Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9464a83d744bb16ab356dc5a575efb989f0629cccfb5f0fbb4e7755291759440
+oid sha256:c65f999e702fe3084aaa846642f45627e309e8d5aaf897c75578ab6215d293d1
 size 61226900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afc96819c810a0b10fbf28ef176daa0e9d10caff3ef1bde0f8923e657df640be
+oid sha256:56936bf022d16e9f88e50706d60b84a176826f79b38151948b0f46f5315b095b
 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": 0.0007655014034192396,
+  "epoch": 0.0011482521051288594,
   "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": 2.651,
       "eval_steps_per_second": 2.651,
       "step": 6
+    },
+    {
+      "epoch": 0.0008930849706557795,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0010206685378923194,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0011482521051288594,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0011482521051288594,
+      "eval_loss": NaN,
+      "eval_runtime": 311.3988,
+      "eval_samples_per_second": 2.653,
+      "eval_steps_per_second": 2.653,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1106646474424320.0,
+  "total_flos": 1659969711636480.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null