End of training

README.md

@@ -1,3 +1,56 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: aipib/llmjp-dareties
+model-index:
+- name: llmjp-dareties-ft-llmhuman-input-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. -->
+
+# llmjp-dareties-ft-llmhuman-input-adapter
+
+This model is a fine-tuned version of [aipib/llmjp-dareties](https://huggingface.co/aipib/llmjp-dareties) 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: 4
+- total_train_batch_size: 4
+- 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 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "aipib/llmjp-dareties",
+  "bias": "none",
+  "fan_in_fan_out": true,
+  "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": [
+    "c_fc",
+    "c_attn",
+    "wte",
+    "c_proj",
+    "wpe"
+  ],
+  "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 sha256:5480313e9356c3087168a054259991ffbf9ad421199500c43c79e344372781fb
+size 107963160

trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.98989898989899,
+  "eval_steps": 500,
+  "global_step": 49,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10101010101010101,
+      "grad_norm": 13.222509384155273,
+      "learning_rate": 0.0001,
+      "loss": 2.833,
+      "step": 5
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 7.568332195281982,
+      "learning_rate": 8.863636363636364e-05,
+      "loss": 2.3982,
+      "step": 10
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 7.395251750946045,
+      "learning_rate": 7.727272727272727e-05,
+      "loss": 1.9974,
+      "step": 15
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 6.726298809051514,
+      "learning_rate": 6.59090909090909e-05,
+      "loss": 1.8703,
+      "step": 20
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 5.273419380187988,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 1.4627,
+      "step": 25
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 5.722088813781738,
+      "learning_rate": 4.318181818181819e-05,
+      "loss": 1.48,
+      "step": 30
+    },
+    {
+      "epoch": 0.7070707070707071,
+      "grad_norm": 7.1894941329956055,
+      "learning_rate": 3.181818181818182e-05,
+      "loss": 1.3753,
+      "step": 35
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 5.0429863929748535,
+      "learning_rate": 2.0454545454545457e-05,
+      "loss": 1.2283,
+      "step": 40
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 19.73174476623535,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.2801,
+      "step": 45
+    },
+    {
+      "epoch": 0.98989898989899,
+      "step": 49,
+      "total_flos": 229900744138752.0,
+      "train_loss": 1.73281158719744,
+      "train_runtime": 13563.9029,
+      "train_samples_per_second": 0.015,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 49,
+  "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": 229900744138752.0,
+  "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:a57c17ec9e9ffbf58ab8ef2da43bf35a1e39b1bce15b1547ed1d40aec254966f
+size 5112