Training in progress, step 90, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ae6b63bb2e23ca5393ba65e8024db166d018ceffb643c15b2c9af1bde132ce
+oid sha256:083558a113db9efb2cf479f3d7de4395a6e412d5fdfa2d4acf791f1c858b34ed
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63e29ed66e6543dff1960b19b8b4946890f74c62337f6c46d1c621b30742df02
+oid sha256:141fe731c27da354e082db328d428f949999b83b115b46b9ef67c59bbcdc3469
 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": 0.4668587896253602,
+  "epoch": 0.5187319884726225,
   "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": 9.484,
       "eval_steps_per_second": 1.198,
       "step": 81
+    },
+    {
+      "epoch": 0.484149855907781,
+      "grad_norm": NaN,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.5014409221902018,
+      "grad_norm": NaN,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.5187319884726225,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.5187319884726225,
+      "eval_loss": NaN,
+      "eval_runtime": 30.8746,
+      "eval_samples_per_second": 9.49,
+      "eval_steps_per_second": 1.198,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9031462535757824e+17,
+  "total_flos": 2.1120281594560512e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null