Training in progress, step 63, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f54f6e5448fb67009edd773e07b13a88c890c68e6ca6cbb079076b2e4cc94a89
+oid sha256:693ff4204f2c381359f37672e2e08211d45de79c7eea5ecc791a3a399031be52
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd34d866559ba0b2220d9c09d28cc16510cf1b3e842bf83a1fadbc16d8c6204e
+oid sha256:a57addfbff74916a19f69367dbaba8fb11c41a22dbd8d8d5643cf9660a77e109
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3112391930835735,
+  "epoch": 0.3631123919308357,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 9.515,
       "eval_steps_per_second": 1.202,
       "step": 54
+    },
+    {
+      "epoch": 0.3285302593659942,
+      "grad_norm": NaN,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.345821325648415,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.3631123919308357,
+      "grad_norm": NaN,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.3631123919308357,
+      "eval_loss": NaN,
+      "eval_runtime": 30.8588,
+      "eval_samples_per_second": 9.495,
+      "eval_steps_per_second": 1.199,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2648959856082944e+17,
+  "total_flos": 1.4737778914885632e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null