Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01edb6ab277eeccbf0ee5f6be2dc0fded8fa915148248b3c8ddacc9e5294db12
+oid sha256:bddfa18d558da2a95549fd5c5c3106e83eb75f2273fb542749812555fcea5e1f
 size 64683604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe53da7d994df8630f89cf936617740f54c0387adf260c7a778e59f4186c4eb7
+oid sha256:a74f0fa67ad2ea453853ea9c83fafb9413743a4d7deb09428e0f1e45b1df8364
 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": 0.0009731570837726056,
+  "epoch": 0.0019463141675452112,
   "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": 13.065,
       "eval_steps_per_second": 6.533,
       "step": 3
+    },
+    {
+      "epoch": 0.0012975427783634742,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0016219284729543427,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0019463141675452112,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0019463141675452112,
+      "eval_loss": NaN,
+      "eval_runtime": 99.404,
+      "eval_samples_per_second": 13.058,
+      "eval_steps_per_second": 6.529,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1567738828947456.0,
+  "total_flos": 3135477657894912.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null