Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0716e8cd0716ed13e89d4d72d43d071a71741c79c2d481e68fc4ba0145fb0c6d
+oid sha256:9a84a251ecd9c8fb67c63a59a8d224783f20b00322aa91714b6858fd0de1eb9d
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc403af9e11857d6f34f26a5e387272147fa59a1882e228f6c5703956aa2070d
+oid sha256:4858ec41c922c440b7e4fefd04746beb3e5a8234c224a3464e7eba0d89a0309e
 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": 0.0005170965031348976,
+  "epoch": 0.0007756447547023463,
   "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": 36.143,
       "eval_steps_per_second": 18.072,
       "step": 6
+    },
+    {
+      "epoch": 0.0006032792536573804,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006894620041798634,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007756447547023463,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007756447547023463,
+      "eval_loss": NaN,
+      "eval_runtime": 121.2632,
+      "eval_samples_per_second": 40.293,
+      "eval_steps_per_second": 20.146,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 218901324496896.0,
+  "total_flos": 324298258513920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null