Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cbb206d2bd5dc2059b0f2b3b4dc9eb31e1ccf942a024794b9f43d90c2190467
+oid sha256:d8c9c750dc3f88bb3640705e7f35ef7c14563a8cf585855709ba483e025a3c7b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:812c7f0285cd035c5897a98c398f7073a006ab7c86852be1926fb49128c001d5
+oid sha256:7c972560184ed3c2f23dac5dce36d314f6d11a20e2d058da06a5bbdd4f904b2b
 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": 8.426670411853516e-05,
+  "epoch": 0.00016853340823707032,
   "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": 9.324,
       "eval_steps_per_second": 4.662,
       "step": 3
+    },
+    {
+      "epoch": 0.00011235560549138022,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.00014044450686422527,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00016853340823707032,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.00016853340823707032,
+      "eval_loss": NaN,
+      "eval_runtime": 1607.8443,
+      "eval_samples_per_second": 9.323,
+      "eval_steps_per_second": 4.662,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 924782124072960.0,
+  "total_flos": 1895803354349568.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null