Model save

README.md

@@ -3,12 +3,9 @@ library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-14B-Instruct
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: Qwen2.5-14B-Instruct-star-nl-3Rounds-iter-1

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.851063829787234,
     "total_flos": 1.70668694534357e+17,
-    "train_loss": 0.559986629486084,
-    "train_runtime": 582.7329,
+    "train_loss": 0.5626590156555176,
+    "train_runtime": 583.7651,
     "train_samples": 748,
-    "train_samples_per_second": 6.418,
+    "train_samples_per_second": 6.407,
     "train_steps_per_second": 0.043
 }

config.json

@@ -24,7 +24,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.47.1",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151665
 }

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:413386ad6d055588b7f28aa5d00caf27c8cab2cb680c415ceb0578149f5c207f
+oid sha256:f8f9b5f88c1f454895e784effe9555c4c158670f4a73ae5a4c19b06f1e384898
 size 4982125520

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b430d2faacc0f0829c7859fd238f3ee1eeca1c8aea03acaf7e3540983c60978e
+oid sha256:02e121ba84cccfb0893309ef0758528aea8ee01c8e16b6b7c880032e9e3483bd
 size 4954847344

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2454ceaf7475b5330ad7395f57b3b3abbb042825805b14cce721e9609351ed8
+oid sha256:ac9f0ac0b86364b586ee0ba230934f5c9f9bb9c0b2db421d372660cbdb264479
 size 4954847392

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:739e9308f48a30826132cdc00887b8152b183679bd4d3a7c9f03e9baf91f603d
+oid sha256:9c3516a4d0acf96e36897aac6f4fa094cbcb6f5d18cdd01be133e8488d8d2cc2
 size 4954847392

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f42f36be99b518998681df94d7de2270d3bcf9525d3c1a1d6061a5517092463
+oid sha256:bb0c7b2071a3a2aff92ed9b7ed5d466b690c51e26669cdcf98042c43ba4add3f
 size 4954847392

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc45cd8dad35a0985906c9a25441e8932f8ace0b504752081a21699d9006db2
+oid sha256:2e89bae0f8f908685e0c8e831adef7608c22829ebadc5685c1650bff420cebe6
 size 4730447400

runs/Feb26_04-46-39_a100-80-8-zifeng-1/events.out.tfevents.1740545225.a100-80-8-zifeng-1.97947.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35e3292972c92f61ae4e41f6fa035cce996401791fd9a4aeeb081c6749d9c20
+size 7282

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.851063829787234,
     "total_flos": 1.70668694534357e+17,
-    "train_loss": 0.559986629486084,
-    "train_runtime": 582.7329,
+    "train_loss": 0.5626590156555176,
+    "train_runtime": 583.7651,
     "train_samples": 748,
-    "train_samples_per_second": 6.418,
+    "train_samples_per_second": 6.407,
     "train_steps_per_second": 0.043
 }

trainer_state.json

@@ -10,53 +10,53 @@
   "log_history": [
     {
       "epoch": 0.1702127659574468,
-      "grad_norm": 1.0480686423347865,
+      "grad_norm": 1.0480449041222901,
       "learning_rate": 4.980286753286196e-06,
       "loss": 1.1367,
       "step": 1
     },
     {
       "epoch": 0.851063829787234,
-      "grad_norm": 0.7371347999735538,
+      "grad_norm": 0.7218518716452021,
       "learning_rate": 4.522542485937369e-06,
-      "loss": 0.7211,
+      "loss": 0.7212,
       "step": 5
     },
     {
       "epoch": 1.851063829787234,
-      "grad_norm": 0.1221598511317441,
+      "grad_norm": 0.48974754683120497,
       "learning_rate": 3.272542485937369e-06,
-      "loss": 0.5451,
+      "loss": 0.5486,
       "step": 10
     },
     {
       "epoch": 2.851063829787234,
-      "grad_norm": 0.06221615866869028,
+      "grad_norm": 0.05989476827451271,
       "learning_rate": 1.7274575140626318e-06,
-      "loss": 0.4954,
+      "loss": 0.4988,
       "step": 15
     },
     {
       "epoch": 3.851063829787234,
-      "grad_norm": 0.04156397934867294,
+      "grad_norm": 0.04162142765751137,
       "learning_rate": 4.774575140626317e-07,
-      "loss": 0.478,
+      "loss": 0.4812,
       "step": 20
     },
     {
       "epoch": 4.851063829787234,
-      "grad_norm": 0.036582860908155705,
+      "grad_norm": 0.03625801845951793,
       "learning_rate": 0.0,
-      "loss": 0.4771,
+      "loss": 0.4803,
       "step": 25
     },
     {
       "epoch": 4.851063829787234,
       "step": 25,
       "total_flos": 1.70668694534357e+17,
-      "train_loss": 0.559986629486084,
-      "train_runtime": 582.7329,
-      "train_samples_per_second": 6.418,
+      "train_loss": 0.5626590156555176,
+      "train_runtime": 583.7651,
+      "train_samples_per_second": 6.407,
       "train_steps_per_second": 0.043
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b6cd22decd9ce87a02de6508d2ec702205300998b0483fdaf10bcd09a40928d
+oid sha256:b82e3f589ead1fa3980b186350331e33ac1776d442bae40f34a7a0036f1a1f7d
 size 7096