Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:294322a3921efabcf477dc40b7b403c369a45a4957c3e80807fc97e64c4a09cf
+oid sha256:176ef3c507fb509247ed678ad7820d7b95ef91bb124c7c80f8f6d76583facf5a
 size 268290900

run-2/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3a7265c52e0a7d0ae4394d065a3129b9fdf16531547a47093c87bc66b35b5eb
+oid sha256:a085d735cd8cb688348e3d616bb12ef7bafe15d11b3ddb22f501564224348220
 size 268290900

run-2/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c797c50bd678b10335d7b7709444984baf12d8f89a40002375b8646df847b3c
+oid sha256:de2939019b76d56435d04fa44a1daaf95a1a67c19ae9f063ef8ba801e49059be
 size 536643898

run-2/checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c794bc4c67ef18245dd516031ce405ab557e4d551d225d8dd1e1abc0f2be8e33
+oid sha256:9f182501c34e4ea3ebc7617d27edab7e1367582b147e518cd90295ec7f2eaa0f
 size 1064

run-2/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a21424fcc7b0ab6ff9f908cdab480c20a3c07931af6e79061f4c4e5b5311db
+oid sha256:e3bb46aada442b39115d169cd9c125713b5e861f4eaf782c3cede72bc75c5fe3
 size 5304

run-2/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dab1cd5f64b14ee6b4befe3e3e768c0220fe9d0802217433f46a5220e28373d
+oid sha256:176ef3c507fb509247ed678ad7820d7b95ef91bb124c7c80f8f6d76583facf5a
 size 268290900

run-2/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb7505a6ea2eff11bb84b98677dc2eb785c4e7f7580c88c7dc7b97295cf4423
+oid sha256:6b1d434063a810ac5a8e9f21a272ba532b984a3780a2fe594e1d2489d014ad75
 size 536643898

run-2/checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71453465aad25f4c5a0a948496c64b1f74df850abda497954afe3695c00756ee
+oid sha256:91d97f7c1be085852e2ffd2fe2f8a493a080e2b2858e2f3baf642fe214e035a0
 size 1064

run-2/checkpoint-1500/trainer_state.json

@@ -10,66 +10,66 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.587741935483871,
-      "eval_loss": 0.19460442662239075,
-      "eval_runtime": 5.4234,
-      "eval_samples_per_second": 571.599,
-      "eval_steps_per_second": 11.985,
+      "eval_accuracy": 0.6690322580645162,
+      "eval_loss": 0.42948082089424133,
+      "eval_runtime": 5.3921,
+      "eval_samples_per_second": 574.917,
+      "eval_steps_per_second": 12.055,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.5228433012962341,
-      "learning_rate": 1.685534591194969e-05,
-      "loss": 0.3144,
+      "grad_norm": 0.8646999001502991,
+      "learning_rate": 1.371069182389937e-05,
+      "loss": 0.6591,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8212903225806452,
-      "eval_loss": 0.09393113851547241,
-      "eval_runtime": 5.9301,
-      "eval_samples_per_second": 522.759,
-      "eval_steps_per_second": 10.961,
+      "eval_accuracy": 0.8229032258064516,
+      "eval_loss": 0.16900987923145294,
+      "eval_runtime": 5.4801,
+      "eval_samples_per_second": 565.687,
+      "eval_steps_per_second": 11.861,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8793548387096775,
-      "eval_loss": 0.06259110569953918,
-      "eval_runtime": 5.99,
-      "eval_samples_per_second": 517.529,
-      "eval_steps_per_second": 10.851,
+      "eval_accuracy": 0.8729032258064516,
+      "eval_loss": 0.0963619202375412,
+      "eval_runtime": 5.6559,
+      "eval_samples_per_second": 548.098,
+      "eval_steps_per_second": 11.492,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.4349106550216675,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.109,
+      "grad_norm": 0.7748064398765564,
+      "learning_rate": 7.421383647798742e-06,
+      "loss": 0.1958,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9006451612903226,
-      "eval_loss": 0.04817655682563782,
-      "eval_runtime": 6.7151,
-      "eval_samples_per_second": 461.646,
-      "eval_steps_per_second": 9.68,
+      "eval_accuracy": 0.8977419354838709,
+      "eval_loss": 0.07352616637945175,
+      "eval_runtime": 5.4921,
+      "eval_samples_per_second": 564.449,
+      "eval_steps_per_second": 11.835,
       "step": 1272
     },
     {
       "epoch": 4.716981132075472,
-      "grad_norm": 0.2985810339450836,
-      "learning_rate": 1.0566037735849058e-05,
-      "loss": 0.0692,
+      "grad_norm": 0.542826771736145,
+      "learning_rate": 1.1320754716981133e-06,
+      "loss": 0.113,
       "step": 1500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 3180,
+  "max_steps": 1590,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -87,8 +87,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.11018489395767606,
-    "num_train_epochs": 10,
-    "temperature": 13
+    "alpha": 0.1651888586206014,
+    "num_train_epochs": 5,
+    "temperature": 2
   }
 }

run-2/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a21424fcc7b0ab6ff9f908cdab480c20a3c07931af6e79061f4c4e5b5311db
+oid sha256:e3bb46aada442b39115d169cd9c125713b5e861f4eaf782c3cede72bc75c5fe3
 size 5304

runs/Nov12_03-50-03_fde6a76996dd/events.out.tfevents.1731385960.fde6a76996dd.16977.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7299387b0655afa7853258c09274f2fb1a3e6607c6a114e90ca322d5189eb5a7
-size 13811
+oid sha256:19f2b6fc5c4e57da32c66a68d2d8ec6aaa6882bcf0712fffc8994d6c51ee2517
+size 15022