Model save

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: mistral-instruct-adv-robust-3-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. -->
+
+# mistral-instruct-adv-robust-3-sft-lora
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5498
+
+## 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: 0.0003
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.1318        | 0.12  | 1    | 2.8355          |
+| 3.1318        | 1.12  | 2    | 2.6371          |
+| 3.1318        | 2.12  | 3    | 2.4963          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0a0+32f93b1
+- 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": "mistralai/Mistral-7B-Instruct-v0.1",
+  "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": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29c55278f6fb9e8cb7f6880bebe4efa53063d92efd8aa988d98809f27c1dc009
+size 109086672

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.12,
+    "eval_loss": 2.549821615219116,
+    "eval_runtime": 1.5336,
+    "eval_samples": 234,
+    "eval_samples_per_second": 152.584,
+    "eval_steps_per_second": 5.217,
+    "train_loss": 2.9835983912150064,
+    "train_runtime": 146.3783,
+    "train_samples": 2097,
+    "train_samples_per_second": 42.978,
+    "train_steps_per_second": 0.164
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.12,
+    "eval_loss": 2.549821615219116,
+    "eval_runtime": 1.5336,
+    "eval_samples": 234,
+    "eval_samples_per_second": 152.584,
+    "eval_steps_per_second": 5.217
+}

runs/Jan08_20-24-37_c33a1a6d4547/events.out.tfevents.1704745624.c33a1a6d4547.1255.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960d7590e4410329bb6ef7639047b7db43a1f7e94984384b01cf045eb85290f
+size 5601

runs/Jan08_20-24-37_c33a1a6d4547/events.out.tfevents.1704745772.c33a1a6d4547.1255.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29dd3adbebc0f0287c00b7d6ed0b43251670ba320203566b6709b42a88f6e7b2
+size 306

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.12,
+    "train_loss": 2.9835983912150064,
+    "train_runtime": 146.3783,
+    "train_samples": 2097,
+    "train_samples_per_second": 42.978,
+    "train_steps_per_second": 0.164
+}

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.121212121212121,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00029871672920607153,
+      "loss": 3.1318,
+      "step": 1
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 2.8355371952056885,
+      "eval_runtime": 1.8669,
+      "eval_samples_per_second": 125.339,
+      "eval_steps_per_second": 4.285,
+      "step": 1
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 2.63714861869812,
+      "eval_runtime": 1.5412,
+      "eval_samples_per_second": 151.829,
+      "eval_steps_per_second": 5.191,
+      "step": 2
+    },
+    {
+      "epoch": 2.12,
+      "eval_loss": 2.496318817138672,
+      "eval_runtime": 1.5238,
+      "eval_samples_per_second": 153.559,
+      "eval_steps_per_second": 5.25,
+      "step": 3
+    },
+    {
+      "epoch": 2.12,
+      "step": 3,
+      "total_flos": 270826947477504.0,
+      "train_loss": 2.9835983912150064,
+      "train_runtime": 146.3783,
+      "train_samples_per_second": 42.978,
+      "train_steps_per_second": 0.164
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 24,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 270826947477504.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b41f85065bd5a2c4de181b61230762a44325e1c0e139aa6894b9d121d56647
+size 5688