End of training
Browse files- README.md +14 -2
- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
README.md
CHANGED
@@ -1,11 +1,23 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
4 |
metrics:
|
5 |
- accuracy
|
6 |
model-index:
|
7 |
- name: smolm-autoreg-bpe-counterfactual-babylm-indef_articles_with_pl_nouns_removal-1e-3
|
8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -13,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# smolm-autoreg-bpe-counterfactual-babylm-indef_articles_with_pl_nouns_removal-1e-3
|
15 |
|
16 |
-
This model was trained from scratch on
|
17 |
It achieves the following results on the evaluation set:
|
18 |
- Loss: 3.4176
|
19 |
- Accuracy: 0.4125
|
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
model-index:
|
9 |
- name: smolm-autoreg-bpe-counterfactual-babylm-indef_articles_with_pl_nouns_removal-1e-3
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Causal Language Modeling
|
13 |
+
type: text-generation
|
14 |
+
dataset:
|
15 |
+
name: kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal
|
16 |
+
type: kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal
|
17 |
+
metrics:
|
18 |
+
- name: Accuracy
|
19 |
+
type: accuracy
|
20 |
+
value: 0.41252109443859236
|
21 |
---
|
22 |
|
23 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
25 |
|
26 |
# smolm-autoreg-bpe-counterfactual-babylm-indef_articles_with_pl_nouns_removal-1e-3
|
27 |
|
28 |
+
This model was trained from scratch on the kanishka/counterfactual_babylm_aann_indef_articles_with_pl_nouns_removal dataset.
|
29 |
It achieves the following results on the evaluation set:
|
30 |
- Loss: 3.4176
|
31 |
- Accuracy: 0.4125
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.41252109443859236,
|
4 |
+
"eval_loss": 3.417576313018799,
|
5 |
+
"eval_runtime": 147.5666,
|
6 |
+
"eval_samples": 57920,
|
7 |
+
"eval_samples_per_second": 392.501,
|
8 |
+
"eval_steps_per_second": 6.133,
|
9 |
+
"perplexity": 30.495414041670983,
|
10 |
+
"train_loss": 2.994195082282441,
|
11 |
+
"train_runtime": 55239.7487,
|
12 |
+
"train_samples": 595216,
|
13 |
+
"train_samples_per_second": 215.503,
|
14 |
+
"train_steps_per_second": 13.469
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.41252109443859236,
|
4 |
+
"eval_loss": 3.417576313018799,
|
5 |
+
"eval_runtime": 147.5666,
|
6 |
+
"eval_samples": 57920,
|
7 |
+
"eval_samples_per_second": 392.501,
|
8 |
+
"eval_steps_per_second": 6.133,
|
9 |
+
"perplexity": 30.495414041670983
|
10 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"train_loss": 2.994195082282441,
|
4 |
+
"train_runtime": 55239.7487,
|
5 |
+
"train_samples": 595216,
|
6 |
+
"train_samples_per_second": 215.503,
|
7 |
+
"train_steps_per_second": 13.469
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|