Model save
Browse files
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: gemma
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: google/gemma-2b
|
9 |
+
datasets:
|
10 |
+
- generator
|
11 |
+
model-index:
|
12 |
+
- name: gemma2b-summarize-gemini1_5flash-128k
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# gemma2b-summarize-gemini1_5flash-128k
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 2.5119
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.0002
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- distributed_type: multi-GPU
|
47 |
+
- num_devices: 4
|
48 |
+
- gradient_accumulation_steps: 2
|
49 |
+
- total_train_batch_size: 64
|
50 |
+
- total_eval_batch_size: 32
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: cosine
|
53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
54 |
+
- num_epochs: 15
|
55 |
+
|
56 |
+
### Training results
|
57 |
+
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
59 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
60 |
+
| 1.1289 | 1.0 | 208 | 2.5162 |
|
61 |
+
| 1.0298 | 2.0 | 416 | 2.4574 |
|
62 |
+
| 0.9905 | 3.0 | 624 | 2.4455 |
|
63 |
+
| 0.9668 | 4.0 | 832 | 2.4518 |
|
64 |
+
| 0.9507 | 5.0 | 1040 | 2.4578 |
|
65 |
+
| 0.9348 | 6.0 | 1248 | 2.4685 |
|
66 |
+
| 0.9236 | 7.0 | 1456 | 2.4789 |
|
67 |
+
| 0.9156 | 8.0 | 1664 | 2.4831 |
|
68 |
+
| 0.8987 | 9.0 | 1872 | 2.4963 |
|
69 |
+
| 0.9008 | 10.0 | 2080 | 2.5021 |
|
70 |
+
| 0.8976 | 11.0 | 2288 | 2.5050 |
|
71 |
+
| 0.8941 | 12.0 | 2496 | 2.5107 |
|
72 |
+
| 0.8878 | 13.0 | 2704 | 2.5123 |
|
73 |
+
| 0.8896 | 14.0 | 2912 | 2.5120 |
|
74 |
+
| 0.8797 | 15.0 | 3120 | 2.5119 |
|
75 |
+
|
76 |
+
|
77 |
+
### Framework versions
|
78 |
+
|
79 |
+
- PEFT 0.11.1
|
80 |
+
- Transformers 4.40.1
|
81 |
+
- Pytorch 2.2.0+cu121
|
82 |
+
- Datasets 2.19.2
|
83 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 19644912
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7b95deeb84e22467dfafc0746ad9bfc804aab1f995e55e3b26cf0c371a8c453
|
3 |
size 19644912
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"total_flos": 2.443473144564941e+18,
|
4 |
+
"train_loss": 0.9840393823690904,
|
5 |
+
"train_runtime": 10705.8296,
|
6 |
+
"train_samples": 126706,
|
7 |
+
"train_samples_per_second": 18.636,
|
8 |
+
"train_steps_per_second": 0.291
|
9 |
+
}
|
runs/Jun05_07-07-54_7bdd13775218/events.out.tfevents.1717571446.7bdd13775218.143388.0
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 sha256:15516be6c3aee7292a9eb871ba40ac9de82f14402722b1c7fe3362e0785bc7cb
|
3 |
+
size 141645
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"total_flos": 2.443473144564941e+18,
|
4 |
+
"train_loss": 0.9840393823690904,
|
5 |
+
"train_runtime": 10705.8296,
|
6 |
+
"train_samples": 126706,
|
7 |
+
"train_samples_per_second": 18.636,
|
8 |
+
"train_steps_per_second": 0.291
|
9 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|