26/200 Hours

checkpoint-6656/adapter_config.json

@@ -0,0 +1,17 @@
+{
+  "base_model_name_or_path": "models/llama-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 128,
+  "lora_dropout": 0,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-6656/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6883855cfb09ee768225813419cd4b7569b8fd6e9f00d35194092ef216f7ba02
+size 209772877

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_parameters.json

@@ -0,0 +1 @@
+{"lora_name": "VicUnLocked", "always_override": false, "save_steps": 500.0, "micro_batch_size": 4, "batch_size": 128, "epochs": 3.0, "learning_rate": "3e-4", "lr_scheduler_type": "constant_with_warmup", "lora_rank": 64, "lora_alpha": 128, "lora_dropout": 0, "cutoff_len": 2048, "dataset": "vicuna-all", "eval_dataset": "None", "format": "vicuna-format", "eval_steps": 100.0, "raw_text_file": "None", "overlap_len": 128, "newline_favor_len": 128, "higher_rank_limit": false, "warmup_steps": 100.0, "optimizer": "adamw_torch"}