Model save

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- generator
+model-index:
+- name: Test_with_new_script
+  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. -->
+
+# Test_with_new_script
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0914
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.1117        | 1.0   | 18   | 1.0914          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.15.2

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
     "v_proj",
-    "down_proj",
-    "k_proj",
     "up_proj",
-    "gate_proj"
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a26a3368a121f7215dfdae1e050f70bb5c6055d5f5bb4101120c83132cdf0d
+oid sha256:7a556de130555737da15606adb66dd0e66194f78ed23944c51c1073777131b36
 size 83946192

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.0914130210876465,
+    "eval_runtime": 15.6172,
+    "eval_samples": 124,
+    "eval_samples_per_second": 7.94,
+    "eval_steps_per_second": 0.512,
+    "train_loss": 1.161470651626587,
+    "train_runtime": 443.1723,
+    "train_samples": 1143,
+    "train_samples_per_second": 2.579,
+    "train_steps_per_second": 0.041
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.0914130210876465,
+    "eval_runtime": 15.6172,
+    "eval_samples": 124,
+    "eval_samples_per_second": 7.94,
+    "eval_steps_per_second": 0.512
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.161470651626587,
+    "train_runtime": 443.1723,
+    "train_samples": 1143,
+    "train_samples_per_second": 2.579,
+    "train_steps_per_second": 0.041
+}

trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001,
+      "loss": 1.2833,
+      "step": 1
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018314696123025454,
+      "loss": 1.2373,
+      "step": 5
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0001,
+      "loss": 1.168,
+      "step": 10
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.1117,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0914130210876465,
+      "eval_runtime": 15.7258,
+      "eval_samples_per_second": 7.885,
+      "eval_steps_per_second": 0.509,
+      "step": 18
+    },
+    {
+      "epoch": 1.0,
+      "step": 18,
+      "total_flos": 1.0560439065981747e+17,
+      "train_loss": 1.161470651626587,
+      "train_runtime": 443.1723,
+      "train_samples_per_second": 2.579,
+      "train_steps_per_second": 0.041
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 18,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1.0560439065981747e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e47e387855a76d030702f2871574128825b580847efa35a29d5629c0661791
+oid sha256:4f31dabe80950b12d6098c0f5d3b662eee5c22504bfac428a3670697aac3bdf5
 size 4856