Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2feea1054828ad3172c352c84ed6798ef59cc8d1f21c210f78ef23122e88532e
+oid sha256:71f0d7b3291e09dd93f47867c1137cdf7c55b22a74c7be79332033d43df356e8
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed07f10db2e36ab3cde037c8d4578b30f499bef3c2bd6f2a9e3e95dc1f66142
+oid sha256:f49314a344bf67129cd1d2bb79cf1b4fbb56bd464b88e373c23827c73bf8f008
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:229c36a62fc464984692ce088ac1368dfa1125205e2ac52e9b22745e8bca2873
+oid sha256:7026cc9503810ffbbc031c2dc29c53ea4bb44f2ef3341c91c007f3028c1944d6
 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": 0.027346387575962187,
+  "epoch": 0.03038487508440243,
   "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": 65.221,
       "eval_steps_per_second": 8.158,
       "step": 81
+    },
+    {
+      "epoch": 0.02835921674544227,
+      "grad_norm": 2.0330305099487305,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 1.9747,
+      "step": 84
+    },
+    {
+      "epoch": 0.02937204591492235,
+      "grad_norm": 2.5625412464141846,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 1.9695,
+      "step": 87
+    },
+    {
+      "epoch": 0.03038487508440243,
+      "grad_norm": 2.109513759613037,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 1.957,
+      "step": 90
+    },
+    {
+      "epoch": 0.03038487508440243,
+      "eval_loss": 2.0099809169769287,
+      "eval_runtime": 76.5101,
+      "eval_samples_per_second": 65.207,
+      "eval_steps_per_second": 8.156,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5839729836687360.0,
+  "total_flos": 6488588707430400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null