ep2

configs/mistral-7b-oo-phase1.yml

@@ -0,0 +1,71 @@
+base_model: mistralai/Mistral-7B-v0.1
+base_model_config: mistralai/Mistral-7B-v0.1
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: openaccess-ai-collective/oo-gpt4-filtered
+    type: alpaca_w_system.load_open_orca_chatml
+    data_files:
+      - 1M-GPT4-Augmented-filtered-gt10.parquet
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.005
+output_dir: ./mistral-oo
+
+sequence_len: 4096
+sample_packing: true
+pad_to_sequence_len: true
+
+wandb_project: mistral-oo-7b
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 6
+num_epochs: 4
+optimizer: adamw_torch
+adam_beta2: 0.95
+adam_epsilon: 0.00001
+max_grad_norm: 1.0
+lr_scheduler: cosine
+learning_rate: 0.000006
+
+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: 100
+eval_steps: 0.05
+eval_table_size:
+eval_table_max_new_tokens:
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "<|im_end|>"
+  unk_token: "<unk>"
+tokens:
+  - "<|im_start|>"
+  - "<|im_end|>"

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e6cd0ab7ee0e68c7e8019dbb89ea25bbce57837a35a1e41402838ce11d32d6b
+oid sha256:4aaee725fafdf4c88baa1c0d2900b249c1bcf6716af55e610e75c50bfaa9eb4c
 size 9943044428

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47288e5bb620c13adecf6ac4228c1fa35cdc168e69d1b9199833290cca2adda9
+oid sha256:ec039d944707a7e6eb7d1453861143a3ea99d657b52b7d9a0aee2de734d9075f
 size 4540552031