Training in progress, step 8, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e9e12aa20be3a6eb4426023f282c0efffadfe52eb49d7389c1e5d003cb5718
+oid sha256:749512039905e54b4fda9b285bfa58998f095aabc18773c9ece09be87caff2a0
 size 20312676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af2b1964596c44d062b56fa984a33825c3868435808cbe97f40f7c1ae5440ba
+oid sha256:c6089a8858f8deb2de47fb0521be50994912c13387776ea61d86b7928ecdc7e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb315c953aaf7a2b711346e094e1b3fb4641d4817507c6cc22bd7da7f0502a5
+oid sha256:3d7b358298aa83a40c1b56e5c320426fa83976856684a928a0b4adb7fc547539
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32,
+  "epoch": 0.64,
   "eval_steps": 4,
-  "global_step": 4,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,14 @@
       "eval_samples_per_second": 72.484,
       "eval_steps_per_second": 24.161,
       "step": 4
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": NaN,
+      "eval_runtime": 0.0848,
+      "eval_samples_per_second": 70.793,
+      "eval_steps_per_second": 23.598,
+      "step": 8
     }
   ],
   "logging_steps": 10,
@@ -42,7 +50,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 11400552382464.0,
+  "total_flos": 22801104764928.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null