Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3198af97fd8cfcdad00f14309da038efe5e49694545c548255fddfa9f700511
+oid sha256:b9cfc8ccd959cc28b94fe4e9b5271f98586d2c2bec8a3ae3a191b499690dcefd
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc85a9457cebb5f59ed810be458b3f2c3915dff9727701deebf85d4edc275634
+oid sha256:f0d56eae9bb54a5d185de847d222a79c5fecfb2d395ef561ca40242b105b759b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001503824630912272,
+  "epoch": 0.002255736946368408,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,28 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.0017351822664372371,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0017351822664372371,
+      "eval_loss": NaN,
+      "eval_runtime": 947.161,
+      "eval_samples_per_second": 7.686,
+      "eval_steps_per_second": 3.843,
+      "step": 30
+    },
+    {
+      "epoch": 0.002024379310843443,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
     }
   ],
   "logging_steps": 5,
@@ -85,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1280978121129984.0,
+  "total_flos": 1921467181694976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null