Update README.md

README.md

@@ -1,3 +1,49 @@
 ---
 license: apache-2.0
 ---
+
+Preliminary info during eval. Model card will be updated.
+
+wandb: wandb: https://wandb.ai/open-assistant/supervised-finetuning/runs/3lr77x4h
+export: 560 steps
+
+
+Model:
+```
+falcon-40b:
+  dtype: bf16
+  log_dir: "falcon_log_40b"
+  learning_rate: 5e-6
+  model_name: "tiiuae/falcon-40b"
+  deepspeed_config: configs/zero3_config_falcon.json
+  output_dir: falcon
+  weight_decay: 0.0
+  max_length: 2048
+  warmup_steps: 20
+  gradient_checkpointing: true
+  gradient_accumulation_steps: 1
+  per_device_train_batch_size: 18
+  per_device_eval_batch_size: 10
+  eval_steps: 80
+  save_steps: 80
+  num_train_epochs: 8
+  save_total_limit: 4
+  use_flash_attention: false
+  residual_dropout: 0.3
+  residual_dropout_lima: true
+  sort_by_length: false
+  save_strategy: steps
+```
+
+Dataset:
+```
+oasst_only:
+  save_strategy: epoch
+  datasets:
+    - oasst_export:
+        lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk"
+        input_file_path: 2023-04-04_oasst_ready.jsonl.gz
+        val_split: 0.05
+  sort_by_length: false
+  use_custom_sampler: false
+```