Training in progress, step 2862

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9ff50c9e5f7dbdfafe4634702c271461312412ada297046b7621f2bf299e45
+oid sha256:755d6f33a68d74c3413fc4bbba4ca89a5d3159e69fde0fa3e01444213d2c014a
 size 268290900

run-0/checkpoint-2862/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f98f65f6f4d59b5136dafc34c275d1e1ff53fbebfeb846d7b829da4b5a5935f
+oid sha256:755d6f33a68d74c3413fc4bbba4ca89a5d3159e69fde0fa3e01444213d2c014a
 size 268290900

run-0/checkpoint-2862/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:077b54b56463721081bbcefac5c215f973b3e567e91af28295deb5de5dfe7b8b
+oid sha256:8284814110bf9706bdb36829746349a1e012f87f90cd24e84e24ee54d061514d
 size 536643898

run-0/checkpoint-2862/trainer_state.json

@@ -10,109 +10,109 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5767741935483871,
-      "eval_loss": 0.18995507061481476,
-      "eval_runtime": 5.3293,
-      "eval_samples_per_second": 581.689,
-      "eval_steps_per_second": 12.197,
+      "eval_accuracy": 0.5887096774193549,
+      "eval_loss": 0.19886387884616852,
+      "eval_runtime": 5.1732,
+      "eval_samples_per_second": 599.241,
+      "eval_steps_per_second": 12.565,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.5155988335609436,
+      "grad_norm": 0.5294517874717712,
       "learning_rate": 1.650593990216632e-05,
-      "loss": 0.3062,
+      "loss": 0.3203,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8174193548387096,
-      "eval_loss": 0.09330115467309952,
-      "eval_runtime": 5.6232,
-      "eval_samples_per_second": 551.287,
-      "eval_steps_per_second": 11.559,
+      "eval_accuracy": 0.8193548387096774,
+      "eval_loss": 0.09618715196847916,
+      "eval_runtime": 5.2244,
+      "eval_samples_per_second": 593.365,
+      "eval_steps_per_second": 12.442,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8764516129032258,
-      "eval_loss": 0.06318038702011108,
-      "eval_runtime": 5.4039,
-      "eval_samples_per_second": 573.66,
-      "eval_steps_per_second": 12.028,
+      "eval_accuracy": 0.8783870967741936,
+      "eval_loss": 0.06421981006860733,
+      "eval_runtime": 5.1205,
+      "eval_samples_per_second": 605.405,
+      "eval_steps_per_second": 12.694,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.42988139390945435,
+      "grad_norm": 0.44660821557044983,
       "learning_rate": 1.3011879804332637e-05,
-      "loss": 0.108,
+      "loss": 0.1116,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8990322580645161,
-      "eval_loss": 0.04927925392985344,
-      "eval_runtime": 5.4126,
-      "eval_samples_per_second": 572.741,
-      "eval_steps_per_second": 12.009,
+      "eval_accuracy": 0.8996774193548387,
+      "eval_loss": 0.04962550476193428,
+      "eval_runtime": 5.0817,
+      "eval_samples_per_second": 610.038,
+      "eval_steps_per_second": 12.791,
       "step": 1272
     },
     {
       "epoch": 4.716981132075472,
-      "grad_norm": 0.297043114900589,
+      "grad_norm": 0.3033629357814789,
       "learning_rate": 9.517819706498952e-06,
-      "loss": 0.0699,
+      "loss": 0.0713,
       "step": 1500
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9074193548387097,
-      "eval_loss": 0.040702205151319504,
-      "eval_runtime": 5.5616,
-      "eval_samples_per_second": 557.389,
-      "eval_steps_per_second": 11.687,
+      "eval_accuracy": 0.9080645161290323,
+      "eval_loss": 0.040737707167863846,
+      "eval_runtime": 5.3814,
+      "eval_samples_per_second": 576.062,
+      "eval_steps_per_second": 12.079,
       "step": 1590
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9103225806451613,
-      "eval_loss": 0.035840049386024475,
-      "eval_runtime": 5.3906,
-      "eval_samples_per_second": 575.073,
-      "eval_steps_per_second": 12.058,
+      "eval_accuracy": 0.9116129032258065,
+      "eval_loss": 0.0357489213347435,
+      "eval_runtime": 5.0778,
+      "eval_samples_per_second": 610.498,
+      "eval_steps_per_second": 12.801,
       "step": 1908
     },
     {
       "epoch": 6.289308176100629,
-      "grad_norm": 0.26027998328208923,
+      "grad_norm": 0.26608094573020935,
       "learning_rate": 6.02375960866527e-06,
-      "loss": 0.0552,
+      "loss": 0.0561,
       "step": 2000
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.917741935483871,
-      "eval_loss": 0.03322926536202431,
-      "eval_runtime": 5.4915,
-      "eval_samples_per_second": 564.507,
-      "eval_steps_per_second": 11.836,
+      "eval_accuracy": 0.9187096774193548,
+      "eval_loss": 0.03307666257023811,
+      "eval_runtime": 5.171,
+      "eval_samples_per_second": 599.502,
+      "eval_steps_per_second": 12.57,
       "step": 2226
     },
     {
       "epoch": 7.861635220125786,
-      "grad_norm": 0.2637036442756653,
+      "grad_norm": 0.27350321412086487,
       "learning_rate": 2.5296995108315863e-06,
-      "loss": 0.0486,
+      "loss": 0.0492,
       "step": 2500
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.9203225806451613,
-      "eval_loss": 0.03138649836182594,
-      "eval_runtime": 5.5051,
-      "eval_samples_per_second": 563.117,
-      "eval_steps_per_second": 11.807,
+      "eval_accuracy": 0.9241935483870968,
+      "eval_loss": 0.031220456585288048,
+      "eval_runtime": 5.1775,
+      "eval_samples_per_second": 598.747,
+      "eval_steps_per_second": 12.554,
       "step": 2544
     }
   ],
@@ -133,12 +133,12 @@
       "attributes": {}
     }
   },
-  "total_flos": 651155886807636.0,
+  "total_flos": 760794662700744.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.39616967623231003,
+    "alpha": 0.260556849082234,
     "num_train_epochs": 9,
-    "temperature": 20
+    "temperature": 11
   }
 }

run-0/checkpoint-2862/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45fdb811c2d25bdfa6f70464c8f8897df3766bc1abc5d6e057a6e0a40f0dc9f
+oid sha256:a815016dfca6056394449b7eec53142e869a6e9ff738e6f9557bb4382010c025
 size 5240

runs/Oct11_17-03-17_c179252869f4/events.out.tfevents.1728666603.c179252869f4.732.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3373440a79b54f81f779ae53e565a2192b27fb9a7751fdc9599093acef9dbf8d
-size 28757
+oid sha256:9e0de4ba7fc2c6f2573bce588f86d9c687debacd510f6c419bc93278669290d4
+size 29434