Model save

README.md

@@ -1,16 +1,12 @@
 ---
 license: apache-2.0
-base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
-datasets:
-- HuggingFaceH4/ultrachat_200k
+base_model: mistralai/Mistral-7B-v0.1
 model-index:
 - name: mistral10p
   results: []
@@ -21,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral10p
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 
@@ -60,12 +56,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.7408        | 1.0   | 406  | nan             |
+| 0.7407        | 1.0   | 406  | nan             |
 
 
 ### Framework versions
 
+- PEFT 0.11.1
 - Transformers 4.41.1
 - Pytorch 2.2.2+cu121
 - Datasets 2.19.1
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-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": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 6,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "down_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:da997482022f77257f714a5b4ee4fd8bd82f27c8741c9a176cf00a498373f762
+size 62973728

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 2.1311021010303058e+18,
-    "train_loss": 0.5565521074046055,
-    "train_runtime": 51643.2656,
+    "train_loss": 0.011041376391067882,
+    "train_runtime": 1933.8682,
     "train_samples": 103932,
-    "train_samples_per_second": 2.012,
-    "train_steps_per_second": 0.008
+    "train_samples_per_second": 53.743,
+    "train_steps_per_second": 0.21
 }

runs/Jun05_02-54-31_ip-172-31-69-60.ec2.internal/events.out.tfevents.1717556207.ip-172-31-69-60.ec2.internal.12886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d5c27fc6080db884f2b04f662e0f2ac08a93fe90a907158ee4c542650dc66c
+size 5929

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 2.1311021010303058e+18,
-    "train_loss": 0.5565521074046055,
-    "train_runtime": 51643.2656,
+    "train_loss": 0.011041376391067882,
+    "train_runtime": 1933.8682,
     "train_samples": 103932,
-    "train_samples_per_second": 2.012,
-    "train_steps_per_second": 0.008
+    "train_samples_per_second": 53.743,
+    "train_steps_per_second": 0.21
 }

trainer_state.json

@@ -577,27 +577,27 @@
     },
     {
       "epoch": 0.9975369458128078,
-      "grad_norm": 0.09673314541578293,
+      "grad_norm": 0.09686147421598434,
       "learning_rate": 3.7040883734462683e-09,
-      "loss": 0.7408,
+      "loss": 0.7407,
       "step": 405
     },
     {
       "epoch": 1.0,
       "eval_loss": NaN,
-      "eval_runtime": 943.1531,
-      "eval_samples_per_second": 1.225,
-      "eval_steps_per_second": 0.306,
+      "eval_runtime": 938.2112,
+      "eval_samples_per_second": 1.231,
+      "eval_steps_per_second": 0.308,
       "step": 406
     },
     {
       "epoch": 1.0,
       "step": 406,
       "total_flos": 2.1311021010303058e+18,
-      "train_loss": 0.5565521074046055,
-      "train_runtime": 51643.2656,
-      "train_samples_per_second": 2.012,
-      "train_steps_per_second": 0.008
+      "train_loss": 0.011041376391067882,
+      "train_runtime": 1933.8682,
+      "train_samples_per_second": 53.743,
+      "train_steps_per_second": 0.21
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f53ee518de97b89137557250c893b2d6e808559462ee5b243ed9ee3e21a591
+oid sha256:648d63baf672a6f17623644c56c33c8048f3d70cb555378b7bed7d94a948d830
 size 5304