Training in progress, step 25

README.md

@@ -0,0 +1,52 @@
+---
+base_model: NousResearch/Llama-2-7b-chat-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: llama-2-7b-chat-recipe-qlora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llama-2-7b-chat-recipe-qlora
+
+This model is a fine-tuned version of [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f956b6c41fb074e4a5d866733c2868606b640d796d9a98a0f8755c095167ff
+size 134264202

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83e0a208359c90bc846e122fc4f71f6bd08cca1046faf2d27637e623cb7055e
+size 134235048

runs/Dec05_23-34-26_ip-172-31-30-2/events.out.tfevents.1701819267.ip-172-31-30-2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7621da03064001f9d10bcd3272b8504e2d50590f759e215ab54f86ad0bb2d97f
+size 4925

runs/Dec05_23-40-53_ip-172-31-30-2/events.out.tfevents.1701819654.ip-172-31-30-2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a136eb30ece741b536afb44d2a75d303f8bc8269ebb8f15f9616734344ea5fed
+size 4950

runs/Dec05_23-43-40_ip-172-31-30-2/events.out.tfevents.1701819820.ip-172-31-30-2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:628807aa401c776b7905538013d7b5b6d1b5ebf81860a7326c3819a2b2e0ffa3
+size 5258

runs/Dec05_23-47-45_ip-172-31-30-2/events.out.tfevents.1701820067.ip-172-31-30-2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6cd114a561259a42fb4b13d955a3c0f1acdeac312d36c129567a64e86c404d
+size 4602

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeabfc72e916ff3e7e7d7273499dd67985b32e84916fa61e4acd9fc7ce8a4dbd
+size 4600