Training in progress, step 28000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420ff4fe9de1143f6d478acce2666b05167b1e73cbb48f68aa640ad83f974110
+oid sha256:53f8c5fa890500685f737549791ff26aecd530587ab0f480410c97af7644766b
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064dee5bf90775739713e79948b81af1622b4b5b79a6d2a89f1f9b54e8753f88
+oid sha256:e9aecf46288b4f99b67c154c48c24f6fdc9770e07aa906231bba8f267757027b
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bcd68158522b3abec65e47068b30ffe1fa7af6ba0e5e50ccb5b0e6178b01211
+oid sha256:d21c1525fad1765f2c3753d4302c91b34bbece43f24f8d97e4e848b61e5236b0
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3730432187525435,
-  "global_step": 27500,
+  "epoch": 0.37982582272986243,
+  "global_step": 28000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -336,11 +336,17 @@
       "learning_rate": 0.0,
       "loss": 0.0358,
       "step": 27500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0,
+      "loss": 0.037,
+      "step": 28000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 2.873487036461875e+16,
+  "total_flos": 2.925728455930675e+16,
   "trial_name": null,
   "trial_params": null
 }

runs/Oct16_21-59-35_1b3a04926831/events.out.tfevents.1665958666.1b3a04926831.23.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:983b4c2526ec0ea143b54713f753237200860008c419787b041b74add0dfeace
-size 54317
+oid sha256:5094e99532c1b47e2b4f0ef6f837898447ce25718d65a99ad8719c50d2eb06c9
+size 54477