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-64k
+  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-64k
+
+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: 5.5381
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9333        | 1.0   | 406  | 2.4449          |
+| 0.8399        | 2.0   | 812  | 2.3513          |
+| 0.7898        | 3.0   | 1218 | 2.4311          |
+| 0.7295        | 4.0   | 1624 | 2.5969          |
+| 0.6377        | 5.0   | 2030 | 2.8601          |
+| 0.5891        | 6.0   | 2436 | 3.1033          |
+| 0.5095        | 7.0   | 2842 | 3.5735          |
+| 0.4514        | 8.0   | 3248 | 3.9319          |
+| 0.3872        | 9.0   | 3654 | 4.4386          |
+| 0.3371        | 10.0  | 4060 | 4.8561          |
+| 0.2993        | 11.0  | 4466 | 5.2020          |
+| 0.29          | 12.0  | 4872 | 5.4070          |
+| 0.2802        | 13.0  | 5278 | 5.5084          |
+| 0.2693        | 14.0  | 5684 | 5.5384          |
+| 0.2715        | 15.0  | 6090 | 5.5381          |
+
+
+### 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 sha256:36387e4c6c73369de294f76e79b31616f6d103c61b1abc51db200ee7b04c07b8
+oid sha256:530dc4e1db6c3022c545725157c6e5d2e7ecf9b878bff1f8f1217168bfc5439e
 size 50056096

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 15.0,
+    "total_flos": 4.655418812370256e+18,
+    "train_loss": 0.9284773617542436,
+    "train_runtime": 39545.4398,
+    "train_samples": 59995,
+    "train_samples_per_second": 2.463,
+    "train_steps_per_second": 0.154
+}

runs/Jun08_20-45-26_user-WS-C621E-SAGE-Series/events.out.tfevents.1717847247.user-WS-C621E-SAGE-Series.15766.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d1197a13f7fbc6d79dbf7e900fffbef3fbbe60275039e3b524cbc09b02a3a44
-size 262533
+oid sha256:f5edfe583774eebf4e76106848adfefc227b7c5f5041131b6eec910b45d38264
+size 266956

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 15.0,
+    "total_flos": 4.655418812370256e+18,
+    "train_loss": 0.9284773617542436,
+    "train_runtime": 39545.4398,
+    "train_samples": 59995,
+    "train_samples_per_second": 2.463,
+    "train_steps_per_second": 0.154
+}