Training in progress, step 27
Browse files- .gitattributes +1 -0
- README.md +58 -0
- adapter_config.json +61 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +49 -0
- runs/Jun27_14-53-24_a7733bc8af01/events.out.tfevents.1751036108.a7733bc8af01.12996.0 +3 -0
- runs/Jun27_14-53-24_a7733bc8af01/events.out.tfevents.1751036139.a7733bc8af01.12996.1 +3 -0
- runs/Jun27_14-56-29_a7733bc8af01/events.out.tfevents.1751036194.a7733bc8af01.12996.2 +3 -0
- runs/Jun27_14-57-02_a7733bc8af01/events.out.tfevents.1751036226.a7733bc8af01.12996.3 +3 -0
- runs/Jun27_14-57-02_a7733bc8af01/events.out.tfevents.1751036322.a7733bc8af01.12996.4 +3 -0
- runs/Jun27_14-59-49_a7733bc8af01/events.out.tfevents.1751036395.a7733bc8af01.12996.5 +3 -0
- runs/Jun27_15-02-01_a7733bc8af01/events.out.tfevents.1751036524.a7733bc8af01.12996.6 +3 -0
- runs/Jun27_15-03-33_a7733bc8af01/events.out.tfevents.1751036895.a7733bc8af01.12996.7 +3 -0
- runs/Jun27_15-11-36_a7733bc8af01/events.out.tfevents.1751037102.a7733bc8af01.12996.8 +3 -0
- runs/Jun27_15-11-49_a7733bc8af01/events.out.tfevents.1751037111.a7733bc8af01.12996.9 +3 -0
- runs/Jun27_15-18-58_a7733bc8af01/events.out.tfevents.1751037550.a7733bc8af01.12996.10 +3 -0
- runs/Jun27_15-41-51_a7733bc8af01/events.out.tfevents.1751038921.a7733bc8af01.12996.11 +3 -0
- runs/Jun27_15-49-43_a7733bc8af01/events.out.tfevents.1751039414.a7733bc8af01.12996.12 +3 -0
- runs/Jun27_16-00-11_a7733bc8af01/events.out.tfevents.1751040018.a7733bc8af01.12996.13 +3 -0
- runs/Jun27_16-00-11_a7733bc8af01/events.out.tfevents.1751040072.a7733bc8af01.12996.14 +3 -0
- runs/Jun27_16-17-50_a7733bc8af01/events.out.tfevents.1751041077.a7733bc8af01.12996.15 +3 -0
- runs/Jun27_16-27-25_a7733bc8af01/events.out.tfevents.1751041656.a7733bc8af01.12996.16 +3 -0
- special_tokens_map.json +36 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: google/gemma-3n-E2B-it
|
3 |
+
library_name: transformers
|
4 |
+
model_name: gemma-3n-finevideo
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
- sft
|
8 |
+
- trl
|
9 |
+
licence: license
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Card for gemma-3n-finevideo
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [google/gemma-3n-E2B-it](https://huggingface.co/google/gemma-3n-E2B-it).
|
15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
16 |
+
|
17 |
+
## Quick start
|
18 |
+
|
19 |
+
```python
|
20 |
+
from transformers import pipeline
|
21 |
+
|
22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
23 |
+
generator = pipeline("text-generation", model="merve/gemma-3n-finevideo", device="cuda")
|
24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
25 |
+
print(output["generated_text"])
|
26 |
+
```
|
27 |
+
|
28 |
+
## Training procedure
|
29 |
+
|
30 |
+
|
31 |
+
|
32 |
+
|
33 |
+
This model was trained with SFT.
