Training in progress, step 35, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a4a5888d0eb9edb735edf1836a19a959b1ba8681885f9aa21198c19709da23
+oid sha256:14d79aec87f25697b8cf04ac479bb9cdc2a09c6015a47112596f400eff01a54c
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a2da2c27db3e75cb60a65bdad6cbec94e7027398481edbf9379026b0fbc10c
+oid sha256:930d0a935a0eb8b037f241e9e7697244a4582f0883b9be5d3edea45e0d615ed0
 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": 0.010512483574244415,
+  "epoch": 0.012264564169951819,
   "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": 9.264,
       "eval_steps_per_second": 1.158,
       "step": 30
+    },
+    {
+      "epoch": 0.011563731931668857,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.012264564169951819,
+      "eval_loss": NaN,
+      "eval_runtime": 518.5102,
+      "eval_samples_per_second": 9.269,
+      "eval_steps_per_second": 1.159,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.367941139995034e+16,
+  "total_flos": 7.298089845837005e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null