Training in progress, step 150, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bab3f29a129f1ec7ef77918a336f7ea910099b3fc59edfbc465e96fd0afb8929
+oid sha256:4d1c6f2ace36bfaa9fa8b36fc128db4d46e020ee4601a54f4da7ccb636e802ea
 size 4027642

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f770008fe6d30ec720efa262a50dafd8210c481ff38fb343f4aff53cbd92df50
+oid sha256:74139b209595bf2e3f1b4f0211cb9b6f346abe0b16d7a26568cafcc0677daffe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0027010419269233106,
+  "epoch": 0.004051562890384966,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 191.418,
       "eval_steps_per_second": 95.715,
       "step": 100
+    },
+    {
+      "epoch": 0.0029711461196156416,
+      "grad_norm": NaN,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.0032412503123079727,
+      "grad_norm": NaN,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.0035113545050003037,
+      "grad_norm": NaN,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.003781458697692635,
+      "grad_norm": NaN,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.004051562890384966,
+      "grad_norm": NaN,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.004051562890384966,
+      "eval_loss": NaN,
+      "eval_runtime": 81.0952,
+      "eval_samples_per_second": 192.231,
+      "eval_steps_per_second": 96.122,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1052810687545344.0,
+  "total_flos": 1581207476502528.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null