Training in progress, step 500

README.md

@@ -0,0 +1,54 @@
+---
+license: llama2
+base_model: lmsys/vicuna-7b-v1.5
+tags:
+- generated_from_trainer
+model-index:
+- name: race_cot_256
+  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. -->
+
+# race_cot_256
+
+This model is a fine-tuned version of [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) on an unknown 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.13.1
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6104a5eedf9fd5d713937905694795b6c14acfe3042afbaf63973f7edeb8ac
+size 160069834

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08745ced9ab4d73d1082bdba038ad3d3b33008489bb604b61983fe38c8cafcef
+size 159967880

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.2506813730156864,
+    "train_runtime": 2949.4195,
+    "train_samples_per_second": 1.736,
+    "train_steps_per_second": 0.434
+}

args.txt

@@ -0,0 +1,14 @@
+base_model_name: lmsys/vicuna-7b-v1.5
+batch_size: 4
+cot: true
+dataset_name: BENBENBENb/RACE1000COT
+epochs: 20
+eval_strategy: epoch
+evaluation: false
+learning_rate: 0.0001
+logging_steps: 1
+output_dir: brettbbb/race_cot_256
+seed: 42
+skip_example: true
+train_size: 256
+warmup_steps: 5

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.2506813730156864,
+    "train_runtime": 2949.4195,
+    "train_samples_per_second": 1.736,
+    "train_steps_per_second": 0.434
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac6a540939444bbc3b1c9ba5c47ae452c946c7c317baab3d25d368e609b1116
+size 4600