Training in progress, step 220, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d54587f0b1a198dd39c4ae5e433126d643f66f0ed0846d561ef67c3037c9a48e
+oid sha256:0fbfedb128c3a8a90f3c52d5cb8498cfc4a1cc5679a309d2ba9e24f4e116613c
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b18511a4e4cf4754059d13bb09b4648a957c0877ea68b53a97a0ab51ece6344
+oid sha256:8aaa39867ef9a795fc2fde473bb2d03cac009f05ada558ae7564b3b55853713c
 size 255265850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d99c128ab1f240cd1c4228cbdcc4238c34c69acef749723e334ae111d48356bc
+oid sha256:7333eda3fb157e4797c9458ec4e20fb25f3cea65d779dd1876520831c6fa7301
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e465ffabd9644ccbc2caf12ae583025fdb275dc63c3b925248b2abc2e151ad
+oid sha256:bddfe446a5a284cd678d00b6a2a398b1ec19fbab21ddba1394b97157f0314350
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
+oid sha256:134925db3ae71cb88cb92756cc2cdea3066935b4ecbf838e78bbfa60c95c3818
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.666666666666668,
+  "epoch": 18.333333333333332,
   "eval_steps": 40,
-  "global_step": 200,
+  "global_step": 220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,20 @@
       "eval_samples_per_second": 142.96,
       "eval_steps_per_second": 2.286,
       "step": 200
+    },
+    {
+      "epoch": 17.5,
+      "grad_norm": 4.1875,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 3.2339,
+      "step": 210
+    },
+    {
+      "epoch": 18.333333333333332,
+      "grad_norm": 4.46875,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.1968,
+      "step": 220
     }
   ],
   "logging_steps": 10,
@@ -214,7 +228,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2971581575790592e+16,
+  "total_flos": 1.425922867593216e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null