Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:583294e9760387c36ff5aef39609749aeb1526b267e1ed27b169f9f8c326c3c1
+oid sha256:f9f0895190829d062f17015eff7a59141eaaa09ae0d490730aa052e2f93c8584
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:402f7ec2da450e51c00f680e6c7fe1410d21bdf5bfa43abff67d3b68195d1701
+oid sha256:f6cbf4682011922a51af0c2acb371d7bf47e4e29f1e851a1ac34e5526d4d4432
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455977057132821379da92f1a77f9b1f540991d9dd7c684ba956aca72c970f71
+oid sha256:eaef23ad6b9358048cfa2eb81866d8f39693a1c7df686b619cd9d9ea3051d3a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02194787379972565,
+  "epoch": 0.024691358024691357,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 13.9,
       "eval_steps_per_second": 1.738,
       "step": 72
+    },
+    {
+      "epoch": 0.022862368541380886,
+      "grad_norm": 3.332122564315796,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 5.6472,
+      "step": 75
+    },
+    {
+      "epoch": 0.02377686328303612,
+      "grad_norm": 3.3746860027313232,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 5.0507,
+      "step": 78
+    },
+    {
+      "epoch": 0.024691358024691357,
+      "grad_norm": 3.771028757095337,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 4.741,
+      "step": 81
+    },
+    {
+      "epoch": 0.024691358024691357,
+      "eval_loss": 1.3051848411560059,
+      "eval_runtime": 397.5922,
+      "eval_samples_per_second": 13.896,
+      "eval_steps_per_second": 1.738,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0125076377423053e+17,
+  "total_flos": 1.1390710924600934e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null