End of training

README.md

@@ -1,3 +1,58 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+model-index:
+- name: mistraldog
+  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. -->
+
+# mistraldog
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) 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: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "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": [
+    "q_proj",
+    "v_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 sha256:65eebef713be36343b8624dc5918d3b5f7b96badf114538580a5bffd2beb5c1b
+size 27280152

runs/May24_18-59-46_f391a23663e8/events.out.tfevents.1716577187.f391a23663e8.6489.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4f4b3a445dbdee9768145bd73621a76d3c9ec92969beaec41070fc7858a210
+size 6151

runs/May24_19-00-55_f391a23663e8/events.out.tfevents.1716577255.f391a23663e8.6489.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d27040b2e65a174dcc4ba5b0ca970ec8f8eb4d34e2b0a4d4af868283070d8e3f
+size 6151

runs/May24_19-03-30_f391a23663e8/events.out.tfevents.1716577410.f391a23663e8.6489.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de60303c525c16412a77c6aeb5dd9c6d2f0c90d8544f923308a37671e721235c
+size 6151

runs/May24_19-04-37_f391a23663e8/events.out.tfevents.1716577479.f391a23663e8.6489.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23edaa294a291dd0ed78d9e80c9ed2052dafdebfeb48b995b13e0d28cf999a98
+size 6150

runs/May24_19-19-34_f391a23663e8/events.out.tfevents.1716578376.f391a23663e8.11521.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f083b5f9aedc0e4fafb4472fdad163972c46592232afc6a7c17dab74c0aa44
+size 42094

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d0acb6f8f1bd292fb4763b50a6328055e9cf8cfbfa978a0393e1284e4fa675
+size 5112