Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3ba91fcfa33a4fc60d7d960039c3cbbe3ab374b9c3163b3c0f9f4ea0bf01a5
+oid sha256:d206fd32b6cf1d08f1504a4866441403ecd7fdf3ac14659d4ddca244489c16e1
 size 19552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23225fdb9d0919cbadab2d67e7a184b58ed35fe3def41e07f1e8c230e4d536fc
+oid sha256:e84fedcaffd4f6b725ea12f1770529622232946601b79bcd3294dd6734268a33
 size 44354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b165213f53197ccef9210a316146efd985350a4587234352809bf283a32d781
+oid sha256:db326375a5aad8c6b99fcad9f85ce3d1f2a6779d8d9ea03968cefdb563d4858d
 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": 0.05137891953154514,
+  "epoch": 0.06422364941443143,
   "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": 36.086,
       "eval_steps_per_second": 4.515,
       "step": 68
+    },
+    {
+      "epoch": 0.05213449187759728,
+      "grad_norm": 0.02452562004327774,
+      "learning_rate": 7.803575286758364e-05,
+      "loss": 12.4501,
+      "step": 69
+    },
+    {
+      "epoch": 0.05440120891575368,
+      "grad_norm": 0.024608276784420013,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 12.449,
+      "step": 72
+    },
+    {
+      "epoch": 0.056667925953910084,
+      "grad_norm": 0.025729818269610405,
+      "learning_rate": 7.379736965185368e-05,
+      "loss": 12.4491,
+      "step": 75
+    },
+    {
+      "epoch": 0.058934642992066494,
+      "grad_norm": 0.026810096576809883,
+      "learning_rate": 7.158771761692464e-05,
+      "loss": 12.4492,
+      "step": 78
+    },
+    {
+      "epoch": 0.0612013600302229,
+      "grad_norm": 0.030193008482456207,
+      "learning_rate": 6.932495846462261e-05,
+      "loss": 12.4488,
+      "step": 81
+    },
+    {
+      "epoch": 0.0634680770683793,
+      "grad_norm": 0.0322081558406353,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 12.4457,
+      "step": 84
+    },
+    {
+      "epoch": 0.06422364941443143,
+      "eval_loss": 12.447479248046875,
+      "eval_runtime": 61.6601,
+      "eval_samples_per_second": 36.166,
+      "eval_steps_per_second": 4.525,
+      "step": 85
     }
   ],
   "logging_steps": 3,
@@ -220,7 +270,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 150133014528.0,
+  "total_flos": 188051619840.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null