Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: tiiuae/falcon-7b
+tags:
+- generated_from_trainer
+model-index:
+- name: falcon-7b-sft-lora
+  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. -->
+
+# falcon-7b-sft-lora
+
+This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6898
+
+## 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
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 4096
+- total_eval_batch_size: 64
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.6877        | 0.99  | 50   | 1.6898          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.2+cu121
+- 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": "tiiuae/falcon-7b",
+  "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": [
+    "query_key_value",
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1472d95895fe0a3106d3df2e3c0c5fa104e008600e01777d9e979465a6b3003
+size 522227376

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.99,
+    "eval_loss": 1.6898281574249268,
+    "eval_runtime": 1242.0087,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 18.607,
+    "eval_steps_per_second": 0.291,
+    "train_loss": 1.7278787899017334,
+    "train_runtime": 16160.382,
+    "train_samples": 207865,
+    "train_samples_per_second": 12.863,
+    "train_steps_per_second": 0.003
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "eval_loss": 1.6898281574249268,
+    "eval_runtime": 1242.0087,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 18.607,
+    "eval_steps_per_second": 0.291
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,124 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "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": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "train_loss": 1.7278787899017334,
+    "train_runtime": 16160.382,
+    "train_samples": 207865,
+    "train_samples_per_second": 12.863,
+    "train_steps_per_second": 0.003
+}

trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9852216748768473,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9980267284282718e-05,
+      "loss": 1.7982,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 1.7845,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.7893,
+      "step": 10
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 1.768,
+      "step": 15
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 1.749,
+      "step": 20
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1e-05,
+      "loss": 1.7308,
+      "step": 25
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 1.7066,
+      "step": 30
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 1.6928,
+      "step": 35
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 1.6886,
+      "step": 40
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 1.6787,
+      "step": 45
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0,
+      "loss": 1.6877,
+      "step": 50
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.6897964477539062,
+      "eval_runtime": 1242.0222,
+      "eval_samples_per_second": 18.607,
+      "eval_steps_per_second": 0.291,
+      "step": 50
+    },
+    {
+      "epoch": 0.99,
+      "step": 50,
+      "total_flos": 4.2510105305184993e+18,
+      "train_loss": 1.7278787899017334,
+      "train_runtime": 16160.382,
+      "train_samples_per_second": 12.863,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4.2510105305184993e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6314db0d7ec1e303d8367f2ef7820b084104320bd76154213be099e5902bcc9
+size 4664