test trainer.push_to_hu
Browse files- .gitattributes +1 -0
- README.md +110 -0
- adapter_config.json +42 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- chat_template.jinja +47 -0
- runs/Jan02_08-32-10_f408cf05027b/events.out.tfevents.1767342733.f408cf05027b.55.0 +3 -0
- special_tokens_map.json +33 -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 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: gemma
|
| 4 |
+
base_model: google/gemma-3-270m-it
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:google/gemma-3-270m-it
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: gemma3-peft-multiclass
|
| 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 |
+
# gemma3-peft-multiclass
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it) on an unknown dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 2.2109
|
| 24 |
+
- Accuracy: 0.42
|
| 25 |
+
- F1 Macro: 0.4174
|
| 26 |
+
- Precision Macro: 0.4194
|
| 27 |
+
- Recall Macro: 0.4193
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 5e-05
|
| 47 |
+
- train_batch_size: 8
|
| 48 |
+
- eval_batch_size: 8
|
| 49 |
+
- seed: 42
|
| 50 |
+
- gradient_accumulation_steps: 4
|
| 51 |
+
- total_train_batch_size: 32
|
| 52 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 53 |
+
- lr_scheduler_type: linear
|
| 54 |
+
- num_epochs: 3
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro |
|
| 59 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|
|
| 60 |
+
| 16.4047 | 0.0710 | 10 | 3.6137 | 0.352 | 0.3320 | 0.3414 | 0.3439 |
|
| 61 |
+
| 14.2141 | 0.1421 | 20 | 3.4200 | 0.356 | 0.3440 | 0.3466 | 0.3498 |
|
| 62 |
+
| 13.5641 | 0.2131 | 30 | 3.2952 | 0.354 | 0.3528 | 0.3651 | 0.3571 |
|
| 63 |
+
| 13.9938 | 0.2842 | 40 | 3.1136 | 0.35 | 0.3475 | 0.3472 | 0.3480 |
|
| 64 |
+
| 12.8039 | 0.3552 | 50 | 2.9981 | 0.352 | 0.3483 | 0.3495 | 0.3518 |
|
| 65 |
+
| 11.6164 | 0.4263 | 60 | 2.8842 | 0.36 | 0.3536 | 0.3576 | 0.3604 |
|
| 66 |
+
| 11.4141 | 0.4973 | 70 | 2.7804 | 0.382 | 0.3811 | 0.3892 | 0.3827 |
|
| 67 |
+
| 10.9391 | 0.5684 | 80 | 2.7409 | 0.382 | 0.3795 | 0.3942 | 0.3874 |
|
| 68 |
+
| 11.2023 | 0.6394 | 90 | 2.6599 | 0.368 | 0.3605 | 0.3686 | 0.3621 |
|
| 69 |
+
| 11.1117 | 0.7105 | 100 | 2.5964 | 0.382 | 0.3689 | 0.3782 | 0.3741 |
|
| 70 |
+
| 10.8336 | 0.7815 | 110 | 2.5515 | 0.382 | 0.3739 | 0.3737 | 0.3780 |
|
| 71 |
+
| 10.7383 | 0.8526 | 120 | 2.5144 | 0.378 | 0.3737 | 0.3775 | 0.3778 |
|
| 72 |
+
| 10.7766 | 0.9236 | 130 | 2.5157 | 0.376 | 0.3646 | 0.3887 | 0.3816 |
|
| 73 |
+
| 9.9812 | 0.9947 | 140 | 2.4519 | 0.388 | 0.3848 | 0.3864 | 0.3848 |
|
| 74 |
+
| 9.3602 | 1.0639 | 150 | 2.4290 | 0.39 | 0.3832 | 0.3870 | 0.3889 |
|
| 75 |
+
| 9.6672 | 1.1350 | 160 | 2.4054 | 0.398 | 0.3901 | 0.3951 | 0.3922 |
|
| 76 |
+
| 9.6578 | 1.2060 | 170 | 2.3940 | 0.404 | 0.4040 | 0.4068 | 0.4061 |
|
| 77 |
+
| 10.1414 | 1.2771 | 180 | 2.4032 | 0.388 | 0.3807 | 0.4050 | 0.3947 |
|
| 78 |
+
| 9.7828 | 1.3481 | 190 | 2.3542 | 0.4 | 0.3963 | 0.3984 | 0.3969 |
|
| 79 |
+
| 9.8086 | 1.4192 | 200 | 2.3286 | 0.406 | 0.4018 | 0.4031 | 0.4027 |
|
| 80 |
+
| 9.1289 | 1.4902 | 210 | 2.3212 | 0.39 | 0.3819 | 0.3964 | 0.3933 |
|
| 81 |
+
| 9.5641 | 1.5613 | 220 | 2.3019 | 0.414 | 0.4137 | 0.4157 | 0.4171 |
|
| 82 |
+
| 9.6461 | 1.6323 | 230 | 2.2907 | 0.412 | 0.4055 | 0.4088 | 0.4080 |
|
| 83 |
+
| 9.1906 | 1.7034 | 240 | 2.2955 | 0.422 | 0.4008 | 0.4265 | 0.4151 |
|
| 84 |
+
| 9.0484 | 1.7744 | 250 | 2.2959 | 0.406 | 0.4017 | 0.4147 | 0.4101 |
|
| 85 |
+
| 9.2789 | 1.8455 | 260 | 2.2869 | 0.392 | 0.3850 | 0.4055 | 0.3972 |
|
| 86 |
+
