End of training
Browse files
README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: flan-t5-xl-codeparrot-xlcost-text-to-code
|
7 |
results: []
|
@@ -12,7 +14,18 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# flan-t5-xl-codeparrot-xlcost-text-to-code
|
14 |
|
15 |
-
This model is a fine-tuned version of [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Model description
|
18 |
|
@@ -33,9 +46,8 @@ More information needed
|
|
33 |
The following hyperparameters were used during training:
|
34 |
- learning_rate: 3e-05
|
35 |
- train_batch_size: 6
|
36 |
-
- eval_batch_size:
|
37 |
- seed: 42
|
38 |
-
- distributed_type: multi-GPU
|
39 |
- gradient_accumulation_steps: 24
|
40 |
- total_train_batch_size: 144
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- xlcost-text-to-code
|
7 |
model-index:
|
8 |
- name: flan-t5-xl-codeparrot-xlcost-text-to-code
|
9 |
results: []
|
|
|
14 |
|
15 |
# flan-t5-xl-codeparrot-xlcost-text-to-code
|
16 |
|
17 |
+
This model is a fine-tuned version of [epinnock/flan-t5-xl-codeparrot-xlcost-text-to-code](https://huggingface.co/epinnock/flan-t5-xl-codeparrot-xlcost-text-to-code) on the xlcost-text-to-code dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- eval_loss: 1.9876
|
20 |
+
- eval_rouge1: 43.1227
|
21 |
+
- eval_rouge2: 25.6539
|
22 |
+
- eval_rougeL: 41.8635
|
23 |
+
- eval_rougeLsum: 41.8883
|
24 |
+
- eval_gen_len: 9.0445
|
25 |
+
- eval_runtime: 1137.2469
|
26 |
+
- eval_samples_per_second: 7.17
|
27 |
+
- eval_steps_per_second: 0.897
|
28 |
+
- step: 0
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
46 |
The following hyperparameters were used during training:
|
47 |
- learning_rate: 3e-05
|
48 |
- train_batch_size: 6
|
49 |
+
- eval_batch_size: 8
|
50 |
- seed: 42
|
|
|
51 |
- gradient_accumulation_steps: 24
|
52 |
- total_train_batch_size: 144
|
53 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "epinnock/flan-t5-xl-codeparrot-xlcost-text-to-code",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
logs/events.out.tfevents.1675268686.n7boh0yjgo.2602.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e29ac3a3a4f50b91df243d0465d1e584914ccdf580bfd9c8cb777f11c3acf40
|
3 |
+
size 532
|
logs/events.out.tfevents.1675268748.n7boh0yjgo.2602.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7667a2c8aadb974adef23d78562ff714b6e742287eadb92e9a509a883458bf99
|
3 |
+
size 368
|
logs/events.out.tfevents.1675270112.n7boh0yjgo.2602.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11400ffbc8f9b2daaedd5c83126713694cab42fc9d01bf612a9e865c8c24ab42
|
3 |
+
size 488
|
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 250,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 250
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 0,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "<pad>"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -104,7 +104,7 @@
|
|
104 |
"eos_token": "</s>",
|
105 |
"extra_ids": 100,
|
106 |
"model_max_length": 512,
|
107 |
-
"name_or_path": "
|
108 |
"pad_token": "<pad>",
|
109 |
"sp_model_kwargs": {},
|
110 |
"special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
|
|
|
104 |
"eos_token": "</s>",
|
105 |
"extra_ids": 100,
|
106 |
"model_max_length": 512,
|
107 |
+
"name_or_path": "epinnock/flan-t5-xl-codeparrot-xlcost-text-to-code",
|
108 |
"pad_token": "<pad>",
|
109 |
"sp_model_kwargs": {},
|
110 |
"special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3695
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:491e1d6ab27ed0a02576cb652b859006579b223f27eab55bbd954b8f42e1efc3
|
3 |
size 3695
|