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: llama10p
   results: []
@@ -21,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama10p
 
-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: 1.1320
+- Loss: 1.0923
 
 ## Model description
 
@@ -60,12 +56,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8582        | 1.0   | 406  | 1.1320          |
+| 0.8609        | 1.0   | 406  | 1.0923          |
 
 
 ### 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": [
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_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 sha256:490cfe6483d61b26eab388dacaf988a11fe86a5f103516f63c3eef5eca8122d8
+size 62973728

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
-    "total_flos": 2.0153794240142377e+18,
-    "train_loss": 0.8606077206545862,
-    "train_runtime": 31606.2831,
+    "total_flos": 2.0153806840502682e+18,
+    "train_loss": 0.012793793173259115,
+    "train_runtime": 598.372,
     "train_samples": 103932,
-    "train_samples_per_second": 3.288,
-    "train_steps_per_second": 0.013
+    "train_samples_per_second": 173.691,
+    "train_steps_per_second": 0.679
 }

runs/Jun05_18-54-33_COE-CS-sv003/events.out.tfevents.1717613738.COE-CS-sv003.61918.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb6f643cdba833d5b3650342d221ee9d2e993bf87deeee4bb14993791712b3d
+size 5052

runs/Jun05_19-25-05_COE-CS-sv003/events.out.tfevents.1717615567.COE-CS-sv003.65372.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c419c2060fc56d7965342f05f0e9e36b2034cd7647d9bed40e6ba70bbaea266
+size 5888

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": 2.0153794240142377e+18,
-    "train_loss": 0.8606077206545862,
-    "train_runtime": 31606.2831,
+    "total_flos": 2.0153806840502682e+18,
+    "train_loss": 0.012793793173259115,
+    "train_runtime": 598.372,
     "train_samples": 103932,
-    "train_samples_per_second": 3.288,
-    "train_steps_per_second": 0.013
+    "train_samples_per_second": 173.691,
+    "train_steps_per_second": 0.679
 }

trainer_state.json

@@ -577,27 +577,27 @@
     },
     {
       "epoch": 0.9975369458128078,
-      "grad_norm": 0.07590048760175705,
+      "grad_norm": 0.08985913544893265,
       "learning_rate": 3.7040883734462683e-09,
-      "loss": 0.8582,
+      "loss": 0.8609,
       "step": 405
     },
     {
       "epoch": 1.0,
-      "eval_loss": 1.1319997310638428,
-      "eval_runtime": 131.0398,
-      "eval_samples_per_second": 8.814,
-      "eval_steps_per_second": 0.557,
+      "eval_loss": 1.0922821760177612,
+      "eval_runtime": 133.4455,
+      "eval_samples_per_second": 8.655,
+      "eval_steps_per_second": 0.547,
       "step": 406
     },
     {
       "epoch": 1.0,
       "step": 406,
-      "total_flos": 2.0153794240142377e+18,
-      "train_loss": 0.8606077206545862,
-      "train_runtime": 31606.2831,
-      "train_samples_per_second": 3.288,
-      "train_steps_per_second": 0.013
+      "total_flos": 2.0153806840502682e+18,
+      "train_loss": 0.012793793173259115,
+      "train_runtime": 598.372,
+      "train_samples_per_second": 173.691,
+      "train_steps_per_second": 0.679
     }
   ],
   "logging_steps": 5,
@@ -617,7 +617,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0153794240142377e+18,
+  "total_flos": 2.0153806840502682e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc79e9c0ba070af738ce753f31c7b99dc8029f8556d41c3b1f586c5bd22c9eab
+oid sha256:721540601195dc2734d399d00b884d12c57457209221430da06e9a4110647d74
 size 5240