Upload 11 files

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+model-index:
+- name: train_2024-03-01-19-26-33
+  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. -->
+
+# train_2024-03-01-19-26-33
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the docker_NL 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: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "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,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_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 sha256:6e19bc963b4f047e5838667bae68fec185b460a81553528f07747acd304cef07
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.95,
+    "train_loss": 0.38846387134657967,
+    "train_runtime": 487.2698,
+    "train_samples_per_second": 4.956,
+    "train_steps_per_second": 0.037
+}

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 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": 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
+    }
+  },
+  "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": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.95,
+    "train_loss": 0.38846387134657967,
+    "train_runtime": 487.2698,
+    "train_samples_per_second": 4.956,
+    "train_steps_per_second": 0.037
+}

trainer_log.jsonl

@@ -0,0 +1,4 @@
+{"current_steps": 5, "total_steps": 18, "loss": 0.6603, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016427876096865394, "epoch": 0.26, "percentage": 27.78, "elapsed_time": "0:02:05", "remaining_time": "0:05:26"}
+{"current_steps": 10, "total_steps": 18, "loss": 0.3484, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.263518223330697e-05, "epoch": 0.53, "percentage": 55.56, "elapsed_time": "0:04:22", "remaining_time": "0:03:30"}
+{"current_steps": 15, "total_steps": 18, "loss": 0.2464, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.339745962155613e-05, "epoch": 0.79, "percentage": 83.33, "elapsed_time": "0:06:40", "remaining_time": "0:01:20"}
+{"current_steps": 18, "total_steps": 18, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.95, "percentage": 100.0, "elapsed_time": "0:08:07", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9536423841059603,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8373088240623474,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.6603,
+      "step": 5
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.0933210849761963,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.3484,
+      "step": 10
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.969545841217041,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.2464,
+      "step": 15
+    },
+    {
+      "epoch": 0.95,
+      "step": 18,
+      "total_flos": 7430501711216640.0,
+      "train_loss": 0.38846387134657967,
+      "train_runtime": 487.2698,
+      "train_samples_per_second": 4.956,
+      "train_steps_per_second": 0.037
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 18,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 7430501711216640.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7658868efde504abf2c5d8a32349763db5ea96804272e161da4d92d6bb2e47f2
+size 5112