Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0928c9182eeda93b4ea93e4953fdb9afcfbc625d997f09568bc66d790a47a7c6
+oid sha256:ea1392edc237c1f18dc3850b3ff2e9945d069d32792e1b2da99a030a21e000a6
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0132ff413f52f81c775255343583b0e4ac70e1f73d89ef8352cb7b196b37587a
+oid sha256:956987de089b073e2784139a2f760af6bee6dbe2414c1fa2144f86d49c78dea7
 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": 0.00018063040009633623,
+  "epoch": 0.0002709456001445043,
   "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": 23.753,
       "eval_steps_per_second": 11.877,
       "step": 6
+    },
+    {
+      "epoch": 0.0002107354667790589,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.00024084053346178162,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0002709456001445043,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0002709456001445043,
+      "eval_loss": NaN,
+      "eval_runtime": 586.997,
+      "eval_samples_per_second": 23.828,
+      "eval_steps_per_second": 11.915,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 371755025694720.0,
+  "total_flos": 561587379240960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null