Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960cd9845c564bfc5e3103367fd2ab34c17fd8f491a601ce226f7d51fce43bb8
+oid sha256:93a48d4497c53c5c4cadb807b99facccc26970afcf17ac4796756576006b5f31
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da77caaffdbca7b449e54ff89926b8f62d34c209002a887f7c8145c9abb77cfb
+oid sha256:f85ce3223ea1b2aa9d427fce1a014052d88cc5c50755364cd241e510cd1068b3
 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": 0.00022631688135337495,
+  "epoch": 0.00033947532203006245,
   "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": 25.748,
       "eval_steps_per_second": 12.875,
       "step": 6
+    },
+    {
+      "epoch": 0.00026403636157893746,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0003017558418044999,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.00033947532203006245,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.00033947532203006245,
+      "eval_loss": NaN,
+      "eval_runtime": 433.2824,
+      "eval_samples_per_second": 25.764,
+      "eval_steps_per_second": 12.883,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1262268960473088.0,
+  "total_flos": 1995199324618752.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null