Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdab722bfe265bbb140ca4b72ef20bd36d960a5623ddae26895fc7ccd8817b39
+oid sha256:b0d5cbc1c3185dd32ef37f10b4ed5ca24bfb2dd19226e9f8ece5cd30ab043d21
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0c8b540103cf20fcfa5f99e4071e6a17851fbca178422cac9c25e398b2b3de
+oid sha256:e1925e47092b74a7e8d517d4419865703021d371eca3bd12555cb7a717db1f0a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2e50c443ac7207b5267536238a64dd1a88e448dcd4e5f4d67ce9d326fccb89
+oid sha256:626e62d0dc43f44f6bc046ba286539cfe2f03253ef6e57f2d823d1d84ff9a2a3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008352452888556624,
+  "epoch": 0.00928050320950736,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 14.03,
       "eval_steps_per_second": 1.754,
       "step": 81
+    },
+    {
+      "epoch": 0.008661802995540202,
+      "grad_norm": 9.557851791381836,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 6.1063,
+      "step": 84
+    },
+    {
+      "epoch": 0.008971153102523782,
+      "grad_norm": 6.9002885818481445,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 5.9132,
+      "step": 87
+    },
+    {
+      "epoch": 0.00928050320950736,
+      "grad_norm": 5.555031776428223,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 5.4556,
+      "step": 90
+    },
+    {
+      "epoch": 0.00928050320950736,
+      "eval_loss": 1.4364467859268188,
+      "eval_runtime": 1163.3776,
+      "eval_samples_per_second": 14.04,
+      "eval_steps_per_second": 1.755,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1777419102912512e+17,
+  "total_flos": 1.31836781002752e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null