Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6517a209ac5d5a1c26f06016c074944deebfb838c486c25d12b5c411ff56d5ee
+oid sha256:b590db5b2a28d85c0b82d5580062e98db2d95e7e75fafdcf726fbbacea9f32be
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70701041128af6937348c92468e75d858b8823688a9ee96c3d463a6a67a0f8a
+oid sha256:1220a35005eeb73eee58f3c7ed357c175737e6d8476f3d618898c86e0d179e11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b52924c88c1c80163d374a6650253dd74b8b46052a3da6fc5e4076e57b5effa
+oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01735357917570499,
+  "epoch": 0.021691973969631236,
   "eval_steps": 4,
-  "global_step": 16,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -159,6 +159,42 @@
       "eval_samples_per_second": 7.653,
       "eval_steps_per_second": 3.836,
       "step": 16
+    },
+    {
+      "epoch": 0.01843817787418655,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.019522776572668113,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.020607375271149676,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.021691973969631236,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.021691973969631236,
+      "eval_loss": NaN,
+      "eval_runtime": 50.8357,
+      "eval_samples_per_second": 7.652,
+      "eval_steps_per_second": 3.836,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -178,7 +214,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4471748686774272.0,
+  "total_flos": 5589685858467840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null