End of training

README.md

@@ -0,0 +1,58 @@
+---
+base_model: bigscience/bloomz-7b1
+library_name: peft
+license: bigscience-bloom-rail-1.0
+tags:
+- generated_from_trainer
+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/bloomz-7b1](https://huggingface.co/bigscience/bloomz-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: 2
+- training_steps: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.1.dev0
+- Transformers 4.44.0.dev0
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigscience/bloomz-7b1",
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense_4h_to_h",
+    "query_key_value",
+    "dense_h_to_4h",
+    "dense"
+  ],
+  "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 sha256:4ec35725eb5142525c4fc93cd8c3ad590cdea335b07d32d6d46a38f66ffdcfe9
+size 62948128

runs/Jul31_18-25-16_339865bd6f7e/events.out.tfevents.1722450318.339865bd6f7e.1041.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9cb43fbe142b46b15e3cc0b4e1d9545128df33adea075f35bd5d8a67bdfb9b
+size 7915

runs/Jul31_18-37-42_339865bd6f7e/events.out.tfevents.1722451063.339865bd6f7e.1041.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a2674009a766b5627138aad5b94234af28ab838d6d7f00105aa21091b9c16c
+size 7915

runs/Jul31_18-47-51_339865bd6f7e/events.out.tfevents.1722451672.339865bd6f7e.1041.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d373c265bf64b8de00830e27f84039eb38692ac5731b06618756a0c66cd5f5a
+size 7915

runs/Jul31_19-09-14_339865bd6f7e/events.out.tfevents.1722452955.339865bd6f7e.1041.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2504036aa7fa0de94b884defd7325ac9dfe2e23e2bd7e6c4ee69200fb37b7e45
+size 7915

runs/Jul31_19-24-16_339865bd6f7e/events.out.tfevents.1722453856.339865bd6f7e.1041.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea984ea2eef7b6753d3bcaad96b78e5050d0eaa4a6cd0c08fa17974eb465c84
+size 7915

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2cb1748a9b2d8eb6cc8d97e537eb8679b765c1da1615ad7f01986ceb5c20c1
+size 5176