Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: MediaTek-Research/Breeze-7B-Instruct-v1_0
+model-index:
+- name: train_2024-05-03-06-11-08
+  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_2024-05-03-06-11-08
+
+This model is a fine-tuned version of [MediaTek-Research/Breeze-7B-Instruct-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0) 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: 5e-05
+- 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 0.10.0
+- Transformers 4.41.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "MediaTek-Research/Breeze-7B-Instruct-v1_0",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "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": [
+    "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 sha256:6e2fbfb2fb610baa2d235961b84c091ff83f84ac86d44ea50e6f345eea4ce2ef
+size 13648432

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<EOD>": 61873,
+  "<PAD>": 61874
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9536423841059603,
+    "train_loss": 0.8629565901226468,
+    "train_runtime": 640.3959,
+    "train_samples_per_second": 3.771,
+    "train_steps_per_second": 0.028
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:9298e56c094f0d30431b0e52ad53287f0cadc99ac8ca17cc2144b0eb4753f130
+size 911034

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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
+    },
+    "61873": {
+      "content": "<EOD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61874": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% set system_message = 'You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<s>' + system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + ' [/INST] ' }}{% elif message['role'] == 'assistant' %}{{ content }}{% 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,
+  "use_fast": true
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9536423841059603,
+    "train_loss": 0.8629565901226468,
+    "train_runtime": 640.3959,
+    "train_samples_per_second": 3.771,
+    "train_steps_per_second": 0.028
+}

trainer_log.jsonl

@@ -0,0 +1,4 @@
+{"current_steps": 5, "total_steps": 18, "loss": 1.2805, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.1069690242163484e-05, "epoch": 0.26490066225165565, "percentage": 27.78, "elapsed_time": "0:02:56", "remaining_time": "0:07:38"}
+{"current_steps": 10, "total_steps": 18, "loss": 0.8658, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.0658795558326743e-05, "epoch": 0.5298013245033113, "percentage": 55.56, "elapsed_time": "0:05:52", "remaining_time": "0:04:41"}
+{"current_steps": 15, "total_steps": 18, "loss": 0.6177, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.3493649053890326e-06, "epoch": 0.7947019867549668, "percentage": 83.33, "elapsed_time": "0:08:50", "remaining_time": "0:01:46"}
+{"current_steps": 18, "total_steps": 18, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.9536423841059603, "percentage": 100.0, "elapsed_time": "0:10:40", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "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": 0.26490066225165565,
+      "grad_norm": 4.038422107696533,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 1.2805,
+      "step": 5
+    },
+    {
+      "epoch": 0.5298013245033113,
+      "grad_norm": 4.315277576446533,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.8658,
+      "step": 10
+    },
+    {
+      "epoch": 0.7947019867549668,
+      "grad_norm": 4.228354454040527,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.6177,
+      "step": 15
+    },
+    {
+      "epoch": 0.9536423841059603,
+      "step": 18,
+      "total_flos": 1.039869065822208e+16,
+      "train_loss": 0.8629565901226468,
+      "train_runtime": 640.3959,
+      "train_samples_per_second": 3.771,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 18,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.039869065822208e+16,
+  "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:ea7c932516ca79a8d77640ac79deba41fd4efd5f54cc9e369f4472b5ca883493
+size 5304