Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4018e222ba654e7389dc391c433c701d4f5838c682c4f25b82a40ce4e8b61dcd
+oid sha256:1549d56f4075bc5b6343d1529fd14039847615e2b2122b5d0e5d5fd7f8912229
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eab86eba0b2832a7e95ae63ef7f153a72efc20d119164fd6e60abb894e2d0875
+oid sha256:dd351cfa3aac057a42d31b36795f5d23b7d9456e52b48799d6b159d37c63da9f
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c16b24865a63961b775a7107dc272a0c419a6935a35e7609e0a4f3bf916ee3
+oid sha256:ee11719cafc57eb6e3b41b5cd34aac6653a2aa206c921a430a81aac0b966b2db
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4967fab956f007beafd6b8bc5c5dee4d86950ea055e4ab46c9a7cdc66a69112d
+oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5483870967741935,
+  "epoch": 1.7204301075268817,
   "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": 8.968,
       "eval_steps_per_second": 4.509,
       "step": 81
+    },
+    {
+      "epoch": 1.6057347670250897,
+      "grad_norm": 1.877886176109314,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3041,
+      "step": 84
+    },
+    {
+      "epoch": 1.6630824372759858,
+      "grad_norm": 1.9166302680969238,
+      "learning_rate": 1.2750399292720283e-05,
+      "loss": 1.3063,
+      "step": 87
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 1.6511739492416382,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.2796,
+      "step": 90
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "eval_loss": 1.8262274265289307,
+      "eval_runtime": 19.737,
+      "eval_samples_per_second": 8.968,
+      "eval_steps_per_second": 4.509,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.83414773002666e+17,
+  "total_flos": 5.3712752555851776e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null