End of training

README.md

@@ -0,0 +1,56 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: yuiseki/karasu-aya-ja-v0.1
+model-index:
+- name: karasu-aya-ft-onlyqa-adapter
+  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. -->
+
+# karasu-aya-ft-onlyqa-adapter
+
+This model is a fine-tuned version of [yuiseki/karasu-aya-ja-v0.1](https://huggingface.co/yuiseki/karasu-aya-ja-v0.1) on the None 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0
+- 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": "yuiseki/karasu-aya-ja-v0.1",
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "mlp.gate_proj",
+    "self_attn.v_proj",
+    "mlp.up_proj",
+    "mlp.down_proj",
+    "self_attn.k_proj",
+    "self_attn.q_proj",
+    "self_attn.o_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 sha256:1763fa29d3aaed609a9761ccc62f3364e46082179eaf8a864774c41c2931a896
+size 100966336

trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9911504424778761,
+  "eval_steps": 500,
+  "global_step": 56,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08849557522123894,
+      "grad_norm": 0.6312227845191956,
+      "learning_rate": 0.0001,
+      "loss": 1.6685,
+      "step": 5
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 0.35548320412635803,
+      "learning_rate": 9.019607843137255e-05,
+      "loss": 1.4885,
+      "step": 10
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "grad_norm": 0.612781286239624,
+      "learning_rate": 8.039215686274511e-05,
+      "loss": 1.3795,
+      "step": 15
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 0.7122682929039001,
+      "learning_rate": 7.058823529411765e-05,
+      "loss": 1.2164,
+      "step": 20
+    },
+    {
+      "epoch": 0.4424778761061947,
+      "grad_norm": 0.6391258835792542,
+      "learning_rate": 6.078431372549019e-05,
+      "loss": 0.9956,
+      "step": 25
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 0.4501003324985504,
+      "learning_rate": 5.0980392156862745e-05,
+      "loss": 1.0388,
+      "step": 30
+    },
+    {
+      "epoch": 0.6194690265486725,
+      "grad_norm": 0.35456234216690063,
+      "learning_rate": 4.11764705882353e-05,
+      "loss": 1.014,
+      "step": 35
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 0.4066126048564911,
+      "learning_rate": 3.137254901960784e-05,
+      "loss": 0.9312,
+      "step": 40
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "grad_norm": 0.4473574161529541,
+      "learning_rate": 2.1568627450980395e-05,
+      "loss": 0.8882,
+      "step": 45
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "grad_norm": 0.42478886246681213,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.9296,
+      "step": 50
+    },
+    {
+      "epoch": 0.9734513274336283,
+      "grad_norm": 0.493737131357193,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 0.8824,
+      "step": 55
+    },
+    {
+      "epoch": 0.9911504424778761,
+      "step": 56,
+      "total_flos": 214057638850560.0,
+      "train_loss": 1.126003892293998,
+      "train_runtime": 11094.3613,
+      "train_samples_per_second": 0.01,
+      "train_steps_per_second": 0.005
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 56,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 214057638850560.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ae0f9527e3c5c8681cbfa53a8155a7dfb4ab093deede0e22c7b0c8ffe7e893
+size 5112