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-claude3sonnet-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-claude3sonnet-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: 2.5206
+
+## 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: 3
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 48
+- total_eval_batch_size: 24
+- 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 |
+|:-------------:|:-------:|:-----:|:---------------:|
+| 1.0494        | 0.9994  | 808   | 2.4662          |
+| 0.9661        | 2.0     | 1617  | 2.4507          |
+| 0.9526        | 2.9994  | 2425  | 2.4659          |
+| 0.925         | 4.0     | 3234  | 2.4750          |
+| 0.9099        | 4.9994  | 4042  | 2.4839          |
+| 0.8939        | 6.0     | 4851  | 2.4936          |
+| 0.8795        | 6.9994  | 5659  | 2.5032          |
+| 0.8694        | 8.0     | 6468  | 2.5068          |
+| 0.8608        | 8.9994  | 7276  | 2.5143          |
+| 0.8421        | 10.0    | 8085  | 2.5187          |
+| 0.8555        | 10.9994 | 8893  | 2.5196          |
+| 0.8442        | 12.0    | 9702  | 2.5193          |
+| 0.8621        | 12.9994 | 10510 | 2.5206          |
+| 0.8586        | 14.0    | 11319 | 2.5210          |
+| 0.8485        | 14.9907 | 12120 | 2.5206          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- 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:e25dd6a7c539bd5f47ec5c0538d304c7e8cb502138cdb10b6aa7f38042a33b77
+oid sha256:a9087fa1bb83829ae295ab3613a7241125ca8071426aea9e9d36caa432da8207
 size 19644912

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 14.990723562152134,
+    "total_flos": 7.118964864348848e+18,
+    "train_loss": 0.9255497357436139,
+    "train_runtime": 41659.6506,
+    "train_samples": 253979,
+    "train_samples_per_second": 13.97,
+    "train_steps_per_second": 0.291
+}

runs/Jun06_00-12-23_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717600439.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.943366.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d67e946bdcc644a717949c8a464ccaaaf89da937256619fdf4bd65f287aa27f6
-size 520001
+oid sha256:ff33c1562d567a0c8254886b85d673f799c7b3af0fa56e2455914811f9f34a16
+size 521470

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 14.990723562152134,
+    "total_flos": 7.118964864348848e+18,
+    "train_loss": 0.9255497357436139,
+    "train_runtime": 41659.6506,
+    "train_samples": 253979,
+    "train_samples_per_second": 13.97,
+    "train_steps_per_second": 0.291
+}