End of training
Browse files- README.md +7 -4
- config.json +1 -1
- pytorch_model.bin +2 -2
- tokenizer.json +1 -6
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -55,7 +55,10 @@ The following hyperparameters were used during training:
|
|
| 55 |
- learning_rate: 5e-05
|
| 56 |
- train_batch_size: 32
|
| 57 |
- eval_batch_size: 64
|
| 58 |
-
- seed:
|
|
|
|
|
|
|
|
|
|
| 59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
- lr_scheduler_type: linear
|
| 61 |
- lr_scheduler_warmup_steps: 20
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.3076923076923077
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.7773
|
| 36 |
+
- Accuracy: 0.3077
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 55 |
- learning_rate: 5e-05
|
| 56 |
- train_batch_size: 32
|
| 57 |
- eval_batch_size: 64
|
| 58 |
+
- seed: 1
|
| 59 |
+
- distributed_type: multi-GPU
|
| 60 |
+
- gradient_accumulation_steps: 2
|
| 61 |
+
- total_train_batch_size: 64
|
| 62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 63 |
- lr_scheduler_type: linear
|
| 64 |
- lr_scheduler_warmup_steps: 20
|
config.json
CHANGED
|
@@ -54,7 +54,7 @@
|
|
| 54 |
"prefix": "translate English to Romanian: "
|
| 55 |
}
|
| 56 |
},
|
| 57 |
-
"torch_dtype": "
|
| 58 |
"transformers_version": "4.34.1",
|
| 59 |
"use_cache": true,
|
| 60 |
"vocab_size": 32128
|
|
|
|
| 54 |
"prefix": "translate English to Romanian: "
|
| 55 |
}
|
| 56 |
},
|
| 57 |
+
"torch_dtype": "bfloat16",
|
| 58 |
"transformers_version": "4.34.1",
|
| 59 |
"use_cache": true,
|
| 60 |
"vocab_size": 32128
|
pytorch_model.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:cdeb500ba7be5f70311bd2630980f095edeb31b24a7cb27f8c3e72ec55bfe7ac
|
| 3 |
+
size 447089825
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
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:dcab6ddc1b87a49965f15aeb6c4fcec9087a213cafb40893d389a8084b322844
|
| 3 |
+
size 5819
|