602733887,
|
| 4 |
+
"eval_loss": 4.952412128448486,
|
| 5 |
+
"eval_runtime": 130.2782,
|
| 6 |
+
"eval_samples": 120706,
|
| 7 |
+
"eval_samples_per_second": 926.525,
|
| 8 |
+
"eval_steps_per_second": 5.795,
|
| 9 |
+
"perplexity": 141.51590710222774,
|
| 10 |
+
"total_flos": 3.046251597339341e+18,
|
| 11 |
+
"train_loss": 5.746741898249789,
|
| 12 |
+
"train_runtime": 91431.3002,
|
| 13 |
+
"train_samples": 2277342,
|
| 14 |
+
"train_samples_per_second": 622.692,
|
| 15 |
+
"train_steps_per_second": 3.892
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"eval_accuracy": 0.6765868602733887,
|
| 4 |
+
"eval_loss": 4.952412128448486,
|
| 5 |
+
"eval_runtime": 130.2782,
|
| 6 |
+
"eval_samples": 120706,
|
| 7 |
+
"eval_samples_per_second": 926.525,
|
| 8 |
+
"eval_steps_per_second": 5.795,
|
| 9 |
+
"perplexity": 141.51590710222774
|
| 10 |
+
}
|
logs/events.out.tfevents.1733794275.ki-g0009.1814023.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5aa2dbb653fd785b2a87d7d8cd02978cae8a68ba3c9c6f2af618808e71006010
|
| 3 |
+
size 417
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"total_flos": 3.046251597339341e+18,
|
| 4 |
+
"train_loss": 5.746741898249789,
|
| 5 |
+
"train_runtime": 91431.3002,
|
| 6 |
+
"train_samples": 2277342,
|
| 7 |
+
"train_samples_per_second": 622.692,
|
| 8 |
+
"train_steps_per_second": 3.892
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|