|
34 |
+
|
35 |
+
### Framework versions
|
36 |
+
|
37 |
+
- TRL: 0.19.0
|
38 |
+
- Transformers: 4.53.0
|
39 |
+
- Pytorch: 2.6.0+cu124
|
40 |
+
- Datasets: 3.6.0
|
41 |
+
- Tokenizers: 0.21.1
|
42 |
+
|
43 |
+
## Citations
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
Cite TRL as:
|
48 |
+
|
49 |
+
```bibtex
|
50 |
+
@misc{vonwerra2022trl,
|
51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
53 |
+
year = 2020,
|
54 |
+
journal = {GitHub repository},
|
55 |
+
publisher = {GitHub},
|
56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
57 |
+
}
|
58 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-3n-E2B-it",
|
5 |
+
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 32,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.05,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"r": 16,
|
24 |
+
"rank_pattern": {},
|
25 |
+
"revision": null,
|
26 |
+
"target_modules": [
|
27 |
+
"linear_start",
|
28 |
+
"ffw_layer_2",
|
29 |
+
"altup_projections.1",
|
30 |
+
"post",
|
31 |
+
"v_proj",
|
32 |
+
"o_proj",
|
33 |
+
"modality_router",
|
34 |
+
"per_layer_projection",
|
35 |
+
"per_layer_input_gate",
|
36 |
+
"linear_left",
|
37 |
+
"q_proj",
|
38 |
+
"linear_end",
|
39 |
+
"down_proj",
|
40 |
+
"prediction_coefs",
|
41 |
+
"altup_unembed_projections.0",
|
42 |
+
"input_proj_linear",
|
43 |
+
"k_proj",
|
44 |
+
"linear_right",
|
45 |
+
"altup_projections.2",
|
46 |
+
"up_proj",
|
47 |
+
"gate_proj",
|
48 |
+
"embedding_projection",
|
49 |
+
"correction_coefs",
|
50 |
+
"altup_projections.0",
|
51 |
+
"pos_proj",
|
52 |
+
"per_layer_model_projection",
|
53 |
+
"ffw_layer_1",
|
54 |
+
"altup_unembed_projections.2",
|
55 |
+
"altup_unembed_projections.1"
|
56 |
+
],
|
57 |
+
"task_type": "CAUSAL_LM",
|
58 |
+
"trainable_token_indices": null,
|
59 |
+
"use_dora": false,
|
60 |
+
"use_rslora": false
|
61 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7edd90144d3df68ff24938748ba2b0fd3c3e5bdcab789ffcfa95240c9c68c910
|
3 |
+
size 149802432
|
chat_template.jinja
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{{ bos_token }}
|
2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
3 |
+
{%- if messages[0]['content'] is string -%}
|
4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
5 |
+
|
6 |
+
' -%}
|
7 |
+
{%- else -%}
|
8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
9 |
+
|
10 |
+
' -%}
|
11 |
+
{%- endif -%}
|
12 |
+
{%- set loop_messages = messages[1:] -%}
|
13 |
+
{%- else -%}
|
14 |
+
{%- set first_user_prefix = "" -%}
|
15 |
+
{%- set loop_messages = messages -%}
|
16 |
+
{%- endif -%}
|
17 |
+
{%- for message in loop_messages -%}
|
18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
20 |
+
{%- endif -%}
|
21 |
+
{%- if (message['role'] == 'assistant') -%}
|
22 |
+
{%- set role = "model" -%}
|
23 |
+
{%- else -%}
|
24 |
+
{%- set role = message['role'] -%}
|
25 |
+
{%- endif -%}
|
26 |
+
{{ '<start_of_turn>' + role + '
|
27 |
+
' + (first_user_prefix if loop.first else "") }}
|
28 |
+
{%- if message['content'] is string -%}
|
29 |
+
{{ message['content'] | trim }}
|
30 |
+
{%- elif message['content'] is iterable -%}
|
31 |
+
{%- for item in message['content'] -%}
|
32 |
+
{%- if item['type'] == 'audio' -%}
|
33 |
+
{{ '<audio_soft_token>' }}
|
34 |
+
{%- elif item['type'] == 'image' -%}
|
35 |
+
{{ '<image_soft_token>' }}
|
36 |
+
{%- elif item['type'] == 'text' -%}
|
37 |
+
{{ item['text'] | trim }}
|
38 |
+
{%- endif -%}
|
39 |
+
{%- endfor -%}
|
40 |
+
{%- else -%}
|
41 |
+
{{ raise_exception("Invalid content type") }}
|
42 |
+
{%- endif -%}
|
43 |
+
{{ '<end_of_turn>
|
44 |
+
' }}
|
45 |
+
{%- endfor -%}
|
46 |
+
{%- if add_generation_prompt -%}
|
47 |
+
{{'<start_of_turn>model
|
48 |
+
'}}
|
49 |
+
{%- endif -%}
|
runs/Jun27_14-53-24_a7733bc8af01/events.out.tfevents.1751036108.a7733bc8af01.12996.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05994d4543ace4652e8388f994173478c170657277c762e6c3b43fa45af3e715
|
3 |
+
size 9249
|
runs/Jun27_14-53-24_a7733bc8af01/events.out.tfevents.1751036139.a7733bc8af01.12996.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:354d6c7cf35203d2101a254864ea9d909405a9526a0383a3b7d22c2af474bf2c
|
3 |
+
size 9249
|
runs/Jun27_14-56-29_a7733bc8af01/events.out.tfevents.1751036194.a7733bc8af01.12996.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:533c807e591b9938f56f51d97a8907db26e7203488df62e58d0e690aa0efdc53
