End of training

README.md

@@ -0,0 +1,54 @@
+---
+base_model: facebook/opt-350m
+library_name: peft
+license: other
+tags:
+- generated_from_trainer
+model-index:
+- name: gi
+  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. -->
+
+# gi
+
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 0.1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.1.dev0
+- Transformers 4.44.0
+- Pytorch 2.4.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "decoder.layers.22.self_attn.k_proj",
+    "decoder.layers.23.self_attn.out_proj",
+    "decoder.layers.23.self_attn.v_proj",
+    "decoder.layers.23.self_attn.k_proj",
+    "decoder.layers.23.self_attn.q_proj",
+    "decoder.layers.22.self_attn.q_proj",
+    "decoder.layers.22.self_attn.v_proj",
+    "decoder.layers.22.self_attn.out_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836fd30cffbfe0fbf6cdc2d2470408aef317c6ec1b900eff047f20be99649faa
+size 4301568

runs/Aug07_05-07-38_e7aa16e3ac73/events.out.tfevents.1723007286.e7aa16e3ac73.853.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26daf3b224daf42cc7479321454c21b81caf4c3574e053b65521820845bbc00c
+size 5164

runs/Aug07_05-09-02_e7aa16e3ac73/events.out.tfevents.1723007343.e7aa16e3ac73.853.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80b7c7fb7642fca8b6323cf04bd5e308faf969e6d000329ce3eee5721ca6547
+size 14810

runs/Aug07_05-13-58_e7aa16e3ac73/events.out.tfevents.1723007641.e7aa16e3ac73.853.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cce0806a8304ebbe7921378ef263b51faaf0574e6e232ec0d9556ca5654207b
+size 6135

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd86935e7d15e66c7d4345d26c8f3d4abb5a8f3ab72d94109c2cd33c94a87d3
+size 5176