Training in progress, step 2000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c06d9ef52dfd6cb1290a5937123ea6ad62407a08194a9f06b6857d478ccb34
+oid sha256:3d67e381b422c395db768ed23034a2a8bba5e803f3f1aff15b4c13df8440e2fc
 size 268290900

run-0/checkpoint-2000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295c6c1f872ff632f863e58a5986fe3864390ff88e5981b65632027c9c57d453
+oid sha256:3d67e381b422c395db768ed23034a2a8bba5e803f3f1aff15b4c13df8440e2fc
 size 268290900

run-0/checkpoint-2000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5da8d6971d3d4157e629934f7fd366eabb0abb8463a0e04b9c07e013ea6ad67
+oid sha256:b729784501b7eea68616711ea8b128a6303122c7ad69180933e842861cfd56d8
 size 536643898

run-0/checkpoint-2000/trainer_state.json

@@ -10,80 +10,80 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5880645161290322,
-      "eval_loss": 0.20538708567619324,
-      "eval_runtime": 5.2125,
-      "eval_samples_per_second": 594.727,
-      "eval_steps_per_second": 12.47,
+      "eval_accuracy": 0.5829032258064516,
+      "eval_loss": 0.20076851546764374,
+      "eval_runtime": 5.4347,
+      "eval_samples_per_second": 570.412,
+      "eval_steps_per_second": 11.96,
       "step": 318
     },
     {
       "epoch": 1.57,
       "learning_rate": 1.550763701707098e-05,
-      "loss": 0.3249,
+      "loss": 0.3179,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8335483870967741,
-      "eval_loss": 0.1016974076628685,
-      "eval_runtime": 5.4495,
-      "eval_samples_per_second": 568.859,
-      "eval_steps_per_second": 11.928,
+      "eval_accuracy": 0.8312903225806452,
+      "eval_loss": 0.09997060149908066,
+      "eval_runtime": 5.5066,
+      "eval_samples_per_second": 562.957,
+      "eval_steps_per_second": 11.804,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8848387096774194,
-      "eval_loss": 0.06891165673732758,
-      "eval_runtime": 5.6248,
-      "eval_samples_per_second": 551.129,
-      "eval_steps_per_second": 11.556,
+      "eval_accuracy": 0.885483870967742,
+      "eval_loss": 0.06820663809776306,
+      "eval_runtime": 5.3564,
+      "eval_samples_per_second": 578.748,
+      "eval_steps_per_second": 12.135,
       "step": 954
     },
     {
       "epoch": 3.14,
       "learning_rate": 1.101527403414196e-05,
-      "loss": 0.1169,
+      "loss": 0.1149,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8993548387096775,
-      "eval_loss": 0.05370178818702698,
-      "eval_runtime": 5.6282,
-      "eval_samples_per_second": 550.795,
-      "eval_steps_per_second": 11.549,
+      "eval_accuracy": 0.8987096774193548,
+      "eval_loss": 0.05336497724056244,
+      "eval_runtime": 5.5937,
+      "eval_samples_per_second": 554.197,
+      "eval_steps_per_second": 11.62,
       "step": 1272
     },
     {
       "epoch": 4.72,
       "learning_rate": 6.522911051212939e-06,
-      "loss": 0.0768,
+      "loss": 0.0759,
       "step": 1500
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.91,
-      "eval_loss": 0.04600737988948822,
-      "eval_runtime": 5.691,
-      "eval_samples_per_second": 544.716,
-      "eval_steps_per_second": 11.421,
+      "eval_accuracy": 0.9093548387096774,
+      "eval_loss": 0.04582875967025757,
+      "eval_runtime": 6.0528,
+      "eval_samples_per_second": 512.159,
+      "eval_steps_per_second": 10.739,
       "step": 1590
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.912258064516129,
-      "eval_loss": 0.04226335510611534,
-      "eval_runtime": 5.7066,
-      "eval_samples_per_second": 543.231,
-      "eval_steps_per_second": 11.39,
+      "eval_accuracy": 0.9116129032258065,
+      "eval_loss": 0.04215848818421364,
+      "eval_runtime": 5.6245,
+      "eval_samples_per_second": 551.164,
+      "eval_steps_per_second": 11.557,
       "step": 1908
     },
     {
       "epoch": 6.29,
       "learning_rate": 2.0305480682839176e-06,
-      "loss": 0.0634,
+      "loss": 0.0628,
       "step": 2000
     }
   ],
@@ -94,8 +94,8 @@
   "total_flos": 519927215063004.0,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.47065466175612003,
+    "alpha": 0.3888910320919544,
     "num_train_epochs": 7,
-    "temperature": 11
+    "temperature": 14
   }
 }

run-0/checkpoint-2000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9875ecc9817a22000d7b6d79d7630f539ed7cf56aea4abb3a9a7bda735d6a72d
+oid sha256:c4ff8148ef350bdda6fc8fdc944910a6b03a9fdbe918074b22f041373f4f085f
 size 4664

runs/Jan25_17-40-54_c146da53f02f/events.out.tfevents.1706205085.c146da53f02f.3236.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b8d1a16722860450d51e7c01e4473120c44d056eeb92421a7a32afcb65d9de8
-size 13927
+oid sha256:2a8f1f8f41aa8ccd8df5646a9ec6a75176493f9441b4d95a72304127ef0c7b9b
+size 14407