|
3 |
+
size 9249
|
runs/Jun27_14-57-02_a7733bc8af01/events.out.tfevents.1751036226.a7733bc8af01.12996.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e603c9fe9ab85ab392e4877a0914729ff05180d3c84fd4dbc3529382e751883
|
3 |
+
size 9250
|
runs/Jun27_14-57-02_a7733bc8af01/events.out.tfevents.1751036322.a7733bc8af01.12996.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c9e141f66eed9ebc68ab505ac70778f6804960c6c3e3f6bb026da9522f5c903
|
3 |
+
size 18412
|
runs/Jun27_14-59-49_a7733bc8af01/events.out.tfevents.1751036395.a7733bc8af01.12996.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4627ab0b57516db4e298b364204ddd6e77b4c38992da3f301b7cacc94464674
|
3 |
+
size 9272
|
runs/Jun27_15-02-01_a7733bc8af01/events.out.tfevents.1751036524.a7733bc8af01.12996.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5b1f68aea39edcced7e9d01acf99ad2e77877cbcac68fc9c1d3a4c66de7ee07
|
3 |
+
size 9273
|
runs/Jun27_15-03-33_a7733bc8af01/events.out.tfevents.1751036895.a7733bc8af01.12996.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd2dd2ea00ab2b3f3b18314290cfe033931749b7df6f8c692769cbd0c9ae8c45
|
3 |
+
size 9273
|
runs/Jun27_15-11-36_a7733bc8af01/events.out.tfevents.1751037102.a7733bc8af01.12996.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b660684c053b6f1c055cec56daa5cfd0c15a28e04ec093b220ee31b45677e417
|
3 |
+
size 9272
|
runs/Jun27_15-11-49_a7733bc8af01/events.out.tfevents.1751037111.a7733bc8af01.12996.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5d7f5f67babb93846de50cb7bc998124c50dee38bec70c159db755418f3089b
|
3 |
+
size 9273
|
runs/Jun27_15-18-58_a7733bc8af01/events.out.tfevents.1751037550.a7733bc8af01.12996.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bee67f2fc70200453ced816e9fe5086967b7396ee09f44cf8da8fa182ee1b284
|
3 |
+
size 9273
|
runs/Jun27_15-41-51_a7733bc8af01/events.out.tfevents.1751038921.a7733bc8af01.12996.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:535ac00a5c1048eee304dba944088fc67ae1c82279df71ef6b174a6d7be27066
|
3 |
+
size 18458
|
runs/Jun27_15-49-43_a7733bc8af01/events.out.tfevents.1751039414.a7733bc8af01.12996.12
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcf0abc593ab8cf52f1e8291586fcb89287f3ecb2fc95f0364cbc76a5a31320b
|
3 |
+
size 9273
|
runs/Jun27_16-00-11_a7733bc8af01/events.out.tfevents.1751040018.a7733bc8af01.12996.13
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d80d2ee46792373cc4226d254454c4eed79b719500ca187b50821439d0eeaadf
|
3 |
+
size 9251
|
runs/Jun27_16-00-11_a7733bc8af01/events.out.tfevents.1751040072.a7733bc8af01.12996.14
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:289d0378b41033139314c842bea38e56360b811cec3758001335663d045fa90c
|
3 |
+
size 9251
|
runs/Jun27_16-17-50_a7733bc8af01/events.out.tfevents.1751041077.a7733bc8af01.12996.15
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69e0e8b1524acb77b0a68a5c5c2f79b2d87cb8072f586dc77e80cc23e34bb915
|
3 |
+
size 9273
|
runs/Jun27_16-27-25_a7733bc8af01/events.out.tfevents.1751041656.a7733bc8af01.12996.16
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00cf6b2e2e5b15d2a270450713c5cace8deab1c6c90ad7766be4736cb39578dd
|
3 |
+
size 11148
|
special_tokens_map.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio_token": "<audio_soft_token>",
|
3 |
+
"boa_token": "<start_of_audio>",
|
4 |
+
"boi_token": "<start_of_image>",
|
5 |
+
"bos_token": {
|
6 |
+
"content": "<bos>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eoa_token": "<end_of_audio>",
|
13 |
+
"eoi_token": "<end_of_image>",
|
14 |
+
"eos_token": {
|
15 |
+
"content": "<eos>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"image_token": "<image_soft_token>",
|
22 |
+
"pad_token": {
|
23 |
+
"content": "<pad>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"unk_token": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
}
|
36 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed504d44c6898db6d71f4abf77cf8e12a9ee3ac90bb1aec0e1edc012c4251b23
|
3 |
+
size 33442708
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea5f0cc48abfbfc04d14562270a32e02149a3e7035f368cc5a462786f4a59961
|
3 |
+
size 4696020
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19ce49882531a204abe2db6d6d72e853d245395005a716b5499c2953a201b438
|
3 |
+
size 5752
|