Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2babfb128c109bc73ba25362a120790a678a9557822a57433bfa3e3561da88
+oid sha256:33d85208888a99b70fbec4ca5624a934038556ec60b88e38f62139b309d62364
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d495eddf9e2d6d72d53ef10f36943daa4a1692907b67d0b202402e2700358da
+oid sha256:51ae55c6f46b108addfd38220def7ec37523099dd2d6785ae58da64488fc14d0
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87777cac382d33db7fc5c6740fb81b3c03d5c99c763afc019ed939bceba9e53
+oid sha256:bdeae7f85339ec5b7c2107666d9ec4a5e7484ceb3a98a29ce8e0d77f5f16ef4f
 size 14512

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": 0.005474452554744526,
+  "epoch": 0.010948905109489052,
   "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": 4.14,
       "eval_steps_per_second": 1.04,
       "step": 3
+    },
+    {
+      "epoch": 0.0072992700729927005,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.009124087591240875,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.010948905109489052,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.010948905109489052,
+      "eval_loss": NaN,
+      "eval_runtime": 111.5362,
+      "eval_samples_per_second": 4.142,
+      "eval_steps_per_second": 1.04,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8437563647852544.0,
+  "total_flos": 1.6875127295705088e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null