Training in progress, step 27500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70459aba67b6c424f3d63d95f80b4c8948f435a8ba82c9a37542207539196d32
+oid sha256:4122d9c259d5ec8bfc0f78998d825ce75679813bf4905aff951b39cdb5423bc2
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe49df5f886ba45eef1e19dafef5a8690b37670e9ebb31cb5e88b4d03624781
+oid sha256:2f70642558652ee03e9cfb1752bd4116d9c5b6312df9e6c268ee352ab8dae456
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b04015a5468c4c71a68f8a7c3be6fa1a5ab0c6b493b0d95c32db53b793b58b
+oid sha256:7c57924b6164adec227a2d9c1652f2a70968203e42f6929697d1eec808a321ec
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c81cde7407b27a7c82314fa2d256172ae55e83eaeee2d0ecd83c9012414a84
+oid sha256:0c5ebfa8b962a4907f78be196b47502a68d1b60e3ea66ea389d941fd83ad44fc
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2413d92bc1698d7edcc7c6350b8070ca85dbe7faf1af7244026dee62bdfae63
+oid sha256:6c627524736369b95bea8c7f2381019a25c8dc97068539fa73d4629470e57519
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.000933333333332,
+  "epoch": 10.001133333333332,
   "eval_steps": 500,
-  "global_step": 27000,
+  "global_step": 27500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3788,6 +3788,76 @@
       "learning_rate": 7.650680489693051e-07,
       "loss": 0.557980842590332,
       "step": 27000
+    },
+    {
+      "epoch": 3.0024,
+      "grad_norm": 1.261396050453186,
+      "learning_rate": 7.400874619835291e-07,
+      "loss": 0.3162060737609863,
+      "step": 27050
+    },
+    {
+      "epoch": 3.0040666666666667,
+      "grad_norm": 1.6194435358047485,
+      "learning_rate": 7.155111822744376e-07,
+      "loss": 0.29564001083374025,
+      "step": 27100
+    },
+    {
+      "epoch": 3.005733333333333,
+      "grad_norm": 1.2328189611434937,
+      "learning_rate": 6.913399066463582e-07,
+      "loss": 0.29919641494750976,
+      "step": 27150
+    },
+    {
+      "epoch": 3.0074,
+      "grad_norm": 1.320834994316101,
+      "learning_rate": 6.675743204206458e-07,
+      "loss": 0.2997510528564453,
+      "step": 27200
+    },
+    {
+      "epoch": 3.0090666666666666,
+      "grad_norm": 1.3888412714004517,
+      "learning_rate": 6.442150974162642e-07,
+      "loss": 0.28582775115966796,
+      "step": 27250
+    },
+    {
+      "epoch": 3.0107333333333335,
+      "grad_norm": 1.2989741563796997,
+      "learning_rate": 6.212628999306719e-07,
+      "loss": 0.362674560546875,
+      "step": 27300
+    },
+    {
+      "epoch": 3.0124,
+      "grad_norm": 1.8883610963821411,
+      "learning_rate": 5.987183787210437e-07,
+      "loss": 0.4638848876953125,
+      "step": 27350
+    },
+    {
+      "epoch": 3.0140666666666664,
+      "grad_norm": 1.7672468423843384,
+      "learning_rate": 5.765821729858322e-07,
+      "loss": 0.6259365463256836,
+      "step": 27400
+    },
+    {
+      "epoch": 3.0157333333333334,
+      "grad_norm": 1.3275811672210693,
+      "learning_rate": 5.548549103466338e-07,
+      "loss": 0.6669663238525391,
+      "step": 27450
+    },
+    {
+      "epoch": 4.000933333333333,
+      "grad_norm": 1.4393675327301025,
+      "learning_rate": 5.335372068303929e-07,
+      "loss": 0.460877799987793,
+      "step": 27500
     }
   ],
   "logging_steps": 50,
@@ -3807,7 +3877,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4235554483508593e+18,
+  "total_flos": 2.4700701075631227e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null