Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d85208888a99b70fbec4ca5624a934038556ec60b88e38f62139b309d62364
+oid sha256:c8c2c76b2af6161081d482f52bf213543512394491d116e6825476f517b88d68
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ae55c6f46b108addfd38220def7ec37523099dd2d6785ae58da64488fc14d0
+oid sha256:c98d0dc8a323e35694dd8d2b73ddcc61302fe5580936a3cc2762ec9e18b76f71
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdeae7f85339ec5b7c2107666d9ec4a5e7484ceb3a98a29ce8e0d77f5f16ef4f
+oid sha256:22b7476485e31d3ae54029159afe6ba29b64be20b981bfb2216839a09160d527
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010948905109489052,
+  "epoch": 0.016423357664233577,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 4.142,
       "eval_steps_per_second": 1.04,
       "step": 6
+    },
+    {
+      "epoch": 0.012773722627737226,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.014598540145985401,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.016423357664233577,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.016423357664233577,
+      "eval_loss": NaN,
+      "eval_runtime": 111.6503,
+      "eval_samples_per_second": 4.138,
+      "eval_steps_per_second": 1.039,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6875127295705088e+16,
+  "total_flos": 2.531269094355763e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null