Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426fb6497d944b0aa8245c758156eaac4a22f1f1574289c2d572c29951f3bcfa
+oid sha256:05713d8928ad86b405c17af13543bcdfc84daeadd48cd7a31e7d37d7568c17ab
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dfe83e9b2716fb9c0f5219cb43fb11fc429a3b4410b8f04ad6016c8b897425c
+oid sha256:e6223edaadb920eb413aba43890fa90fb2bf1afb4f0f6594525529911f2f6e2e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002932551319648094,
+  "epoch": 0.005865102639296188,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 6.367,
       "eval_steps_per_second": 3.184,
       "step": 10
+    },
+    {
+      "epoch": 0.0035190615835777126,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.004398826979472141,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.004398826979472141,
+      "eval_loss": NaN,
+      "eval_runtime": 225.4801,
+      "eval_samples_per_second": 6.369,
+      "eval_steps_per_second": 3.184,
+      "step": 15
+    },
+    {
+      "epoch": 0.005278592375366569,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.005865102639296188,
+      "eval_loss": NaN,
+      "eval_runtime": 225.3841,
+      "eval_samples_per_second": 6.371,
+      "eval_steps_per_second": 3.186,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6592310406021120.0,
+  "total_flos": 1.318462081204224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null