Training in progress, step 32, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50da99e9fdaa839344065da168a71ad4f6e8b96f23f6f15a0983e22c15d3e2f2
+oid sha256:aed0fe66dc0b4320819879d4a67e5eaf075dcbb50c44b1cd4435ec5e1d410c5a
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee14f56778a2a94900b2d8442fe56ab7cbc2fa431a8e41b11c409f48520cbc07
+oid sha256:8e5f2ad1f452b658160c4bc70d8bc81f7436d50760a7d36c42e849bc3558ad4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f5fefeb88a6787abc5bbe5a6bd249c592b5684d6e50f6921a0da393e208dfa
+oid sha256:5ab6a153c857bb78edd49ded6ae96779b7e267ac5a88c0f4701c1aa25a7f8d03
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2857142857142856,
+  "epoch": 2.612244897959184,
   "eval_steps": 4,
-  "global_step": 28,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -134,6 +134,21 @@
       "eval_samples_per_second": 13.759,
       "eval_steps_per_second": 1.966,
       "step": 28
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": NaN,
+      "learning_rate": 1.5687918106563326e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.612244897959184,
+      "eval_loss": NaN,
+      "eval_runtime": 1.5277,
+      "eval_samples_per_second": 13.746,
+      "eval_steps_per_second": 1.964,
+      "step": 32
     }
   ],
   "logging_steps": 3,
@@ -153,7 +168,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.157840551418266e+16,
+  "total_flos": 4.761245982916608e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null