Model save

README.md

@@ -1,16 +1,12 @@
 ---
 license: llama3
-base_model: meta-llama/Meta-Llama-3-8B
+library_name: peft
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
-datasets:
-- HuggingFaceH4/ultrachat_200k
+base_model: meta-llama/Meta-Llama-3-8B
 model-index:
 - name: llama10pEnt
   results: []
@@ -21,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama10pEnt
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the HuggingFaceH4/ultrachat_200k dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0897
+- Loss: 1.0895
 
 ## Model description
 
@@ -60,12 +56,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8582        | 1.0   | 406  | 1.0897          |
+| 0.8582        | 1.0   | 406  | 1.0895          |
 
 
 ### Framework versions
 
+- PEFT 0.11.1
 - Transformers 4.41.1
 - Pytorch 2.3.0+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": "meta-llama/Meta-Llama-3-8B",
+  "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": [
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_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 sha256:7acbab6581a9ddc6dd6da29414e106053902c05b3c14074b2c409ac01dd91bac
+size 62973728

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 2.015525816363909e+18,
-    "train_loss": 0.8602962029978559,
-    "train_runtime": 31829.4895,
+    "train_loss": 0.012751721396234822,
+    "train_runtime": 598.1972,
     "train_samples": 103932,
-    "train_samples_per_second": 3.265,
-    "train_steps_per_second": 0.013
+    "train_samples_per_second": 173.742,
+    "train_steps_per_second": 0.679
 }

runs/Jun05_19-59-37_COE-CS-sv003/events.out.tfevents.1717617638.COE-CS-sv003.69923.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30cbd5f48b1a55b44dd30a04ab6ea42879a2a837e10746ab9656ea0985bb27e6
+size 5900

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 2048,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 2.015525816363909e+18,
-    "train_loss": 0.8602962029978559,
-    "train_runtime": 31829.4895,
+    "train_loss": 0.012751721396234822,
+    "train_runtime": 598.1972,
     "train_samples": 103932,
-    "train_samples_per_second": 3.265,
-    "train_steps_per_second": 0.013
+    "train_samples_per_second": 173.742,
+    "train_steps_per_second": 0.679
 }

trainer_state.json

@@ -577,27 +577,27 @@
     },
     {
       "epoch": 0.9975369458128078,
-      "grad_norm": 0.07639329135417938,
+      "grad_norm": 0.07533330470323563,
       "learning_rate": 3.7040883734462683e-09,
       "loss": 0.8582,
       "step": 405
     },
     {
       "epoch": 1.0,
-      "eval_loss": 1.089674472808838,
-      "eval_runtime": 131.6876,
-      "eval_samples_per_second": 8.771,
-      "eval_steps_per_second": 0.554,
+      "eval_loss": 1.0895307064056396,
+      "eval_runtime": 133.3674,
+      "eval_samples_per_second": 8.66,
+      "eval_steps_per_second": 0.547,
       "step": 406
     },
     {
       "epoch": 1.0,
       "step": 406,
       "total_flos": 2.015525816363909e+18,
-      "train_loss": 0.8602962029978559,
-      "train_runtime": 31829.4895,
-      "train_samples_per_second": 3.265,
-      "train_steps_per_second": 0.013
+      "train_loss": 0.012751721396234822,
+      "train_runtime": 598.1972,
+      "train_samples_per_second": 173.742,
+      "train_steps_per_second": 0.679
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09ebbc2d48b079454c2506700c63033390944d223589962179ba6bec35d016f
+oid sha256:3a8b11ccb5175b43d374ba1db305346cb2e61b8b1655976aafb6f471913ad96b
 size 5240