Training in progress, step 21500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b28df1971539671747e3a778afbdb5f38bcc6ab00d7766a5153b19f29b78c8d
+oid sha256:9498cb3e3306e8357a032524622b5d26748d8db258d513acaef4c7e389559f2c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7061f248e70b39002a88a3f1e8979a8a5203e1f6c7433a05e47b1416a56cf81d
+oid sha256:b4fcf3c27385ce93621769bdc2dbf10817c3a0a9703e9571bb7778f1cc3f2198
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57271955ed47e1769456cbc5629f14409b6b61904f3f76f733b63102e083bba0
+oid sha256:6135b553c57e576683ea34e2125a95123075dc2da6ac1f60418ada8ca13529ab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd63ac70e4657463d9ad6dfb25e72c667be965cdfce9d42626f1f00c9c329b89
+oid sha256:3693f6d21626ad0956a90ced9d517a1b2895382ded929533dfbb38ad2b207f63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4,
+  "epoch": 1.4333333333333333,
   "eval_steps": 500,
-  "global_step": 21000,
+  "global_step": 21500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1485,6 +1485,41 @@
       "learning_rate": 1.066977777777778e-05,
       "loss": 0.0567,
       "step": 21000
+    },
+    {
+      "epoch": 1.4066666666666667,
+      "grad_norm": 0.4028960168361664,
+      "learning_rate": 1.0625333333333335e-05,
+      "loss": 0.0558,
+      "step": 21100
+    },
+    {
+      "epoch": 1.4133333333333333,
+      "grad_norm": 0.30364444851875305,
+      "learning_rate": 1.058088888888889e-05,
+      "loss": 0.0588,
+      "step": 21200
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.34276890754699707,
+      "learning_rate": 1.0536444444444445e-05,
+      "loss": 0.0537,
+      "step": 21300
+    },
+    {
+      "epoch": 1.4266666666666667,
+      "grad_norm": 0.1914118230342865,
+      "learning_rate": 1.0492e-05,
+      "loss": 0.058,
+      "step": 21400
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.3174405097961426,
+      "learning_rate": 1.0447555555555557e-05,
+      "loss": 0.0576,
+      "step": 21500
     }
   ],
   "logging_steps": 100,
@@ -1504,7 +1539,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.115246280704e+16,
+  "total_flos": 5.237037858816e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null