Upload folder using huggingface_hub

README.md

@@ -0,0 +1,58 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: train_2024-02-26-06-49-61
+  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_2024-02-26-06-49-61
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) 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: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.1
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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,
+  "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": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd3151bb7c7ce1116954ee0374daa59f7805b534e2d75bc0f524c9fd1a5c3a8
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.98,
+    "train_loss": 0.3938806479847109,
+    "train_runtime": 8367.9218,
+    "train_samples_per_second": 0.289,
+    "train_steps_per_second": 0.004
+}

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": 0.98,
+    "train_loss": 0.3938806479847109,
+    "train_runtime": 8367.9218,
+    "train_samples_per_second": 0.289,
+    "train_steps_per_second": 0.004
+}

trainer_log.jsonl

@@ -0,0 +1,8 @@
+{"current_steps": 5, "total_steps": 37, "loss": 1.8153, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001911228490388136, "epoch": 0.13, "percentage": 13.51, "elapsed_time": "0:21:30", "remaining_time": "2:17:40"}
+{"current_steps": 10, "total_steps": 37, "loss": 0.3952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016606747233900815, "epoch": 0.26, "percentage": 27.03, "elapsed_time": "0:43:46", "remaining_time": "1:58:11"}
+{"current_steps": 15, "total_steps": 37, "loss": 0.2029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012928227712765504, "epoch": 0.4, "percentage": 40.54, "elapsed_time": "1:01:48", "remaining_time": "1:30:39"}
+{"current_steps": 20, "total_steps": 37, "loss": 0.1657, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.729821802531212e-05, "epoch": 0.53, "percentage": 54.05, "elapsed_time": "1:18:50", "remaining_time": "1:07:00"}
+{"current_steps": 25, "total_steps": 37, "loss": 0.1042, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.756927164427685e-05, "epoch": 0.66, "percentage": 67.57, "elapsed_time": "1:36:32", "remaining_time": "0:46:20"}
+{"current_steps": 30, "total_steps": 37, "loss": 0.1004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7149035075615794e-05, "epoch": 0.79, "percentage": 81.08, "elapsed_time": "1:53:48", "remaining_time": "0:26:33"}
+{"current_steps": 35, "total_steps": 37, "loss": 0.0942, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4384089652291543e-06, "epoch": 0.93, "percentage": 94.59, "elapsed_time": "2:12:01", "remaining_time": "0:07:32"}
+{"current_steps": 37, "total_steps": 37, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.98, "percentage": 100.0, "elapsed_time": "2:19:27", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9801324503311258,
+  "eval_steps": 500,
+  "global_step": 37,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "grad_norm": 5.132448196411133,
+      "learning_rate": 0.0001911228490388136,
+      "loss": 1.8153,
+      "step": 5
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.215226411819458,
+      "learning_rate": 0.00016606747233900815,
+      "loss": 0.3952,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2212655544281006,
+      "learning_rate": 0.00012928227712765504,
+      "loss": 0.2029,
+      "step": 15
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.6850711107254028,
+      "learning_rate": 8.729821802531212e-05,
+      "loss": 0.1657,
+      "step": 20
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.355529546737671,
+      "learning_rate": 4.756927164427685e-05,
+      "loss": 0.1042,
+      "step": 25
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.9691661596298218,
+      "learning_rate": 1.7149035075615794e-05,
+      "loss": 0.1004,
+      "step": 30
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.6373167037963867,
+      "learning_rate": 1.4384089652291543e-06,
+      "loss": 0.0942,
+      "step": 35
+    },
+    {
+      "epoch": 0.98,
+      "step": 37,
+      "total_flos": 7654509483393024.0,
+      "train_loss": 0.3938806479847109,
+      "train_runtime": 8367.9218,
+      "train_samples_per_second": 0.289,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 37,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 7654509483393024.0,
+  "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 sha256:676e2e32c98aff8e05bed7cbaa5a643536ab49031698861283f6ee682c1fefd0
+size 5048