End of training
Browse files- README.md +16 -4
- all_results.json +16 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1733601151.ki-g0009.1454966.1 +3 -0
- train_results.json +9 -0
- trainer_state.json +0 -0
README.md
CHANGED
|
@@ -4,11 +4,23 @@ license: apache-2.0
|
|
| 4 |
base_model: distilbert-base-uncased
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: bert_base_train_book
|
| 11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,10 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# bert_base_train_book
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 1.
|
| 22 |
-
- Accuracy: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 4 |
base_model: distilbert-base-uncased
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- gokulsrinivasagan/processed_book_corpus_cleaned
|
| 9 |
metrics:
|
| 10 |
- accuracy
|
| 11 |
model-index:
|
| 12 |
- name: bert_base_train_book
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Masked Language Modeling
|
| 16 |
+
type: fill-mask
|
| 17 |
+
dataset:
|
| 18 |
+
name: gokulsrinivasagan/processed_book_corpus_cleaned
|
| 19 |
+
type: gokulsrinivasagan/processed_book_corpus_cleaned
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Accuracy
|
| 22 |
+
type: accuracy
|
| 23 |
+
value: 0.7530519758192171
|
| 24 |
---
|
| 25 |
|
| 26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 28 |
|
| 29 |
# bert_base_train_book
|
| 30 |
|
| 31 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the gokulsrinivasagan/processed_book_corpus_cleaned dataset.
|
| 32 |
It achieves the following results on the evaluation set:
|
| 33 |
+
- Loss: 1.0775
|
| 34 |
+
- Accuracy: 0.7531
|
| 35 |
|
| 36 |
## Model description
|
| 37 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"eval_accuracy": 0.7530519758192171,
|
| 4 |
+
"eval_loss": 1.0775210857391357,
|
| 5 |
+
"eval_runtime": 182.4452,
|
| 6 |
+
"eval_samples": 120706,
|
| 7 |
+
"eval_samples_per_second": 661.601,
|
| 8 |
+
"eval_steps_per_second": 6.895,
|
| 9 |
+
"perplexity": 2.937388983012658,
|
| 10 |
+
"total_flos": 1.498518436978944e+19,
|
| 11 |
+
"train_loss": 2.334269580478457,
|
| 12 |
+
"train_runtime": 190366.3414,
|
| 13 |
+
"train_samples": 2277342,
|
| 14 |
+
"train_samples_per_second": 299.074,
|
| 15 |
+
"train_steps_per_second": 3.115
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"eval_accuracy": 0.7530519758192171,
|
| 4 |
+
"eval_loss": 1.0775210857391357,
|
| 5 |
+
"eval_runtime": 182.4452,
|
| 6 |
+
"eval_samples": 120706,
|
| 7 |
+
"eval_samples_per_second": 661.601,
|
| 8 |
+
"eval_steps_per_second": 6.895,
|
| 9 |
+
"perplexity": 2.937388983012658
|
| 10 |
+
}
|
logs/events.out.tfevents.1733601151.ki-g0009.1454966.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:305037dd027e16484eac517b6aa2c1abcf26ebfefbafce50ad2676b698087ca3
|
| 3 |
+
size 417
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"total_flos": 1.498518436978944e+19,
|
| 4 |
+
"train_loss": 2.334269580478457,
|
| 5 |
+
"train_runtime": 190366.3414,
|
| 6 |
+
"train_samples": 2277342,
|
| 7 |
+
"train_samples_per_second": 299.074,
|
| 8 |
+
"train_steps_per_second": 3.115
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|