checkpoints readme

README.md

@@ -1,224 +1,169 @@
 ---
+language:
+- en
 license: other
-base_model: meta-llama/Meta-Llama-3-8B
 tags:
 - axolotl
 - generated_from_trainer
+- instruct
+- finetune
+- chatml
+- gpt4
+- synthetic data
+- science
+- physics
+- chemistry
+- biology
+- math
+- llama
+- llama3
+base_model: meta-llama/Meta-Llama-3-8B
+datasets:
+- allenai/ai2_arc
+- camel-ai/physics
+- camel-ai/chemistry
+- camel-ai/biology
+- camel-ai/math
+- metaeval/reclor
+- openbookqa
+- mandyyyyii/scibench
+- derek-thomas/ScienceQA
+- TIGER-Lab/ScienceEval
+- jondurbin/airoboros-3.2
+- LDJnr/Capybara
+- Cot-Alpaca-GPT4-From-OpenHermes-2.5
+- STEM-AI-mtl/Electrical-engineering
+- knowrohit07/saraswati-stem
+- sablo/oasst2_curated
+- lmsys/lmsys-chat-1m
+- TIGER-Lab/MathInstruct
+- bigbio/med_qa
+- meta-math/MetaMathQA-40K
+- openbookqa
+- piqa
+- metaeval/reclor
+- derek-thomas/ScienceQA
+- scibench
+- sciq
+- Open-Orca/SlimOrca
+- migtissera/Synthia-v1.3
+- TIGER-Lab/ScienceEval
+- allenai/WildChat
+- microsoft/orca-math-word-problems-200k
+- openchat/openchat_sharegpt4_dataset
+- teknium/GPTeacher-General-Instruct
+- m-a-p/CodeFeedback-Filtered-Instruction
+- totally-not-an-llm/EverythingLM-data-V3
+- HuggingFaceH4/no_robots
+- OpenAssistant/oasst_top1_2023-08-25
+- WizardLM/WizardLM_evol_instruct_70k
 model-index:
 - name: Einstein-v6.1-Llama3-8B
-  results: []
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 62.46
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 82.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 66.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 55.1
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 79.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 66.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
+      name: Open LLM Leaderboard
 ---
 
-<!-- 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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
-<details><summary>See axolotl config</summary>
-
-axolotl version: `0.4.0`
-```yaml
-base_model: meta-llama/Meta-Llama-3-8B
-model_type: LlamaForCausalLM
-tokenizer_type: AutoTokenizer
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-chat_template: chatml
-datasets:
-  - path: data/merged_all.json
-    ds_type: json
-    type: alpaca
-    conversation: chatml
-
-  - path: data/gpteacher-instruct-special-alpaca.json
-    ds_type: json
-    type: gpteacher
-    conversation: chatml
-
-  - path: data/wizardlm_evol_instruct_70k_random_half.json
-    ds_type: json
-    type: alpaca
-    conversation: chatml
-
-  - path: data/capybara_sharegpt.json
-    ds_type: json
-    type: sharegpt
-    conversation: chatml
-
-  - path: data/synthia-v1.3_sharegpt_12500.json
-    ds_type: json
-    type: sharegpt
-    conversation: chatml  
-
-  - path: data/cot_alpaca_gpt4_extracted_openhermes_2.5_sharegpt.json
-    ds_type: json
-    type: sharegpt
-    conversation: chatml
-
-  - path: data/slimorca_dedup_filtered_95k_sharegpt.json
-    ds_type: json
-    type: sharegpt
-    conversation: chatml  
-
-  - path: data/airoboros_3.2_without_contextual_slimorca_orca_sharegpt.json
-    ds_type: json
-    type: sharegpt
-    conversation: chatml  
-
-  - path: data/allenai_wild_chat_gpt4_english_toxic_random_half_4k_sharegpt.json
-    ds_type: json
-    type: sharegpt
-    strict: false
-    conversation: chatml  
-
-  - path: data/pippa_bagel_repo_3k_sharegpt.json
-    ds_type: json
-    type: sharegpt
-    conversation: chatml  
-
-  - path: data/gpt4_data_lmys_1m_sharegpt.json
-    ds_type: json
-    type: sharegpt
-    conversation: chatml  
-
-  - path: data/sharegpt_gpt4_english.json
-    ds_type: json
-    type: sharegpt
-    conversation: chatml
-
-  - path: data/no_robots_sharegpt.json
-    ds_type: json
-    type: sharegpt
-    strict: false
-    conversation: chatml
-
-  - path: data/oasst_top1_from_fusechatmixture_sharegpt.json
-    ds_type: json
-    type: sharegpt
-    strict: false
-    conversation: chatml
-
-  - path: data/everythinglm-data-v3_sharegpt.json
-    ds_type: json
-    type: sharegpt
-    strict: false
-    conversation: chatml
-
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.002
-
-output_dir: ./Einstein-v6.1-Llama3-8B-model
-
-sequence_len: 8192
-sample_packing: true
-pad_to_sequence_len: true
-eval_sample_packing: false
-
-wandb_project: Einstein
-wandb_entity:
-wandb_watch:
-wandb_name: Einstein-v6.1-Llama3-2-epoch
-wandb_log_model:
-hub_model_id: Weyaxi/Einstein-v6.1-Llama3-8B
-
-save_safetensors: true
-
-gradient_accumulation_steps: 4
-micro_batch_size: 1
-num_epochs: 2
-optimizer: adamw_bnb_8bit # look
-lr_scheduler: cosine
-learning_rate: 0.000005 # look
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 2
-eval_table_size:
-eval_table_max_new_tokens: 128
-saves_per_epoch: 2
-debug:
-
-deepspeed: zero3_bf16_cpuoffload_params.json
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "<|im_end|>"
-  unk_token: "<unk>"
-  pad_token: <|end_of_text|> # changed
-tokens:
-  - "<|im_start|>"
-
-```
-
-</details><br>
-
-# Einstein-v6.1-Llama3-8B
-
-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.
-It achieves the following results on the evaluation set:
-- Loss: 0.5786
-
-## 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: 5e-06
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 9
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 36
-- total_eval_batch_size: 9
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 10
-- num_epochs: 2
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.6849        | 0.0   | 1    | 1.7294          |
-| 0.6045        | 0.5   | 507  | 0.6127          |
-| 0.5986        | 1.0   | 1014 | 0.5868          |
-| 0.5136        | 1.48  | 1521 | 0.5786          |
-
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/Z-THA-NDPl3YPUnACsQ0c.png)
 
-### Framework versions
+Checkpoints of [Weyaxi/Einstein-v6-7B](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B). Head to the main model for more information :)
 
-- Transformers 4.40.0.dev0
-- Pytorch 2.1.2+cu118
-- Datasets 2.18.0
-- Tokenizers 0.15.0
+https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B