Step 30500

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc0b6f9ede25848b4440e3a3b75ae481910266027a76a6f6d4ccfceaf2cbcbc4
-size 114425856
+oid sha256:b76cb150609c83406500033daf1401c3c869b1bbd2c657924d34b64ef4f18a0a
+size 124020431

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26aa43a71ef20ec5338c4fdde9142dfd63ea5b4748f0718dc9c1adadc2356b50
+oid sha256:a8b719ac98622aa5081e4588d32365a424b51442f0dc89d51634ec657d9dda47
 size 62015575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55379860d5993322de7e50bc90fdcc01f8bd3b79ab77cc4a24298562169a1da1
+oid sha256:2dde91353e8e873fc6f08fb03c6a05a606a2fb1188c39a2cef816921a1d0a448
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.122365523749608,
-  "global_step": 29000,
+  "epoch": 9.594212016357345,
+  "global_step": 30500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -354,11 +354,29 @@
       "learning_rate": 1.631645171437559e-05,
       "loss": 0.0455,
       "step": 29000
+    },
+    {
+      "epoch": 9.28,
+      "learning_rate": 1.608052846807172e-05,
+      "loss": 0.0437,
+      "step": 29500
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 1.5844605221767853e-05,
+      "loss": 0.0667,
+      "step": 30000
+    },
+    {
+      "epoch": 9.59,
+      "learning_rate": 1.5608681975463986e-05,
+      "loss": 0.0472,
+      "step": 30500
     }
   ],
   "max_steps": 63580,
   "num_train_epochs": 20,
-  "total_flos": 1.020599417048832e+16,
+  "total_flos": 1.073395869196032e+16,
   "trial_name": null,
   "trial_params": null
 }