End of training
Browse files
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-pipps-random_removal-seed_211-1e-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-pipps-random_removal-seed_211-1e-3
|
15 |
|
16 |
-
This model was trained from scratch on
|
17 |
It achieves the following results on the evaluation set:
|
18 |
- Loss: 3.4120
|
19 |
- Accuracy: 0.4099
|
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- kanishka/counterfactual-babylm-pipps-random_removal
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
model-index:
|
9 |
- name: smolm-autoreg-bpe-counterfactual-babylm-pipps-random_removal-seed_211-1e-3
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Causal Language Modeling
|
13 |
+
type: text-generation
|
14 |
+
dataset:
|
15 |
+
name: kanishka/counterfactual-babylm-pipps-random_removal
|
16 |
+
type: kanishka/counterfactual-babylm-pipps-random_removal
|
17 |
+
metrics:
|
18 |
+
- name: Accuracy
|
19 |
+
type: accuracy
|
20 |
+
value: 0.40988659662430754
|
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-pipps-random_removal-seed_211-1e-3
|
27 |
|
28 |
+
This model was trained from scratch on the kanishka/counterfactual-babylm-pipps-random_removal dataset.
|
29 |
It achieves the following results on the evaluation set:
|
30 |
- Loss: 3.4120
|
31 |
- Accuracy: 0.4099
|
all_results.json
CHANGED
@@ -1,5 +1,12 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"train_loss": 3.030422134530729,
|
4 |
"train_runtime": 80926.4318,
|
5 |
"train_samples": 594939,
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.40988659662430754,
|
4 |
+
"eval_loss": 3.4119651317596436,
|
5 |
+
"eval_runtime": 155.2726,
|
6 |
+
"eval_samples": 57919,
|
7 |
+
"eval_samples_per_second": 373.015,
|
8 |
+
"eval_steps_per_second": 5.828,
|
9 |
+
"perplexity": 30.324777928701113,
|
10 |
"train_loss": 3.030422134530729,
|
11 |
"train_runtime": 80926.4318,
|
12 |
"train_samples": 594939,
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.40988659662430754,
|
4 |
+
"eval_loss": 3.4119651317596436,
|
5 |
+
"eval_runtime": 155.2726,
|
6 |
+
"eval_samples": 57919,
|
7 |
+
"eval_samples_per_second": 373.015,
|
8 |
+
"eval_steps_per_second": 5.828,
|
9 |
+
"perplexity": 30.324777928701113
|
10 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 391376736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1058b70cf082e7f824f2d844164b70b137bd58d41d330f2d17357c9901276236
|
3 |
size 391376736
|
runs/Feb18_17-40-04_phyl-ling-p01.la.utexas.edu/events.out.tfevents.1708380750.phyl-ling-p01.la.utexas.edu.4114048.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c87054010ca6ee0b58970cd1c47b37f9ddd12d2b2fa08db528047175dd33d06
|
3 |
+
size 417
|
special_tokens_map.json
CHANGED
@@ -1,30 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<pad>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<|endoftext|>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:784c6b58a52872de687c89103584b1d7734dd70dbbac0b46d0dff013ee7d2a3f
|
3 |
size 4984
|