Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eae9012d93014c9027053f343471d5a0897862eb73b3aa44b0687fa37eabc56
+oid sha256:68baf906fea8389f8e8559a8decd0ab2b60bfca8f3d8f028d93b109d6d36a5c5
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eace36f2feb1498de4e674ea457b3390625579e85bed978663b88f5c1282e76
+oid sha256:7d5029f735a686d99c7ee71d90b3734881048580cc5fb383880200df26eabe22
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94b1a91810562429d557b8e7351faf37318bcc85fdd6894e29a36576f9f1604
+oid sha256:63aab5945fa6a4f19ef11eca5b6add2fab56216a2af2a42b2f4db10b37425e8e
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1917c9f69ccf15e380d9f4d351dbf92bf96c11b80c90f99f57a0469639c9d08
+oid sha256:6f00b18c22d88348c8087e818de79203b3e3b7bc34baa496b7a99bac8f2b2926
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed3db87d9ab6acb1ce4ebfafc1e1df3a006d0a11ad32694145d43298254810c
+oid sha256:a69ec5a2f174981f959eb44ef9f358dd4df695a387539e1ef6b96f489d42e404
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.000766666666667,
+  "epoch": 9.001333333333333,
   "eval_steps": 500,
-  "global_step": 17500,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2458,6 +2458,76 @@
       "learning_rate": 1.14494109172198e-05,
       "loss": 1.1471074676513673,
       "step": 17500
+    },
+    {
+      "epoch": 4.0026,
+      "grad_norm": 1.5319304466247559,
+      "learning_rate": 1.1371860445532802e-05,
+      "loss": 0.8557035827636719,
+      "step": 17550
+    },
+    {
+      "epoch": 4.004266666666667,
+      "grad_norm": 1.7613927125930786,
+      "learning_rate": 1.1294412841462897e-05,
+      "loss": 0.8202173614501953,
+      "step": 17600
+    },
+    {
+      "epoch": 4.005933333333333,
+      "grad_norm": 1.6619144678115845,
+      "learning_rate": 1.121707030086014e-05,
+      "loss": 0.8459001159667969,
+      "step": 17650
+    },
+    {
+      "epoch": 4.0076,
+      "grad_norm": 1.6346546411514282,
+      "learning_rate": 1.1139835016595775e-05,
+      "loss": 0.8195448303222657,
+      "step": 17700
+    },
+    {
+      "epoch": 4.009266666666667,
+      "grad_norm": 1.7639893293380737,
+      "learning_rate": 1.1062709178500023e-05,
+      "loss": 0.815630111694336,
+      "step": 17750
+    },
+    {
+      "epoch": 4.010933333333333,
+      "grad_norm": 1.736759901046753,
+      "learning_rate": 1.0985694973300004e-05,
+      "loss": 0.8889206695556641,
+      "step": 17800
+    },
+    {
+      "epoch": 4.0126,
+      "grad_norm": 1.7116466760635376,
+      "learning_rate": 1.0908794584557749e-05,
+      "loss": 0.8401109313964844,
+      "step": 17850
+    },
+    {
+      "epoch": 4.014266666666667,
+      "grad_norm": 1.6388331651687622,
+      "learning_rate": 1.0832010192608289e-05,
+      "loss": 1.072819595336914,
+      "step": 17900
+    },
+    {
+      "epoch": 4.015933333333333,
+      "grad_norm": 1.7291067838668823,
+      "learning_rate": 1.075534397449782e-05,
+      "loss": 1.0581070709228515,
+      "step": 17950
+    },
+    {
+      "epoch": 5.0015,
+      "grad_norm": 2.015186309814453,
+      "learning_rate": 1.0678798103921991e-05,
+      "loss": 1.088599395751953,
+      "step": 18000
     }
   ],
   "logging_steps": 50,
@@ -2477,7 +2547,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5247432982037135e+18,
+  "total_flos": 1.5722381772810486e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null