Training in progress, step 85, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fec14f6a01d61272bacee525bac8b5fbe0d1cc5cfe555534176434a00372067
+oid sha256:f220adf6445faa3084119deeca55d2d287f74f40538df7e9218a2aeee61a809a
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c72d9f3ca2f0dee1e321d24a425433f913801087616a40c32e828d954463375
+oid sha256:7ee335a62849ee2439378e9094b922b6e35c167d78196a6c3c8df14be4850d15
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f4e77fd2a3bb3f08929494d77da2f57f8781f91a45852bcf8f71a5777dd088c
+oid sha256:b383ad1d61ff4e9bbd86bd276c043e414782d2bb7de68ada3e289a786eb79681
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07472014284733192,
+  "epoch": 0.0934001785591649,
   "eval_steps": 50,
-  "global_step": 68,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -499,6 +499,125 @@
       "learning_rate": 0.00012518479547691435,
       "loss": 0.0,
       "step": 68
+    },
+    {
+      "epoch": 0.07581896847743974,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012420442717428804,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.07691779410754755,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012320907072649044,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.07801661973765538,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001221990293287378,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.0791154453677632,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012117461064942435,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.08021427099787103,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012013612673640363,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.08131309662797885,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011908389392193547,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.08241192225808668,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011801823272632844,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.08351074788819449,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011693946776030599,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.08460957351830231,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011584792762612703,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.08570839914841014,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011474394481749035,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.08680722477851796,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011362785561825406,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.08790605040862579,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001125,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.08900487603873361,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011136072151847529,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.09010370166884142,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011021036720894179,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.09120252729894925,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010904928748046599,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.09230135292905707,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001078778360091808,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.0934001785591649,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010669636963055245,
+      "loss": 0.0,
+      "step": 85
     }
   ],
   "logging_steps": 1,
@@ -518,7 +637,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.0051762314765926e+17,
+  "total_flos": 4.978120149832827e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null