Training in progress, step 35, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d323d847be47e8839d0e28e59584012fcbd41b89f7ecea782af3324142692daf
+oid sha256:b83a81b8e16a8124ae18d714dbbca2b4b5f8c330d762e05c51c7166bb92fec80
 size 588699796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b49069fd0c0422c2f937f1be8e16eed0ae8d4d50e480da209b33fade5ae5d57
+oid sha256:e309b0c5f20ff43b2176507b02a3769210f48a74fb3cb9b2863f868c47b7cb80
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2591792656587473,
+  "epoch": 0.3023758099352052,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,21 @@
       "eval_samples_per_second": 4.224,
       "eval_steps_per_second": 0.542,
       "step": 30
+    },
+    {
+      "epoch": 0.28509719222462204,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.3023758099352052,
+      "eval_loss": NaN,
+      "eval_runtime": 46.1477,
+      "eval_samples_per_second": 4.226,
+      "eval_steps_per_second": 0.542,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.558064933193646e+17,
+  "total_flos": 1.8221437354298573e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null