Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3e86124f91d74d6f37e217633c4e1890f41c6c6434fe4f4d97b7d900ff8512
+oid sha256:7273d0709e6b81d91c728400b70fbae28d3ae62a8b5c021470381ed6ae274d98
 size 144985666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91ea1aa11b3d7319fde0163c37556f7fd7b43252e206a8f06393cf4f5d33ab6a
+oid sha256:36d0e509d0a23344ef62d965f8b2ac3eb8a75cdc88a235b52ad91251466f148e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
+oid sha256:baae720e33260fead254c87141d85e241b839ae924033bfd9652fb777f3f1bf0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07672634271099744,
+  "epoch": 0.11508951406649616,
   "eval_steps": 13,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,42 @@
       "learning_rate": 0.00018090169943749476,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.08056265984654731,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.09207161125319693,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.09974424552429667,
+      "eval_loss": NaN,
+      "eval_runtime": 37.425,
+      "eval_samples_per_second": 17.609,
+      "eval_steps_per_second": 4.409,
+      "step": 26
+    },
+    {
+      "epoch": 0.10358056265984655,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.11508951406649616,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -84,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7973206870654976e+16,
+  "total_flos": 2.7179972082794496e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null