Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: llama-7b-sft-lora-qrecc
+  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-7b-sft-lora-qrecc
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5184
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3033        | 1.0   | 1    | 1.5184          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "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,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6e588007baf58e516ad55d8255d8e94df1294163ebb59aa343e576e2054ae3
+size 268470272

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.5184062719345093,
+    "eval_runtime": 17.7955,
+    "eval_samples": 101,
+    "eval_samples_per_second": 5.676,
+    "eval_steps_per_second": 0.731,
+    "train_loss": 0.30328860878944397,
+    "train_runtime": 67.0626,
+    "train_samples": 101,
+    "train_samples_per_second": 1.506,
+    "train_steps_per_second": 0.015
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.5184062719345093,
+    "eval_runtime": 17.7955,
+    "eval_samples": 101,
+    "eval_samples_per_second": 5.676,
+    "eval_steps_per_second": 0.731
+}

runs/Dec29_16-04-07_rPower2/events.out.tfevents.1703833592.rPower2.2720387.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e456cf7985d037218a33e853d71d637174b8c6def5b2bac789a32e833cf91151
+size 4326

runs/Dec29_16-17-54_rPower2/events.out.tfevents.1703834420.rPower2.2730108.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f33c6d260967599d0ffc2c9192d993b8740f002f609f3e068460a52df98a665
+size 4326

runs/Dec29_16-22-33_rPower2/events.out.tfevents.1703834699.rPower2.2733573.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ebf5a0a5d61e0fb81297c429eba3154c8a6df9478cdb3b3ebe872889c37705
+size 4326

runs/Dec29_16-26-22_rPower2/events.out.tfevents.1703834926.rPower2.2736373.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cde580954b8a020faa6436ff72f004328324fb2e4ce8287eeb7991f852c480c
+size 5094

runs/Dec29_16-26-22_rPower2/events.out.tfevents.1703835011.rPower2.2736373.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e130c2a0586efc96a51aa53d0febc718a44beab850870073846a4754b067144b
+size 354

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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.30328860878944397,
+    "train_runtime": 67.0626,
+    "train_samples": 101,
+    "train_samples_per_second": 1.506,
+    "train_steps_per_second": 0.015
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.3033,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.5184062719345093,
+      "eval_runtime": 18.0579,
+      "eval_samples_per_second": 5.593,
+      "eval_steps_per_second": 0.72,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "step": 1,
+      "total_flos": 2285025504337920.0,
+      "train_loss": 0.30328860878944397,
+      "train_runtime": 67.0626,
+      "train_samples_per_second": 1.506,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2285025504337920.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ed542bd6bc35271666c4eba73e060bc73a44314bda10d405a69eef10e78d89
+size 4664