Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ee8db568ffb64f56be15b0eb94dcdfc0b6a10f75e6778f3e333be38b91bff3a
+oid sha256:a1c6135421fc4f0b07e3dbdd216f62b67327a5be8122640f01bda0ed7335e0a5
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cb24b3f3f4c4a67fab43264a5041d5eddbe696e430c47d0bfd9e5f90902b3a0
+oid sha256:da371ed384dd48ba3f51b4afee7d61db3dfdb18617828b0330774642ccc5f0e8
 size 14244

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": 0.012042147516307075,
+  "epoch": 0.01806322127446061,
   "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": 6.246,
       "eval_steps_per_second": 3.123,
       "step": 6
+    },
+    {
+      "epoch": 0.014049172102358254,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014,
+      "loss": 3.1369,
+      "step": 7
+    },
+    {
+      "epoch": 0.016056196688409432,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016,
+      "loss": 3.4106,
+      "step": 8
+    },
+    {
+      "epoch": 0.01806322127446061,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018,
+      "loss": 3.3776,
+      "step": 9
+    },
+    {
+      "epoch": 0.01806322127446061,
+      "eval_loss": 3.369473695755005,
+      "eval_runtime": 33.7306,
+      "eval_samples_per_second": 6.226,
+      "eval_steps_per_second": 3.113,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1235242526441472.0,
+  "total_flos": 1852863789662208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null