DNA-LLM/synth_model
Browse files- README.md +3 -3
- model.safetensors +1 -1
- tokenizer.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -33,15 +33,15 @@ More information needed
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 5e-05
|
36 |
-
- train_batch_size:
|
37 |
- eval_batch_size: 8
|
38 |
- seed: 42
|
39 |
- gradient_accumulation_steps: 4
|
40 |
-
- total_train_batch_size:
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 1
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 112
|
37 |
- eval_batch_size: 8
|
38 |
- seed: 42
|
39 |
- gradient_accumulation_steps: 4
|
40 |
+
- total_train_batch_size: 448
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 1
|
44 |
+
- num_epochs: 1
|
45 |
|
46 |
### Training results
|
47 |
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6679704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27428baf4861a01210e8ed9ebbcd37a023143725cbd9a9c175708d45abd354d2
|
3 |
size 6679704
|
tokenizer.json
CHANGED
@@ -83,7 +83,7 @@
|
|
83 |
"ignore_merges": false,
|
84 |
"vocab": {
|
85 |
"<|beginoftext|>": 0,
|
86 |
-
"<|
|
87 |
"<|unknown|>": 2,
|
88 |
"a": 3,
|
89 |
"c": 4,
|
|
|
83 |
"ignore_merges": false,
|
84 |
"vocab": {
|
85 |
"<|beginoftext|>": 0,
|
86 |
+
"<|endoftext|>": 1,
|
87 |
"<|unknown|>": 2,
|
88 |
"a": 3,
|
89 |
"c": 4,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41bdf3c574c41652fe5a9dd08da7d3bc77e8a30a4ab0b1b1294e5702a77f0fb8
|
3 |
size 5176
|