End of training
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ tags:
|
|
| 5 |
- axolotl
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
-
- name: Llama-3-8B-tulu-human
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
|
@@ -28,8 +28,8 @@ strict: false
|
|
| 28 |
datasets:
|
| 29 |
- path: penfever/tulu-v2-flan-v2-cot-science
|
| 30 |
type: sharegpt.load_ultrachat
|
|
|
|
| 31 |
|
| 32 |
-
chat_template: llama3
|
| 33 |
dataset_prepared_path: ./datasets/tulu-human
|
| 34 |
output_dir: ./outputs/tulu-human
|
| 35 |
|
|
@@ -37,14 +37,13 @@ sequence_len: 8192
|
|
| 37 |
sample_packing: true
|
| 38 |
pad_to_sequence_len: true
|
| 39 |
|
| 40 |
-
shuffle_merged_datasets: true
|
| 41 |
|
| 42 |
wandb_project: lm-evals
|
| 43 |
wandb_entity:
|
| 44 |
wandb_watch:
|
| 45 |
wandb_name: Llama-3-8B-tulu-human
|
| 46 |
wandb_log_model:
|
| 47 |
-
hub_model_id: penfever/Llama-3-8B-tulu-human
|
| 48 |
|
| 49 |
gradient_accumulation_steps: 8
|
| 50 |
micro_batch_size: 1
|
|
@@ -83,8 +82,8 @@ special_tokens:
|
|
| 83 |
|
| 84 |
</details><br>
|
| 85 |
|
| 86 |
-
[<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/nyu-dice-lab/lm-evals/runs/
|
| 87 |
-
# Llama-3-8B-tulu-human
|
| 88 |
|
| 89 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
| 90 |
|
|
|
|
| 5 |
- axolotl
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
+
- name: Llama-3-8B-tulu-human-v2
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
|
|
|
| 28 |
datasets:
|
| 29 |
- path: penfever/tulu-v2-flan-v2-cot-science
|
| 30 |
type: sharegpt.load_ultrachat
|
| 31 |
+
conversation: llama3
|
| 32 |
|
|
|
|
| 33 |
dataset_prepared_path: ./datasets/tulu-human
|
| 34 |
output_dir: ./outputs/tulu-human
|
| 35 |
|
|
|
|
| 37 |
sample_packing: true
|
| 38 |
pad_to_sequence_len: true
|
| 39 |
|
|
|
|
| 40 |
|
| 41 |
wandb_project: lm-evals
|
| 42 |
wandb_entity:
|
| 43 |
wandb_watch:
|
| 44 |
wandb_name: Llama-3-8B-tulu-human
|
| 45 |
wandb_log_model:
|
| 46 |
+
hub_model_id: penfever/Llama-3-8B-tulu-human-v2
|
| 47 |
|
| 48 |
gradient_accumulation_steps: 8
|
| 49 |
micro_batch_size: 1
|
|
|
|
| 82 |
|
| 83 |
</details><br>
|
| 84 |
|
| 85 |
+
[<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/nyu-dice-lab/lm-evals/runs/rpepckaq)
|
| 86 |
+
# Llama-3-8B-tulu-human-v2
|
| 87 |
|
| 88 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
| 89 |
|
pytorch_model-00001-of-00004.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4976718466
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eda0e48bd701e5c119343bcad0190e08a6abf1b9a933e0c3f2fc10e779d1a1d3
|
| 3 |
size 4976718466
|
pytorch_model-00002-of-00004.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999827718
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0ce61ccaacc7d5e3cf36d5487c37512e8dcab7befed251a4342337e06fc67ad
|
| 3 |
size 4999827718
|
pytorch_model-00003-of-00004.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915940170
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e9ee8f0fe08a3e592c175d9c274beb21c8e1919ffc59b52ca75e396a3f76605
|
| 3 |
size 4915940170
|
pytorch_model-00004-of-00004.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168140873
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ffbc8f50fc62ecad6c8e9e75d9497a027dbfd117fe4f80df83347ceb55d50b
|
| 3 |
size 1168140873
|