Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b03db4aa92684e41a85b6ab0522f6787677fb79142d3c193edae47d771eb02a
+oid sha256:d9e8cfba5a77cad29d727a3166f26c38a84816c41c1f2515caa8a7adb4dcc8c4
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8a6f071dd7e043292fe3c6ba193f1fb90960cffe853e365051820e894ebe3b4
+oid sha256:689217aaa41feaaaeee9288107dd691977948d6c3a1d2a1df9bb651a1352b6aa
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1ba887b2f1ff61690aec183c8d72f5e592af046ae56ecda6cdb85532eef9c7
+oid sha256:52126d43fca697f9a6daabc677f2c11c3e68cba9c6ff06167ebb9376aa2ac9b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40aaba2d15c70d89033b94214bc8306c06d04f2fbceef0fdedf952808109d707
+oid sha256:24510621ac929102038dbb9557bac0e17f0ed52c36608ebab8e700d1b1464f1d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14670981661272922,
+  "epoch": 0.18338727076591155,
   "eval_steps": 17,
-  "global_step": 68,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -201,6 +201,56 @@
       "eval_samples_per_second": 50.878,
       "eval_steps_per_second": 6.384,
       "step": 68
+    },
+    {
+      "epoch": 0.1488673139158576,
+      "grad_norm": 0.03484257683157921,
+      "learning_rate": 7.803575286758364e-05,
+      "loss": 0.0004,
+      "step": 69
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.03455309569835663,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 0.0016,
+      "step": 72
+    },
+    {
+      "epoch": 0.16181229773462782,
+      "grad_norm": 0.011528185568749905,
+      "learning_rate": 7.379736965185368e-05,
+      "loss": 0.0004,
+      "step": 75
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.03166678920388222,
+      "learning_rate": 7.158771761692464e-05,
+      "loss": 0.0024,
+      "step": 78
+    },
+    {
+      "epoch": 0.17475728155339806,
+      "grad_norm": 0.0032140235416591167,
+      "learning_rate": 6.932495846462261e-05,
+      "loss": 0.0002,
+      "step": 81
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.0027989039663225412,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.0001,
+      "step": 84
+    },
+    {
+      "epoch": 0.18338727076591155,
+      "eval_loss": 0.0013614986091852188,
+      "eval_runtime": 15.3471,
+      "eval_samples_per_second": 50.889,
+      "eval_steps_per_second": 6.386,
+      "step": 85
     }
   ],
   "logging_steps": 3,
@@ -220,7 +270,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3257799203028992e+16,
+  "total_flos": 1.6596442068025344e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null