Model save

README.md

@@ -0,0 +1,83 @@
+---
+license: gemma
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: google/gemma-2b
+datasets:
+- generator
+model-index:
+- name: gemma2b-summarize-gemini1_5flash-256k
+  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. -->
+
+# gemma2b-summarize-gemini1_5flash-256k
+
+This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5038
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 1.0614        | 0.9988  | 414  | 2.4760          |
+| 1.0004        | 2.0     | 829  | 2.4481          |
+| 0.9586        | 2.9988  | 1243 | 2.4426          |
+| 0.9412        | 4.0     | 1658 | 2.4496          |
+| 0.9325        | 4.9988  | 2072 | 2.4600          |
+| 0.9129        | 6.0     | 2487 | 2.4629          |
+| 0.8995        | 6.9988  | 2901 | 2.4703          |
+| 0.8999        | 8.0     | 3316 | 2.4830          |
+| 0.8762        | 8.9988  | 3730 | 2.4934          |
+| 0.8821        | 10.0    | 4145 | 2.4974          |
+| 0.8697        | 10.9988 | 4559 | 2.5013          |
+| 0.8729        | 12.0    | 4974 | 2.5031          |
+| 0.8779        | 12.9988 | 5388 | 2.5023          |
+| 0.8743        | 14.0    | 5803 | 2.5033          |
+| 0.8746        | 14.9819 | 6210 | 2.5038          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.40.1
+- Pytorch 2.2.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:633b70d386a7850b0a336a0cb5c965246328188fe945f7db077d866aea849071
+oid sha256:e024dd42370745139d905182e9d9e06c7c9db5e0335dea5b6af4f1da1146f93f
 size 19644912

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 14.981905910735826,
+    "total_flos": 4.863451355047526e+18,
+    "train_loss": 0.9534509487582098,
+    "train_runtime": 21285.3674,
+    "train_samples": 253412,
+    "train_samples_per_second": 18.683,
+    "train_steps_per_second": 0.292
+}

runs/Jun05_10-10-03_7bdd13775218/events.out.tfevents.1717582519.7bdd13775218.245062.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c1d1b72010f4646a9900cde7bb17346fd8a392742a9c5b0b0090d9c3c96eb24
-size 270996
+oid sha256:f417fcbd1432ffeb25fb00c81a4579cefa4fa686a342bb2ada1d5f5e889cece0
+size 272043

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 14.981905910735826,
+    "total_flos": 4.863451355047526e+18,
+    "train_loss": 0.9534509487582098,
+    "train_runtime": 21285.3674,
+    "train_samples": 253412,
+    "train_samples_per_second": 18.683,
+    "train_steps_per_second": 0.292
+}