Training in progress, step 10

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h",
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0920d3c5e341de178f033b35dded693280f0721458d9b147f14c23f8548ffd57
+size 65309632

runs/Dec06_13-38-43_a48b6f973322/events.out.tfevents.1701870008.a48b6f973322.184.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95ba07da3121b00719b3f95dfd8fc2a9bc30c16b2fae9413f9c6961323d6ea0
+size 20357

runs/Dec06_13-52-07_a48b6f973322/events.out.tfevents.1701870760.a48b6f973322.184.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd2fa449dfb40c61eb6f941635b84c4d0a4c3bef7479fb5cae60db4735a0dfc
+size 20375

runs/Dec06_14-10-11_a48b6f973322/events.out.tfevents.1701871821.a48b6f973322.8635.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036bfd28be4e290745f842e7141f0eb9164459160a12f47580f4e515e8167e17
+size 28147

runs/Dec06_14-24-22_a48b6f973322/events.out.tfevents.1701872854.a48b6f973322.8635.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828abd83cd58cf408db8049095b292f65d50db8b21df2db3bf87caf890f6d750
+size 6315

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c57059d0252dac184da6299e1ea4159d1dc6cbaefacfc9b22c0a0b094ea0a85
+size 4600

training_config.json

@@ -0,0 +1,93 @@
+{
+  "experiment_key": "base",
+  "save_safetensors": true,
+  "max_shard_size": "10GB",
+  "local_rank": 0,
+  "use_gradient_checkpointing": true,
+  "trainer_key": "lm",
+  "force_fp32": false,
+  "force_fp16": false,
+  "from_gptq": false,
+  "huggingface_hub_token": null,
+  "single_gpu": null,
+  "master_port": 9994,
+  "deepspeed_stage": null,
+  "deepspeed_config_path": null,
+  "fsdp_strategy": "",
+  "fsdp_offload": true,
+  "seed": 42,
+  "stabilize": false,
+  "norm_fp32": false,
+  "path_to_env_file": "./.env",
+  "prepare_dataset": true,
+  "lora_hub_model_id": null,
+  "lora_model_local_path": null,
+  "fused_model_local_path": null,
+  "fuse_after_training": false,
+  "quantization_dataset_id": null,
+  "quantization_max_samples": 1024,
+  "quantized_model_path": "./quantized_model/",
+  "quantized_hub_model_id": null,
+  "quantized_hub_private_repo": true,
+  "dataset_key": "soda",
+  "train_local_path_to_data": "./train.jsonl",
+  "eval_local_path_to_data": null,
+  "shuffle": true,
+  "max_eval_samples": 1000,
+  "add_eval_to_train_if_no_path": false,
+  "tokenizer_name_or_path": null,
+  "tokenizer_use_fast": null,
+  "tokenizer_padding_side": null,
+  "collator_key": "lm",
+  "max_length": 2048,
+  "model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
+  "push_to_hub_bos_add_bos_token": false,
+  "use_flash_attention_2": false,
+  "trust_remote_code": false,
+  "device_map": null,
+  "prepare_model_for_kbit_training": true,
+  "offload_folder": null,
+  "load_in_8bit": false,
+  "load_in_4bit": true,
+  "llm_int8_threshold": 6.0,
+  "llm_int8_has_fp16_weight": true,
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_quantize_after_model_init": false,
+  "gptq_bits": 4,
+  "gptq_group_size": 128,
+  "gptq_disable_exllama": true,
+  "apply_lora": true,
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "raw_lora_target_modules": "all",
+  "output_dir": "./outputs/",
+  "per_device_train_batch_size": 2,
+  "do_eval": false,
+  "per_device_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "eval_steps": 1000,
+  "warmup_steps": 5,
+  "max_steps": 150,
+  "num_train_epochs": 1,
+  "learning_rate": 0.0002,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.001,
+  "label_smoothing_factor": 0.0,
+  "logging_steps": 1,
+  "save_steps": 10,
+  "save_total_limit": 1,
+  "optim": "paged_adamw_8bit",
+  "push_to_hub": true,
+  "hub_model_id": "TachyHealthResearch/Thealth-Falcon_7b",
+  "hub_private_repo": false,
+  "neftune_noise_alpha": null,
+  "project_name": null,
+  "report_to_wandb": false,
+  "wandb_api_key": null,
+  "wandb_project": null,
+  "wandb_entity": null
+}