End of training

README.md

@@ -0,0 +1,58 @@
+---
+license: bigscience-bloom-rail-1.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: bigscience/bloom-7b1
+model-index:
+- name: outputs
+  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. -->
+
+# outputs
+
+This model is a fine-tuned version of [bigscience/bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) 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: linear
+- lr_scheduler_warmup_steps: 10
+- training_steps: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigscience/bloom-7b1",
+  "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": 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": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6802d6af75cdee360a1c041cc8f6c4fbaf7bab5fe8d6de2f31ce410011705ee6
+size 31466288

runs/Dec31_08-46-27_6fdad89039a6/events.out.tfevents.1704012388.6fdad89039a6.566.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:869eb6155868763d9d3264d6b018cd7f457012d0faf88c60aeb63b574b252636
+size 7474

runs/Dec31_08-57-39_6fdad89039a6/events.out.tfevents.1704013060.6fdad89039a6.566.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f313f8d6af6261b47e38c953abe58a179da00b56067ef4f81b862212c0a6ce31
+size 12402

runs/Dec31_09-02-08_6fdad89039a6/events.out.tfevents.1704013329.6fdad89039a6.566.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5daada350a93199b3f589377262999cedc7f75a7495b416282d96882ccc44670
+size 4856

runs/Dec31_09-02-16_6fdad89039a6/events.out.tfevents.1704013336.6fdad89039a6.566.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06617cca44b155dc04d76b673dd9b93a8549bebb21904a996c367718e953d69d
+size 8282

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3280fc9c82e907270d595d5a1f390b86f2c86464ebebbaa7345f158182a9a0a8
+size 4664