Model save

README.md

@@ -0,0 +1,64 @@
+---
+license: other
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: 01-ai/Yi-6B
+model-index:
+- name: Yi-6B-ruozhiba4
+  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. -->
+
+# Yi-6B-ruozhiba4
+
+This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1112
+
+## 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: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.1871        | 1.0   | 20   | 2.1112          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.2.2+cu118
+- Datasets 2.14.6
+- Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aee20f68fb1a791e8f56b48918196f6f3b23fe1b439af56a6e7bcf886723e05
+oid sha256:7db5f2c4c425096f707888dcaf5b7b8da69c7ac271fe0f8c250879beeed8a5ef
 size 72673912

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.1112499237060547,
+    "eval_runtime": 6.0983,
+    "eval_samples": 240,
+    "eval_samples_per_second": 3.28,
+    "eval_steps_per_second": 3.28,
+    "train_loss": 2.172952950000763,
+    "train_runtime": 88.3266,
+    "train_samples": 240,
+    "train_samples_per_second": 0.226,
+    "train_steps_per_second": 0.226
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.1112499237060547,
+    "eval_runtime": 6.0983,
+    "eval_samples": 240,
+    "eval_samples_per_second": 3.28,
+    "eval_steps_per_second": 3.28
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 2.172952950000763,
+    "train_runtime": 88.3266,
+    "train_samples": 240,
+    "train_samples_per_second": 0.226,
+    "train_steps_per_second": 0.226
+}

trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 5e-05,
+      "loss": 2.1566,
+      "step": 1
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 2.2434,
+      "step": 5
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.0993,
+      "step": 10
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.1794,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 2.1871,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.1112499237060547,
+      "eval_runtime": 6.1153,
+      "eval_samples_per_second": 3.27,
+      "eval_steps_per_second": 3.27,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "step": 20,
+      "total_flos": 1434058374512640.0,
+      "train_loss": 2.172952950000763,
+      "train_runtime": 88.3266,
+      "train_samples_per_second": 0.226,
+      "train_steps_per_second": 0.226
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1,
+  "total_flos": 1434058374512640.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}