Model save

README.md

@@ -0,0 +1,78 @@
+---
+license: gemma
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: google/gemma-7b
+datasets:
+- generator
+model-index:
+- name: gemma7-closedqa-gpt4o-100k
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# gemma7-closedqa-gpt4o-100k
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.0765
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 24
+- total_eval_batch_size: 12
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8445        | 0.9991 | 574  | 2.1107          |
+| 0.784         | 2.0    | 1149 | 2.2301          |
+| 0.6545        | 2.9991 | 1723 | 2.4329          |
+| 0.5693        | 4.0    | 2298 | 2.7030          |
+| 0.4555        | 4.9991 | 2872 | 3.1445          |
+| 0.3504        | 6.0    | 3447 | 3.7197          |
+| 0.2672        | 6.9991 | 4021 | 4.3078          |
+| 0.2167        | 8.0    | 4596 | 4.8456          |
+| 0.2037        | 8.9991 | 5170 | 5.0561          |
+| 0.1899        | 9.9913 | 5740 | 5.0765          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c2770b33db2337c843e11fed3e521191a61166feffc91c116f32e2fb67e37b
+oid sha256:cb356befcd2adf49deec3756c5fe78411e8c9f7d045fb9f608a83728e943c102
 size 200068904

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.991296779808529,
+    "total_flos": 6.645284010274587e+18,
+    "train_loss": 0.6571785643956387,
+    "train_runtime": 32584.0572,
+    "train_samples": 92940,
+    "train_samples_per_second": 4.229,
+    "train_steps_per_second": 0.176
+}

runs/Jun12_15-21-32_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718173315.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.50455.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0378eefe68b85f0259fe71a14075ce12fc0e865ee4087391213d20171c4686
-size 248684
+oid sha256:e708e64a239470e2885943649c07ad059073b96e143d62c187b5cb1a65f38b57
+size 250997

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.991296779808529,
+    "total_flos": 6.645284010274587e+18,
+    "train_loss": 0.6571785643956387,
+    "train_runtime": 32584.0572,
+    "train_samples": 92940,
+    "train_samples_per_second": 4.229,
+    "train_steps_per_second": 0.176
+}