Training in progress, step 48, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9545bc14be0e7babd203c01c8ca481ef646f996e3c0ed59dbce3cec9e4b51b84
+oid sha256:d9cbb0d2f004fe5975a67decf7fc53a11e3766500be5d1095e98e9dfa85fd633
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7222a8bc78f2f195453d152b96260a204ab54c7585bb8a13af06def19205c49
+oid sha256:1e46ed7f51c2a3a3ae3be0a5ed2fae9fb201c81bbc92c8a554135c02f50f5ab9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
+oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04772234273318872,
+  "epoch": 0.052060737527114966,
   "eval_steps": 4,
-  "global_step": 44,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -411,6 +411,42 @@
       "eval_samples_per_second": 7.648,
       "eval_steps_per_second": 3.834,
       "step": 44
+    },
+    {
+      "epoch": 0.04880694143167028,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.049891540130151846,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.0509761388286334,
+      "grad_norm": NaN,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.052060737527114966,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.052060737527114966,
+      "eval_loss": NaN,
+      "eval_runtime": 50.9078,
+      "eval_samples_per_second": 7.641,
+      "eval_steps_per_second": 3.83,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -430,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2297308888629248e+16,
+  "total_flos": 1.3415246060322816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null