Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181452760f4889fb1745514a4de50facf35adde53641198d68d40c6fbe42eedd
+oid sha256:db7b0ba484d365a8232c614da6b35c1ca8564e014b51324208c27b61981f817d
 size 268290900

run-0/checkpoint-1000/trainer_state.json

@@ -10,50 +10,50 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5751612903225807,
-      "eval_loss": 0.1956518292427063,
-      "eval_runtime": 5.3591,
-      "eval_samples_per_second": 578.453,
-      "eval_steps_per_second": 12.129,
+      "eval_accuracy": 0.6083870967741936,
+      "eval_loss": 0.26111724972724915,
+      "eval_runtime": 5.3925,
+      "eval_samples_per_second": 574.869,
+      "eval_steps_per_second": 12.054,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.5248314738273621,
-      "learning_rate": 1.550763701707098e-05,
-      "loss": 0.3123,
+      "grad_norm": 0.612690269947052,
+      "learning_rate": 1.371069182389937e-05,
+      "loss": 0.4067,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.812258064516129,
-      "eval_loss": 0.09787755459547043,
-      "eval_runtime": 5.5145,
-      "eval_samples_per_second": 562.15,
-      "eval_steps_per_second": 11.787,
+      "eval_accuracy": 0.8261290322580646,
+      "eval_loss": 0.1251312643289566,
+      "eval_runtime": 6.2656,
+      "eval_samples_per_second": 494.764,
+      "eval_steps_per_second": 10.374,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8709677419354839,
-      "eval_loss": 0.06755243241786957,
-      "eval_runtime": 5.3827,
-      "eval_samples_per_second": 575.922,
-      "eval_steps_per_second": 12.076,
+      "eval_accuracy": 0.8719354838709678,
+      "eval_loss": 0.08443494886159897,
+      "eval_runtime": 5.7046,
+      "eval_samples_per_second": 543.422,
+      "eval_steps_per_second": 11.394,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.4460333585739136,
-      "learning_rate": 1.101527403414196e-05,
-      "loss": 0.1131,
+      "grad_norm": 0.5761224031448364,
+      "learning_rate": 7.421383647798742e-06,
+      "loss": 0.1453,
       "step": 1000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2226,
+  "max_steps": 1590,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 7,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -71,8 +71,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.5049198984839713,
-    "num_train_epochs": 7,
-    "temperature": 16
+    "alpha": 0.41459555473064347,
+    "num_train_epochs": 5,
+    "temperature": 4
   }
 }

run-0/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b81f5de55f5e8a8af9f6b46510b501dfc71d3179122d526c4f056fedd070e010
+oid sha256:db7b0ba484d365a8232c614da6b35c1ca8564e014b51324208c27b61981f817d
 size 268290900

run-0/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb511dfed27a93f9022cf9613ca1369f6d0223cdc69fb471ea40d8da8227a380
+oid sha256:91a7ce88c184ba71db5dc4fa9fb784f1d4bdb6de5d88f8d28bb6d60f143ead33
 size 536643898

run-0/checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e744277c61f87520794334442fae36c5f9ff6e10cb79d4bfee5176ca7eafe2
+oid sha256:9e1264523e958cf7990dc5f42d876cc12129475c4603804cf66868aaf25c2c24
 size 1064

run-0/checkpoint-500/trainer_state.json

@@ -10,25 +10,25 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5751612903225807,
-      "eval_loss": 0.1956518292427063,
-      "eval_runtime": 5.3591,
-      "eval_samples_per_second": 578.453,
-      "eval_steps_per_second": 12.129,
+      "eval_accuracy": 0.6083870967741936,
+      "eval_loss": 0.26111724972724915,
+      "eval_runtime": 5.3925,
+      "eval_samples_per_second": 574.869,
+      "eval_steps_per_second": 12.054,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.5248314738273621,
-      "learning_rate": 1.550763701707098e-05,
-      "loss": 0.3123,
+      "grad_norm": 0.612690269947052,
+      "learning_rate": 1.371069182389937e-05,
+      "loss": 0.4067,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2226,
+  "max_steps": 1590,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 7,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -46,8 +46,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.5049198984839713,
-    "num_train_epochs": 7,
-    "temperature": 16
+    "alpha": 0.41459555473064347,
+    "num_train_epochs": 5,
+    "temperature": 4
   }
 }

run-0/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:974ac49529ba17d5c7ed773c227ea8996054ebf15fdbbafbe2ab45abb5f14d2b
+oid sha256:7dbf6901b1fd8b4b70b58bb5a6861520d7a2d5accf1885587865c5346ea0a506
 size 5304

runs/Nov12_03-50-03_fde6a76996dd/events.out.tfevents.1731384970.fde6a76996dd.16977.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78fe2eea9fea9447c96f89abcf049db8759dc8f41e9add56d784e9792530b29
+size 13848

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18278fc3ffb0f8a89a794464595c9b39421f549988787cb6690252ca15809610
+oid sha256:7dbf6901b1fd8b4b70b58bb5a6861520d7a2d5accf1885587865c5346ea0a506
 size 5304