| 9.3695 | 1.9165 | 270 | 2.2800 | 0.394 | 0.3898 | 0.4064 | 0.4001 |
|
| 87 |
+
| 9.1937 | 1.9876 | 280 | 2.2526 | 0.414 | 0.4118 | 0.4137 | 0.4130 |
|
| 88 |
+
| 8.7906 | 2.0568 | 290 | 2.2432 | 0.422 | 0.4037 | 0.4311 | 0.4120 |
|
| 89 |
+
| 9.143 | 2.1279 | 300 | 2.2473 | 0.418 | 0.3911 | 0.4353 | 0.4057 |
|
| 90 |
+
| 9.0289 | 2.1989 | 310 | 2.2312 | 0.404 | 0.3995 | 0.4058 | 0.4032 |
|
| 91 |
+
| 8.8203 | 2.2700 | 320 | 2.2432 | 0.402 | 0.3979 | 0.4116 | 0.4062 |
|
| 92 |
+
| 9.082 | 2.3410 | 330 | 2.2344 | 0.416 | 0.4145 | 0.4229 | 0.4206 |
|
| 93 |
+
| 9.0086 | 2.4121 | 340 | 2.2278 | 0.418 | 0.4169 | 0.4236 | 0.4204 |
|
| 94 |
+
| 8.7383 | 2.4831 | 350 | 2.2259 | 0.408 | 0.3991 | 0.4129 | 0.4085 |
|
| 95 |
+
| 8.668 | 2.5542 | 360 | 2.2204 | 0.398 | 0.3902 | 0.3975 | 0.3971 |
|
| 96 |
+
| 9.1867 | 2.6252 | 370 | 2.2122 | 0.412 | 0.4063 | 0.4102 | 0.4078 |
|
| 97 |
+
| 8.8688 | 2.6963 | 380 | 2.2088 | 0.432 | 0.4235 | 0.4312 | 0.4259 |
|
| 98 |
+
| 8.85 | 2.7673 | 390 | 2.2119 | 0.432 | 0.4255 | 0.4327 | 0.4270 |
|
| 99 |
+
| 9.3047 | 2.8384 | 400 | 2.2091 | 0.432 | 0.4264 | 0.4295 | 0.4278 |
|
| 100 |
+
| 9.1258 | 2.9094 | 410 | 2.2139 | 0.428 | 0.4250 | 0.4273 | 0.4264 |
|
| 101 |
+
| 8.825 | 2.9805 | 420 | 2.2109 | 0.42 | 0.4174 | 0.4194 | 0.4193 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- PEFT 0.17.1
|
| 107 |
+
- Transformers 4.57.1
|
| 108 |
+
- Pytorch 2.8.0+cu126
|
| 109 |
+
- Datasets 4.4.1
|
| 110 |
+
- Tokenizers 0.22.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-3-270m-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": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": [
|
| 22 |
+
"classifier",
|
| 23 |
+
"score"
|
| 24 |
+
],
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"qalora_group_size": 16,
|
| 27 |
+
"r": 8,
|
| 28 |
+
"rank_pattern": {},
|
| 29 |
+
"revision": null,
|
| 30 |
+
"target_modules": [
|
| 31 |
+
"q_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
+
"k_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": null,
|
| 37 |
+
"task_type": "SEQ_CLS",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5cda6d01cf8bf08344dff9456b654b813d37b950b9c33866c820bc3c44fbfe8
|
| 3 |
+
size 2971808
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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'] == 'image' -%}
|
| 33 |
+
{{ '<start_of_image>' }}
|
| 34 |
+
{%- elif item['type'] == 'text' -%}
|
| 35 |
+
{{ item['text'] | trim }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
{%- else -%}
|
| 39 |
+
{{ raise_exception("Invalid content type") }}
|
| 40 |
+
{%- endif -%}
|
| 41 |
+
{{ '<end_of_turn>
|
| 42 |
+
' }}
|
| 43 |
+
{%- endfor -%}
|
| 44 |
+
{%- if add_generation_prompt -%}
|
| 45 |
+
{{'<start_of_turn>model
|
| 46 |
+
'}}
|
| 47 |
+
{%- endif -%}
|
runs/Jan02_08-32-10_f408cf05027b/events.out.tfevents.1767342733.f408cf05027b.55.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f0f6bcfd0203bc58615260e886bba6374e2af70217fb22db60c8e2f08deabae
|
| 3 |
+
size 35542
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"eoi_token": "<end_of_image>",
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"content": "<eos>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"image_token": "<image_soft_token>",
|
| 19 |
+
"pad_token": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:091e3cf7f0e56c10d7383f000a34ef2824e95368e43def66837540b0550b6f83
|
| 3 |
+
size 33384832
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
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 sha256:7a715c4a6c45939b23622a35a1364b5119601f3b9edce9b31bd652ac302ce4df
|
| 3 |
+
size 5841
|