Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8098593e33ccd37144bf244f7e85c00bb3adb8cb3c225688acba199c234f2025
+oid sha256:959933e1af9857170a4b99347ec3762d0d5f8de070b5a1d13603b3caf975bf48
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e3ff26fad7d91b228dfcbd64c6833d0f4ba5294112e04881857700ec1092e4
+oid sha256:d4c40c52a45a881eb464287fa64d73edebeb642339a644660b5f6de8173aa66d
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8256a51c921e3764623587232574eeea4ef70bf2e730f79b7a5b429639bc4f0
+oid sha256:18c91c570b07019a1068294715f275674400f8131145c713b4a085e0034f5c76
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:9d42533d2ce676231a5f1b4cd529190e6e167a0f19701b5e4bdd8cf1b59bbcf1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04381161007667032,
+  "epoch": 0.06571741511500548,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 9.328,
       "eval_steps_per_second": 4.712,
       "step": 10
+    },
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 0.28297099471092224,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 0.0256,
+      "step": 11
+    },
+    {
+      "epoch": 0.05257393209200438,
+      "grad_norm": 0.13293632864952087,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.0161,
+      "step": 12
+    },
+    {
+      "epoch": 0.056955093099671415,
+      "grad_norm": 0.238490030169487,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 0.0233,
+      "step": 13
+    },
+    {
+      "epoch": 0.06133625410733844,
+      "grad_norm": 0.1766541600227356,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0222,
+      "step": 14
+    },
+    {
+      "epoch": 0.06571741511500548,
+      "grad_norm": 0.08793684095144272,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.0064,
+      "step": 15
+    },
+    {
+      "epoch": 0.06571741511500548,
+      "eval_loss": 0.018376410007476807,
+      "eval_runtime": 10.3128,
+      "eval_samples_per_second": 9.406,
+      "eval_steps_per_second": 4.751,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7398256992583680.0,
+  "total_flos": 1.109738548887552e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null