shubhamgantayat
commited on
Commit
•
cf3eb72
1
Parent(s):
d16beef
End of training
Browse files
README.md
CHANGED
@@ -33,15 +33,15 @@ More information needed
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 0.0005
|
36 |
-
- train_batch_size:
|
37 |
-
- eval_batch_size:
|
38 |
- seed: 42
|
39 |
- gradient_accumulation_steps: 8
|
40 |
-
- total_train_batch_size:
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: cosine
|
43 |
- lr_scheduler_warmup_steps: 1000
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
### Framework versions
|
51 |
|
52 |
-
- Transformers 4.
|
53 |
- Pytorch 2.1.0+cu118
|
54 |
-
- Datasets 2.
|
55 |
-
- Tokenizers 0.
|
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 0.0005
|
36 |
+
- train_batch_size: 4
|
37 |
+
- eval_batch_size: 4
|
38 |
- seed: 42
|
39 |
- gradient_accumulation_steps: 8
|
40 |
+
- total_train_batch_size: 32
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: cosine
|
43 |
- lr_scheduler_warmup_steps: 1000
|
44 |
+
- num_epochs: 200
|
45 |
|
46 |
### Training results
|
47 |
|
|
|
49 |
|
50 |
### Framework versions
|
51 |
|
52 |
+
- Transformers 4.35.2
|
53 |
- Pytorch 2.1.0+cu118
|
54 |
+
- Datasets 2.15.0
|
55 |
+
- Tokenizers 0.15.0
|
config.json
CHANGED
@@ -35,7 +35,7 @@
|
|
35 |
}
|
36 |
},
|
37 |
"torch_dtype": "float32",
|
38 |
-
"transformers_version": "4.
|
39 |
"use_cache": true,
|
40 |
"vocab_size": 50257
|
41 |
}
|
|
|
35 |
}
|
36 |
},
|
37 |
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.35.2",
|
39 |
"use_cache": true,
|
40 |
"vocab_size": 50257
|
41 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.35.2"
|
6 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61c56a0d3a30c572301c772101743211590cb116ec861f3807757b8d46a01473
|
3 |
+
size 1419322880
|
runs/Nov21_05-14-36_a6bc864b532e/events.out.tfevents.1700543681.a6bc864b532e.7575.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b49e1c60285e9b16f57144b6570994f4a6cb193306245602c8753d7b9d08894c
|
3 |
+
size 4184
|
runs/Nov21_05-16-52_a6bc864b532e/events.out.tfevents.1700543819.a6bc864b532e.8264.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:349b646c198c46fabdc5874050c8afbdc55a71a66a0db11c67893e6ef6f312f5
|
3 |
+
size 4871
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d10d3a5851a2aab0bbaee0dd921c94ef501c50d21226274d33a6970462c3dc6
|
3 |
+
size 4600
|