End of training

README.md

@@ -0,0 +1,56 @@
+---
+library_name: peft
+license: mit
+base_model: microsoft/Phi-4-mini-instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: s1-2q-phi4ins
+  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. -->
+
+# s1-2q-phi4ins
+
+This model is a fine-tuned version of [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu126
+- Datasets 3.3.2
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "qkv_proj",
+    "gate_up_proj",
+    "down_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 sha256:984947e531e78f25b7af0feffcf3013c3cf503d78e8ed985d6ea513917c1acfc
+size 184584072

logs/events.out.tfevents.1744650308.psto2hdwdk5g.3469.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1532466a68e9a2adf736d8d0f8d96a5ae09788924b39f5a1ed09b97e5970dba8
+size 88

logs/events.out.tfevents.1744650353.psto2hdwdk5g.3604.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc6f969db6ae59279955f113bf0e136c4f0eb47a0299ef90165390cd1703084
+size 88

logs/events.out.tfevents.1744650477.psto2hdwdk5g.3776.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c197e296854f770af2e9919f0b0ef13111042751ad963ec4ac0e6da6c2d25069
+size 18521

runs/Apr14_17-05-08_psto2hdwdk5g/events.out.tfevents.1744650309.psto2hdwdk5g.3469.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ca87699c5bb48e0b41b4f37fbf7af2fea91f181cf2cfdcd9e6c94fa631b036
+size 7492

runs/Apr14_17-05-53_psto2hdwdk5g/events.out.tfevents.1744650353.psto2hdwdk5g.3604.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764a202be7447b3ca425f65e74259b20dc653869f48cf65dda5416cee6c685c9
+size 7492

runs/Apr14_17-07-57_psto2hdwdk5g/events.out.tfevents.1744650477.psto2hdwdk5g.3776.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1656f64fa371d0f185720ea3026ea25f9150a2337ecc4a175cd6b57062d6b816
+size 28289

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1479fdd1dbc57e34459b11b8b5a6fa52e44010c7da49005807d4ee5d68528000
+size 5304