Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae8a46d58c63f88a1bc72322a26cb93b75081168f9d6b045f4346803f9f5ef9
+oid sha256:fd874b11027d81450d3c8139a4c08c0666835afc6022318dfa6012d6ebda8ef2
 size 39428606

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c507c8040224badf8a9ff87d2082222c4b15f94ceb7b9c0131b6ca18d869b8
+oid sha256:b39570285d388458e5f194c05b0684bae7b478696486a031ebed3fa7a73607a7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009379543216245369,
+  "epoch": 0.0018759086432490737,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 46.638,
       "eval_steps_per_second": 23.319,
       "step": 10
+    },
+    {
+      "epoch": 0.0011255451859494444,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0014069314824368053,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0014069314824368053,
+      "eval_loss": NaN,
+      "eval_runtime": 96.5696,
+      "eval_samples_per_second": 46.495,
+      "eval_steps_per_second": 23.247,
+      "step": 15
+    },
+    {
+      "epoch": 0.0016883177789241664,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0018759086432490737,
+      "eval_loss": NaN,
+      "eval_runtime": 96.3528,
+      "eval_samples_per_second": 46.6,
+      "eval_steps_per_second": 23.3,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 64157282205696.0,
+  "total_flos": 124219418738688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null