End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: microsoft/phi-2
+model-index:
+- name: phi-2
+  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. -->
+
+# phi-2
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None 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: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- training_steps: 100
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.38.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "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",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7f59b213aaabf03cbdde20491a9117e1019823b00442fb9857b2f9838d58be
+size 31483040

runs/Jan21_08-11-47_54cbda4b5896/events.out.tfevents.1705824714.54cbda4b5896.1986.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c23d1c4b48c1f631a36b26f79ec49749ec58530ec6a38daf541bb1777a485d0
+size 4959

runs/Jan21_08-13-18_54cbda4b5896/events.out.tfevents.1705824802.54cbda4b5896.1986.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ae62ce59c7d154301574863ef8a3fba61f85e40ed240bcb9c355fc97219c9c
+size 4958

runs/Jan21_08-15-16_54cbda4b5896/events.out.tfevents.1705824919.54cbda4b5896.1986.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f755e2eef0bad0f03a94df037fdaaa2371b531a3660a65053d32ae0d8a0f88
+size 4958

runs/Jan21_08-16-50_54cbda4b5896/events.out.tfevents.1705825014.54cbda4b5896.1986.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e74c1b36cd54456f1bbb828bb051cd6c6dff15ef456bec28a92c7a1287e52a
+size 4955

runs/Jan21_08-18-02_54cbda4b5896/events.out.tfevents.1705825087.54cbda4b5896.1986.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e054aa1145d72bf70081340ccd1574c40bcfc60d329a24707aa8c4b79d82723
+size 4955

runs/Jan21_08-28-02_54cbda4b5896/events.out.tfevents.1705825689.54cbda4b5896.1986.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3941fa73fa6931e86c6dc15121da504a684af958c8ac09b9e600ca7b267d299a
+size 4955

runs/Jan21_08-34-39_54cbda4b5896/events.out.tfevents.1705826084.54cbda4b5896.1986.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2eb52ed844ca05283b04120f2d71eb305aa72197272b0899e3e9962b338b09
+size 20704

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3005851bafc8241bdbf5f1f9a75341d78b20afc0c6df05dfffb0142e7c23136e
+size 4664