Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef25062af99cde9561d5f50a7e9da247c6fe4a1a6cd543bbd9dc06f879854f50
+oid sha256:f80602c146e4bed13b9016fd045b86fa2ea00d1091aedc80502b744ff7fe4863
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca82a561ff77829be4f53f199829857bccfb693ef73aa2d0668f096c355cee4
+oid sha256:7824cda9b09088755df9c1fad3a0258c249f3861ebeb526074259caef60b1595
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013062646274424427,
+  "epoch": 0.0026125292548848855,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 4.979,
       "eval_steps_per_second": 2.489,
       "step": 3
+    },
+    {
+      "epoch": 0.001741686169923257,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0021771077124040712,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0026125292548848855,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0026125292548848855,
+      "eval_loss": NaN,
+      "eval_runtime": 777.5883,
+      "eval_samples_per_second": 4.974,
+      "eval_steps_per_second": 2.487,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5683151464497152e+16,
+  "total_flos": 3.1366302928994304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null