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:f9f0895190829d062f17015eff7a59141eaaa09ae0d490730aa052e2f93c8584
+oid sha256:a33375bec8ec83c873dfe3b5dcd16b4f5940892e1e6da203bf9e41daf8ed7498
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6cbf4682011922a51af0c2acb371d7bf47e4e29f1e851a1ac34e5526d4d4432
+oid sha256:787ddd25cfe8eae6733736d44455f2ed8b85eb9edf9846503e3ba97bfd01d5ad
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaef23ad6b9358048cfa2eb81866d8f39693a1c7df686b619cd9d9ea3051d3a5
+oid sha256:b202cc35d4d82828b46ac25c2aa3b0d5b24c9fdd644bb03957f013b307cbc71d
 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": 0.024691358024691357,
+  "epoch": 0.027434842249657063,
   "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": 13.896,
       "eval_steps_per_second": 1.738,
       "step": 81
+    },
+    {
+      "epoch": 0.025605852766346592,
+      "grad_norm": 4.040452003479004,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 5.5279,
+      "step": 84
+    },
+    {
+      "epoch": 0.026520347508001828,
+      "grad_norm": 3.8290328979492188,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 5.4467,
+      "step": 87
+    },
+    {
+      "epoch": 0.027434842249657063,
+      "grad_norm": 4.0576395988464355,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 5.546,
+      "step": 90
+    },
+    {
+      "epoch": 0.027434842249657063,
+      "eval_loss": 1.3046977519989014,
+      "eval_runtime": 397.5869,
+      "eval_samples_per_second": 13.896,
+      "eval_steps_per_second": 1.738,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1390710924600934e+17,
+  "total_flos": 1.2656345471778816e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null