local_model_directory

README.md

@@ -0,0 +1,72 @@
+---
+base_model: scb10x/typhoon-7b
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: local_model_directory
+  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. -->
+
+# local_model_directory
+
+This model is a fine-tuned version of [scb10x/typhoon-7b](https://huggingface.co/scb10x/typhoon-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4505
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 5.0407        | 0.9524 | 5    | 4.8168          |
+| 3.5268        | 1.9048 | 10   | 2.1234          |
+| 1.9397        | 2.8571 | 15   | 1.2800          |
+| 1.0223        | 4.0    | 21   | 0.7717          |
+| 0.8135        | 4.9524 | 26   | 0.5757          |
+| 0.6574        | 5.9048 | 31   | 0.5178          |
+| 0.5833        | 6.8571 | 36   | 0.4854          |
+| 0.4549        | 8.0    | 42   | 0.4494          |
+| 0.5012        | 8.9524 | 47   | 0.4294          |
+| 0.514         | 9.9048 | 52   | 0.4505          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.42.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "scb10x/typhoon-7b",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_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:d6d4599048c51779fc5a921ee791b149c963880a71b0e8782553e905fa61c5c4
+size 83945296

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_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": 0.42944997549057007,
+  "best_model_checkpoint": "local_model_directory/checkpoint-47",
+  "epoch": 9.904761904761905,
+  "eval_steps": 500,
+  "global_step": 52,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 5.0407,
+      "step": 5
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "eval_loss": 4.816819190979004,
+      "eval_runtime": 4.4668,
+      "eval_samples_per_second": 37.61,
+      "eval_steps_per_second": 4.701,
+      "step": 5
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 8.692849159240723,
+      "learning_rate": 0.00019839357429718877,
+      "loss": 3.5268,
+      "step": 10
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "eval_loss": 2.1233882904052734,
+      "eval_runtime": 4.4662,
+      "eval_samples_per_second": 37.616,
+      "eval_steps_per_second": 4.702,
+      "step": 10
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 7.133273601531982,
+      "learning_rate": 0.0001963855421686747,
+      "loss": 1.9397,
+      "step": 15
+    },
+    {
+      "epoch": 2.857142857142857,
+      "eval_loss": 1.2800443172454834,
+      "eval_runtime": 4.4631,
+      "eval_samples_per_second": 37.642,
+      "eval_steps_per_second": 4.705,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.404087066650391,
+      "learning_rate": 0.00019397590361445782,
+      "loss": 1.0223,
+      "step": 21
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7716784477233887,
+      "eval_runtime": 4.4654,
+      "eval_samples_per_second": 37.622,
+      "eval_steps_per_second": 4.703,
+      "step": 21
+    },
+    {
+      "epoch": 4.9523809523809526,
+      "grad_norm": 8.276748657226562,
+      "learning_rate": 0.00019196787148594377,
+      "loss": 0.8135,
+      "step": 26
+    },
+    {
+      "epoch": 4.9523809523809526,
+      "eval_loss": 0.5757163763046265,
+      "eval_runtime": 4.4645,
+      "eval_samples_per_second": 37.63,
+      "eval_steps_per_second": 4.704,
+      "step": 26
+    },
+    {
+      "epoch": 5.904761904761905,
+      "grad_norm": 3.8597450256347656,
+      "learning_rate": 0.00018995983935742974,
+      "loss": 0.6574,
+      "step": 31
+    },
+    {
+      "epoch": 5.904761904761905,
+      "eval_loss": 0.5177809596061707,
+      "eval_runtime": 4.4665,
+      "eval_samples_per_second": 37.613,
+      "eval_steps_per_second": 4.702,
+      "step": 31
+    },
+    {
+      "epoch": 6.857142857142857,
+      "grad_norm": 4.316291332244873,
+      "learning_rate": 0.00018795180722891569,
+      "loss": 0.5833,
+      "step": 36
+    },
+    {
+      "epoch": 6.857142857142857,
+      "eval_loss": 0.4853830933570862,
+      "eval_runtime": 4.465,
+      "eval_samples_per_second": 37.626,
+      "eval_steps_per_second": 4.703,
+      "step": 36
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.386613607406616,
+      "learning_rate": 0.0001855421686746988,
+      "loss": 0.4549,
+      "step": 42
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.4494071304798126,
+      "eval_runtime": 4.4635,
+      "eval_samples_per_second": 37.638,
+      "eval_steps_per_second": 4.705,
+      "step": 42
+    },
+    {
+      "epoch": 8.952380952380953,
+      "grad_norm": 2.4768359661102295,
+      "learning_rate": 0.00018353413654618474,
+      "loss": 0.5012,
+      "step": 47
+    },
+    {
+      "epoch": 8.952380952380953,
+      "eval_loss": 0.42944997549057007,
+      "eval_runtime": 4.465,
+      "eval_samples_per_second": 37.626,
+      "eval_steps_per_second": 4.703,
+      "step": 47
+    },
+    {
+      "epoch": 9.904761904761905,
+      "grad_norm": 3.0964863300323486,
+      "learning_rate": 0.0001815261044176707,
+      "loss": 0.514,
+      "step": 52
+    },
+    {
+      "epoch": 9.904761904761905,
+      "eval_loss": 0.45047804713249207,
+      "eval_runtime": 4.4637,
+      "eval_samples_per_second": 37.637,
+      "eval_steps_per_second": 4.705,
+      "step": 52
+    },
+    {
+      "epoch": 9.904761904761905,
+      "step": 52,
+      "total_flos": 1735676016721920.0,
+      "train_loss": 1.4758788301394536,
+      "train_runtime": 173.2572,
+      "train_samples_per_second": 96.966,
+      "train_steps_per_second": 2.886
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.1
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1735676016721920.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e45e1106a4d07081a7fe4603a0e418c4422a7a2d94da7a304427f1c7e425d6fb
+size 5112