Model save

README.md

@@ -0,0 +1,83 @@
+---
+license: gemma
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: google/gemma-7b
+datasets:
+- generator
+model-index:
+- name: gemma7b-summarize-gpt4o-128k
+  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. -->
+
+# gemma7b-summarize-gpt4o-128k
+
+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: 4.8761
+
+## 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: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 8
+- 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.8829        | 1.0   | 815   | 2.3801          |
+| 0.8134        | 2.0   | 1630  | 2.3417          |
+| 0.7643        | 3.0   | 2445  | 2.4263          |
+| 0.7211        | 4.0   | 3260  | 2.5582          |
+| 0.6713        | 5.0   | 4075  | 2.7395          |
+| 0.629         | 6.0   | 4890  | 3.0156          |
+| 0.5603        | 7.0   | 5705  | 3.2838          |
+| 0.5081        | 8.0   | 6520  | 3.5777          |
+| 0.4652        | 9.0   | 7335  | 4.0181          |
+| 0.434         | 10.0  | 8150  | 4.3232          |
+| 0.3977        | 11.0  | 8965  | 4.6346          |
+| 0.3878        | 12.0  | 9780  | 4.7574          |
+| 0.3766        | 13.0  | 10595 | 4.8475          |
+| 0.3665        | 14.0  | 11410 | 4.8724          |
+| 0.3658        | 15.0  | 12225 | 4.8761          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd5b91d7fc116fc9b2773bca1b0d7c00299ac07dfd4ca342d88f99857964d7c4
+oid sha256:6fd0002e4068a7964c6a73eaeea266c5304d62773841d94dd6bd2a4402d9ffa4
 size 50056096

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 15.0,
+    "total_flos": 9.345237271407755e+18,
+    "train_loss": 0.8459899323898347,
+    "train_runtime": 79658.5706,
+    "train_samples": 119991,
+    "train_samples_per_second": 2.455,
+    "train_steps_per_second": 0.153
+}

runs/Jun09_07-47-20_user-WS-C621E-SAGE-Series/events.out.tfevents.1717887044.user-WS-C621E-SAGE-Series.25578.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9843c6dd9d5e194449eeb515a2675408828178788f8c1f757714a84a294882
-size 524177
+oid sha256:219e4c5e4ed41d892450106273d3af4e86b5adb516f51d7c0e81cac5ab5f5965
+size 525857

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 15.0,
+    "total_flos": 9.345237271407755e+18,
+    "train_loss": 0.8459899323898347,
+    "train_runtime": 79658.5706,
+    "train_samples": 119991,
+    "train_samples_per_second": 2.455,
+    "train_steps_per_second": 0.153
+}