october-sd
commited on
Commit
•
c6a940b
1
Parent(s):
4fb1ce0
Training complete
Browse files
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/mt5-small
|
4 |
+
tags:
|
5 |
+
- summarization
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: mt5-small-finetuned-mr-sum
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# mt5-small-finetuned-mr-sum
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- eval_loss: 2.0995
|
20 |
+
- eval_runtime: 48.6922
|
21 |
+
- eval_samples_per_second: 50.994
|
22 |
+
- eval_steps_per_second: 6.387
|
23 |
+
- epoch: 2.08
|
24 |
+
- step: 3757
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5.6e-05
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 4
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- Transformers 4.38.2
|
54 |
+
- Pytorch 2.1.0+cu121
|
55 |
+
- Datasets 2.18.0
|
56 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.38.2"
|
7 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1200729512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6978725067a40882b2132eddc9d2e2ffa1710c19a3a5e283ab8d385850e258c2
|
3 |
size 1200729512
|
runs/Mar02_03-02-45_7d726f056c04/events.out.tfevents.1709348583.7d726f056c04.2408.0
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 sha256:821a2c1811c5799c732551f269d46e5f2526e4e8d0ca9668c26865ee03e67436
|
3 |
+
size 6111
|