Training in progress, step 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac94be5a702eee2f14cc221105b3ab133906410af20bbd73640a5c66ab880edb
+oid sha256:b2e0658a466d23d18bec8dd6df8b12c5738c285dbabaefec00c779f8e99f0506
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b62f6eddadd89cd3e9be43881bd6539f70eb520b8e491e1b083e4d1af0b28bf
+oid sha256:62983da0207b4692844aafa0401b3d61a325343bb7d9aa4dcf563a3b9c7a2182
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2307692307692308,
+  "epoch": 1.5384615384615383,
   "eval_steps": 1,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -46,6 +46,14 @@
       "eval_samples_per_second": 35.562,
       "eval_steps_per_second": 5.927,
       "step": 4
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": NaN,
+      "eval_runtime": 0.17,
+      "eval_samples_per_second": 35.288,
+      "eval_steps_per_second": 5.881,
+      "step": 5
     }
   ],
   "logging_steps": 3,
@@ -65,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1046056308572160.0,
+  "total_flos": 1318201039257600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null