Training in progress, step 28, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783c472ab3ae23fc38ccb22b4631c7203584e8a61c07b28850b81d832fcd9b17
+oid sha256:50da99e9fdaa839344065da168a71ad4f6e8b96f23f6f15a0983e22c15d3e2f2
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e949c7933076c725521cfd931f6e1e1b56b20df9e6b6437d9f037b7b74a982
+oid sha256:ee14f56778a2a94900b2d8442fe56ab7cbc2fa431a8e41b11c409f48520cbc07
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4e731a4d1c68698303eeb71c2b41d9bb320085f757ec3258171604072c6719b
+oid sha256:35f5fefeb88a6787abc5bbe5a6bd249c592b5684d6e50f6921a0da393e208dfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9591836734693877,
+  "epoch": 2.2857142857142856,
   "eval_steps": 4,
-  "global_step": 24,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,21 @@
       "eval_samples_per_second": 13.727,
       "eval_steps_per_second": 1.961,
       "step": 24
+    },
+    {
+      "epoch": 2.204081632653061,
+      "grad_norm": NaN,
+      "learning_rate": 3.019601169804216e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "eval_loss": NaN,
+      "eval_runtime": 1.5263,
+      "eval_samples_per_second": 13.759,
+      "eval_steps_per_second": 1.966,
+      "step": 28
     }
   ],
   "logging_steps": 3,
@@ -138,7 +153,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.587433854454989e+16,
+  "total_flos": 4.157840551418266e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null