Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b5fcf15bd242e44d655a57970dccb28a1a1a885e86a328e6fa1aebc857fd3a4
+oid sha256:dc9a0e2e05d9eacf5c069bd04337e5de4a41461f12fee894e25c6f74e61bcfb7
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb4f9fc7124e96f82e322ff0279a3fb1e3cde199fba8ef2ed0889f90c1080507
+oid sha256:dc3871a6dd003957f74dd719d49313b586008e765ed00522a4df1d6a65f799a8
 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": 0.0004994797086368366,
+  "epoch": 0.0009989594172736733,
   "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": 4.677,
       "eval_steps_per_second": 2.339,
       "step": 3
+    },
+    {
+      "epoch": 0.0006659729448491155,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008324661810613944,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009989594172736733,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009989594172736733,
+      "eval_loss": NaN,
+      "eval_runtime": 541.4238,
+      "eval_samples_per_second": 4.671,
+      "eval_steps_per_second": 2.336,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 783761302093824.0,
+  "total_flos": 1567522604187648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null