Add fine-tuned adapter files for llama2

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16338d90f0c74a3402a55eefb52e83085767c5e79d9d274ac5182d29628ddb83
+size 92824216

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1029e945573affcbae7aa838743822d789328c9f586742732a249c690e0f647c
+size 46714042

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ffdee95775a291e5a1e6ffe567ec2373fd9f957c21f22cc14752e6968c4de6
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6ec5a4843ffa4b7393d41470a29a9c57f4f966d2d62150a3f0a7fa119a9e3c
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2924831822170225,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.515340268611908,
+      "learning_rate": 8.911111111111111e-05,
+      "loss": 1.8825,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 1.3453257083892822,
+      "eval_runtime": 1951.9862,
+      "eval_samples_per_second": 10.508,
+      "eval_steps_per_second": 0.219,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.49174025654792786,
+      "learning_rate": 6.688888888888889e-05,
+      "loss": 1.2985,
+      "step": 200
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.265929102897644,
+      "eval_runtime": 1951.6138,
+      "eval_samples_per_second": 10.51,
+      "eval_steps_per_second": 0.219,
+      "step": 200
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5104777812957764,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 1.2481,
+      "step": 300
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 1.2371329069137573,
+      "eval_runtime": 1951.7352,
+      "eval_samples_per_second": 10.509,
+      "eval_steps_per_second": 0.219,
+      "step": 300
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.5633695125579834,
+      "learning_rate": 2.2444444444444447e-05,
+      "loss": 1.2295,
+      "step": 400
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.2196089029312134,
+      "eval_runtime": 1951.3878,
+      "eval_samples_per_second": 10.511,
+      "eval_steps_per_second": 0.219,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.5293011665344238,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 1.2129,
+      "step": 500
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 1.2104666233062744,
+      "eval_runtime": 1951.0729,
+      "eval_samples_per_second": 10.513,
+      "eval_steps_per_second": 0.219,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 9.166063140864e+16,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b791709c210e553340c37e011883eb923b6a41e2f882e3714cd59e7e8c5b89a0
+size 4856