Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cafaf7ce4a678a006bf42a6d1d04944fc99a3c2e07dc45d9986c3cdf19347af
+oid sha256:f66472385d43d815e5cb5e2c50cac3ce7b887080c0eb53b6922dc899a81b16cb
 size 579417298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d365eac8d88fb1b8ab6e1019454a8dd28f2f39e275bb7487e21429b7a134f101
+oid sha256:bc9c68dcb18f645e27de5c2ff3cb21e9981d7a10327546a5e42d2fd234ac3b36
 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": 0.011071132023249377,
+  "epoch": 0.022142264046498755,
   "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": 7.365,
       "eval_steps_per_second": 3.692,
       "step": 10
+    },
+    {
+      "epoch": 0.013285358427899253,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.016606698034874065,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.016606698034874065,
+      "eval_loss": NaN,
+      "eval_runtime": 51.8055,
+      "eval_samples_per_second": 7.354,
+      "eval_steps_per_second": 3.687,
+      "step": 15
+    },
+    {
+      "epoch": 0.01992803764184888,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.022142264046498755,
+      "eval_loss": NaN,
+      "eval_runtime": 51.8339,
+      "eval_samples_per_second": 7.35,
+      "eval_steps_per_second": 3.685,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6657663597281280.0,
+  "total_flos": 1.315294515560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null