Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15abefa67a14818f3e0d3d9f5e641bec8c109e1f83be5dfe8271ac0f626c9a8a
+oid sha256:6d8818657dcd593dc6d27f888b16addfd9b17c0356988639eee40f50dc6562b0
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34dbeb7b04207119cff9fe0cdbd03f36ef68c5fd32ddae91bb2dcdadc4860989
+oid sha256:02c679de3d2fdcd39595ed6ccf847ea6fb817f1f77492eb738aa08b129c331cc
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd3c8778f78fc6ec9d991fdcfb271264180badfb60aa8044c4b1f7eca4abe20a
+oid sha256:48969848238b3319c490875539c834bee2d4c3d05c4117e25a0775383fdbfe6a
 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": 0.7902439024390244,
+  "epoch": 0.8780487804878049,
   "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": 35.547,
       "eval_steps_per_second": 4.52,
       "step": 81
+    },
+    {
+      "epoch": 0.8195121951219512,
+      "grad_norm": 0.3776783049106598,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 2.6349,
+      "step": 84
+    },
+    {
+      "epoch": 0.848780487804878,
+      "grad_norm": 0.21473738551139832,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 2.6227,
+      "step": 87
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.21475864946842194,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 2.8433,
+      "step": 90
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "eval_loss": 2.828202247619629,
+      "eval_runtime": 4.8709,
+      "eval_samples_per_second": 35.517,
+      "eval_steps_per_second": 4.517,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7460177980555264e+16,
+  "total_flos": 3.050241344195789e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null