Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4706180c011789fa7ce7d894b4ab7382341f53742f948c67aae277e220bf7321
+oid sha256:b8663c5a1b351b7e358ac35fd06d575dd41d4bb2e8ae839c297516acb56ea026
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5bc72d35a952567b178439a440ebd6225ccee20b3b5a9f8d26721e60808459
+oid sha256:2cb741a1b6c12fea007d9d6a85137f098d7e74d9ca251e354a6aa242a9cce0ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00019504900606277329,
+  "epoch": 0.00039009801212554657,
   "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": 29.661,
       "eval_steps_per_second": 14.833,
       "step": 3
+    },
+    {
+      "epoch": 0.000260065341417031,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.00032508167677128876,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00039009801212554657,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.00039009801212554657,
+      "eval_loss": NaN,
+      "eval_runtime": 194.9611,
+      "eval_samples_per_second": 33.222,
+      "eval_steps_per_second": 16.614,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 47035066613760.0,
+  "total_flos": 94070133227520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null