Training in progress, epoch 1
Browse files- README.md +2 -4
- chat_template.jinja +2 -2
- config.json +1 -1
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- runs/Jul30_14-54-28_bobu-l40s-1.csail.mit.edu/events.out.tfevents.1753901697.bobu-l40s-1.csail.mit.edu.2620400.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,19 +1,17 @@
|
|
| 1 |
---
|
| 2 |
base_model: google/gemma-2-9b-it
|
| 3 |
-
datasets: Gabe-Thomp/gemma-bayesian-training
|
| 4 |
library_name: transformers
|
| 5 |
model_name: gemma-sft-bayesian-lr2.0e-06_assistant_only
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
- sft
|
| 9 |
- trl
|
| 10 |
-
- alignment-handbook
|
| 11 |
licence: license
|
| 12 |
---
|
| 13 |
|
| 14 |
# Model Card for gemma-sft-bayesian-lr2.0e-06_assistant_only
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it)
|
| 17 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 18 |
|
| 19 |
## Quick start
|
|
@@ -29,7 +27,7 @@ print(output["generated_text"])
|
|
| 29 |
|
| 30 |
## Training procedure
|
| 31 |
|
| 32 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/gabe-t-asher-nc-state-university/huggingface/runs/
|
| 33 |
|
| 34 |
|
| 35 |
This model was trained with SFT.
|
|
|
|
| 1 |
---
|
| 2 |
base_model: google/gemma-2-9b-it
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
model_name: gemma-sft-bayesian-lr2.0e-06_assistant_only
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
- sft
|
| 8 |
- trl
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
| 12 |
# Model Card for gemma-sft-bayesian-lr2.0e-06_assistant_only
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/gabe-t-asher-nc-state-university/huggingface/runs/05ouaw6w)
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
chat_template.jinja
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{% if message['role'] == 'assistant' %}{{ '<start_of_turn>' + role + '
|
| 2 |
-
' }}{% generation %}{{ message['content'] | trim }}{
|
| 3 |
-
' }}{% else %}{{ '<start_of_turn>' + role + '
|
| 4 |
' + message['content'] | trim + '<end_of_turn>
|
| 5 |
' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
|
| 6 |
'}}{% endif %}
|
|
|
|
| 1 |
{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{% if message['role'] == 'assistant' %}{{ '<start_of_turn>' + role + '
|
| 2 |
+
' }}{% generation %}{{ message['content'] | trim }}{{ '<end_of_turn>
|
| 3 |
+
' }}{% endgeneration %}{% else %}{{ '<start_of_turn>' + role + '
|
| 4 |
' + message['content'] | trim + '<end_of_turn>
|
| 5 |
' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
|
| 6 |
'}}{% endif %}
|
config.json
CHANGED
|
@@ -72,6 +72,6 @@
|
|
| 72 |
"sliding_window_size": 4096,
|
| 73 |
"torch_dtype": "bfloat16",
|
| 74 |
"transformers_version": "4.54.0",
|
| 75 |
-
"use_cache":
|
| 76 |
"vocab_size": 256000
|
| 77 |
}
|
|
|
|
| 72 |
"sliding_window_size": 4096,
|
| 73 |
"torch_dtype": "bfloat16",
|
| 74 |
"transformers_version": "4.54.0",
|
| 75 |
+
"use_cache": false,
|
| 76 |
"vocab_size": 256000
|
| 77 |
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4903351912
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0e9b6419922c365538b58a07f0e29b98bd2a79936bb7b7a66d5537e54e6a3b1
|
| 3 |
size 4903351912
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4947570872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:091ef4bf5b487a45974945141147a5666709fa6e19d9048586dc44a7ae01669e
|
| 3 |
size 4947570872
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4962221464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cf87443f82b686765d3e8d7e903f04ea19bb595d713974a89e4369d0173fe0d
|
| 3 |
size 4962221464
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3670322200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0185f460d528dfba56c4f6267bec912091e0beeac8afc1fe0ab58322ec03bcd8
|
| 3 |
size 3670322200
|
runs/Jul30_14-54-28_bobu-l40s-1.csail.mit.edu/events.out.tfevents.1753901697.bobu-l40s-1.csail.mit.edu.2620400.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f39e58af573542ebb208a598f1f97abab1aef5974bbbfa05beb441193d195a46
|
| 3 |
+
size 12151
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0120cad0893b90e3acdafd196974e61b7c85a1eb907777fe7541fda3c1ad83e
|
| 3 |
size 8056
|