Training in progress, step 90, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59587431aa0755f4eeae607a90ff6f85242a5296d66e6f36e71e31abdeda445e
+oid sha256:160187578020e11ca2488e566577ab350c8e0dbc296fa4553fcde2ce456017c2
 size 1279641042

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd9014e306facc51ff6aa9e745c7ecb4955c0471ad648ba8c7f9b78a1828521
+oid sha256:718c6026792645e1479d1ca4f708b4dad9d4b0833cb47d16c5c9c805788c51e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06870229007633588,
+  "epoch": 0.07633587786259542,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 13.615,
       "eval_steps_per_second": 3.414,
       "step": 81
+    },
+    {
+      "epoch": 0.07124681933842239,
+      "grad_norm": NaN,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.0737913486005089,
+      "grad_norm": NaN,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.07633587786259542,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.07633587786259542,
+      "eval_loss": NaN,
+      "eval_runtime": 72.9706,
+      "eval_samples_per_second": 13.608,
+      "eval_steps_per_second": 3.412,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.388511147248845e+16,
+  "total_flos": 5.987234608054272e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null