Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e6652d4f4cf847b56ee09f55ddc4aa71f4b641ef2a2d758460b17d2b05b1154
+oid sha256:7f7ef68707a5f5b8d06ff149d9ae9f755003b6075ac855fea279d57ada67d327
 size 4682414560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c36679d5b9dae75f3ef6d4ee031e17c0bdffe90022cc65eb8474f3006a513d
+oid sha256:a11644c814da57640facf34ba5391afecb738e0fa2fc22650c666da3e040419f
 size 2498736801

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4678e09f8fcc61d92df0e65077038de31aeb262232e6a2dbf1a3ffba70ea64
+oid sha256:c178d88dd64302d0da55c078b7a67c25e5a7c7b6abe69bb648b63b0b5924756a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3aba3a7d5dd6e1fe4ca9aeb5413dce931776ed2a811c0c689ce3b6ea4e2b48
+oid sha256:f9d3f6fc42961c8152448a892f3924f49c78cdff3507356794e0f3ef837d1210
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00636504969398887,
+  "epoch": 0.00666814729846453,
   "eval_steps": 500,
-  "global_step": 10500,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1478,6 +1478,76 @@
       "learning_rate": 9.936379827282901e-05,
       "loss": 3.2523733520507814,
       "step": 10500
+    },
+    {
+      "epoch": 0.006395359454436436,
+      "grad_norm": 2.3049190044403076,
+      "learning_rate": 9.936076729747326e-05,
+      "loss": 3.269808044433594,
+      "step": 10550
+    },
+    {
+      "epoch": 0.006425669214884002,
+      "grad_norm": 1.8658502101898193,
+      "learning_rate": 9.935773632211751e-05,
+      "loss": 3.2778192138671876,
+      "step": 10600
+    },
+    {
+      "epoch": 0.006455978975331568,
+      "grad_norm": 2.3192155361175537,
+      "learning_rate": 9.935470534676176e-05,
+      "loss": 3.1481027221679687,
+      "step": 10650
+    },
+    {
+      "epoch": 0.006486288735779134,
+      "grad_norm": 1.8061124086380005,
+      "learning_rate": 9.935167437140603e-05,
+      "loss": 3.1986090087890626,
+      "step": 10700
+    },
+    {
+      "epoch": 0.0065165984962267,
+      "grad_norm": 2.502110004425049,
+      "learning_rate": 9.934864339605028e-05,
+      "loss": 3.0882998657226564,
+      "step": 10750
+    },
+    {
+      "epoch": 0.006546908256674266,
+      "grad_norm": 2.817471504211426,
+      "learning_rate": 9.934561242069454e-05,
+      "loss": 3.1530471801757813,
+      "step": 10800
+    },
+    {
+      "epoch": 0.006577218017121832,
+      "grad_norm": 2.1066269874572754,
+      "learning_rate": 9.934258144533879e-05,
+      "loss": 3.195494384765625,
+      "step": 10850
+    },
+    {
+      "epoch": 0.006607527777569398,
+      "grad_norm": 2.0811686515808105,
+      "learning_rate": 9.933955046998305e-05,
+      "loss": 3.16893310546875,
+      "step": 10900
+    },
+    {
+      "epoch": 0.006637837538016964,
+      "grad_norm": 1.965430736541748,
+      "learning_rate": 9.93365194946273e-05,
+      "loss": 3.1695233154296876,
+      "step": 10950
+    },
+    {
+      "epoch": 0.00666814729846453,
+      "grad_norm": 2.6144657135009766,
+      "learning_rate": 9.933348851927155e-05,
+      "loss": 3.2110235595703127,
+      "step": 11000
     }
   ],
   "logging_steps": 50,
@@ -1497,7 +1567,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.94406667566039e+16,
+  "total_flos": 4.130209137310925e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null