upload

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+license: llama2
+base_model: meta-llama/CodeLlama-13b-Instruct-hf
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- meng-lab/CodeLlama-13B-Instruct-humaneval
+model-index:
+- name: CodeLlama-13b-Instruct-sft-5e-3-epoch-100-human-eval-final
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/uva-llm/huggingface/runs/ktf7e5mf)
+# CodeLlama-13b-Instruct-sft-5e-3-epoch-100-human-eval-final
+
+This model is a fine-tuned version of [meta-llama/CodeLlama-13b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-13b-Instruct-hf) on the meng-lab/CodeLlama-13B-Instruct-humaneval 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: 0.005
+- train_batch_size: 1
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 100
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.43.2
+- Pytorch 2.1.2
+- Datasets 3.0.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011a24a59be10c9b31e3f97bcc70bc33933add0cd5037ef5b3b63d4524860997
+size 248

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1078c6187e12a778b7958505c63acf921c28a5182cd16d517bf0722504554987
+size 760

generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8efb27b6a9f4c441cb9a76e40fecd2b6273a4bb39b9b23bfde3cb65d64a9297
+size 165

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a020a5c23022a5b7d0b8a3c16cc221eadbb8aceb1e8e8622f1fb974062f2ead0
+size 4978429640

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:370a6aea5d6982f3cbe8f16cc01be355558ef70632c19cf1122c44c9da381d84
+size 4970422232

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67f4b1f19ca1d39449e147fc2711d4fa73655ced4c62381c8f02077affeae148
+size 4970422256

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93d562d55dd5812217d1acc53d6586e4b23a54b6a83ec7b33b961b2e37994fc
+size 4933701504

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5b019c3f3839465e51f62974b4659c4466092f8236f7a931b950102dd1e550
+size 4933722216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff9a3a5a44da075b1254ed66edfbf30c26d6e0b77ae59690d551a088951a98c
+size 1612403160

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440ac613ed315497ae0a4135ae071db17f46d2d4cfa4b3a0c1802aeadfb7f579
+size 30467

special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f32ca2dd65336aceb9e359886f34f214330137c9e801e8f41cf542287fc2630
+size 538

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291f17d67e18966968c59917e7e1d2308a713053295404ce082be31d54581103
+size 1844191

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979691167581a52e577ef4c2b8b8d3faa25efc022fb65c7f16036474ddc5cf85
+size 2652

train_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011a24a59be10c9b31e3f97bcc70bc33933add0cd5037ef5b3b63d4524860997
+size 248

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:605e6e18ebc4c2d4f22694f91c40f030bddac0e435521f6a092a9bc9582b1bcb
+size 663189

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea2b1378ed246734f688beb6fa48ecbde4d2616638891dccaaf2c17e55d7835
+size 6904