Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54bc834b0b102b5738c6f329b2c9726532c034ff47b44d3f4004945a23f50cee
+oid sha256:699bfd4aca3d2e5c4e4cde8bfd7897c32108dbe7daf07b2c7d9432ca1b0543aa
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ea44352ddfa8203e0768cb21a45faa7a448031317064d98fe10d093bef34c2d
+oid sha256:2a5a6242c7c02c25e5b316f544047c9044c9faa2fd1a8c1cfa264ca91871fe3a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa0f75a1f3e346be25756b578158b09a68943f0b9f1cfe29f97939687f864ef
+oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.039045553145336226,
+  "epoch": 0.04338394793926247,
   "eval_steps": 4,
-  "global_step": 36,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -339,6 +339,42 @@
       "eval_samples_per_second": 7.646,
       "eval_steps_per_second": 3.833,
       "step": 36
+    },
+    {
+      "epoch": 0.04013015184381779,
+      "grad_norm": NaN,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.04121475054229935,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.04229934924078091,
+      "grad_norm": NaN,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.04338394793926247,
+      "grad_norm": NaN,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04338394793926247,
+      "eval_loss": NaN,
+      "eval_runtime": 50.7973,
+      "eval_samples_per_second": 7.658,
+      "eval_steps_per_second": 3.839,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -358,7 +394,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0061434545242112e+16,
+  "total_flos": 1.117937171693568e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null