Training in progress, step 27000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa391b775f0d5dcb24018c3990fb7c29ef27625dac44264f09f0201ea61bae3
+oid sha256:70459aba67b6c424f3d63d95f80b4c8948f435a8ba82c9a37542207539196d32
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bdafb74e8684c8e1f92c0028b2980a9bdebe0cc49ff0249647d05a17b3e6460
+oid sha256:1fe49df5f886ba45eef1e19dafef5a8690b37670e9ebb31cb5e88b4d03624781
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da56afab166cb01805fb08f77164c54bb9f01376e88d545d9f7d4a3e6c7f528
+oid sha256:a2b04015a5468c4c71a68f8a7c3be6fa1a5ab0c6b493b0d95c32db53b793b58b
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a1bac9c3d7424a0ec2af16484aea0b93a1f8e34ad9ea9ff8b01d003b64aca4
+oid sha256:02c81cde7407b27a7c82314fa2d256172ae55e83eaeee2d0ecd83c9012414a84
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8462f87da0cd589acb4f3244d880cd8e2e7f0f4e43c89dd5fa9ee942ead34988
+oid sha256:d2413d92bc1698d7edcc7c6350b8070ca85dbe7faf1af7244026dee62bdfae63
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.000599999999999,
+  "epoch": 9.000933333333332,
   "eval_steps": 500,
-  "global_step": 26500,
+  "global_step": 27000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3718,6 +3718,76 @@
       "learning_rate": 1.0363658133396608e-06,
       "loss": 0.8027437591552734,
       "step": 26500
+    },
+    {
+      "epoch": 2.002066666666667,
+      "grad_norm": 1.4865727424621582,
+      "learning_rate": 1.0073909157623346e-06,
+      "loss": 0.2347201919555664,
+      "step": 26550
+    },
+    {
+      "epoch": 2.0037333333333334,
+      "grad_norm": 1.0282039642333984,
+      "learning_rate": 9.788127466822905e-07,
+      "loss": 0.21864686965942381,
+      "step": 26600
+    },
+    {
+      "epoch": 2.0054,
+      "grad_norm": 1.0267033576965332,
+      "learning_rate": 9.506321163682908e-07,
+      "loss": 0.21448984146118164,
+      "step": 26650
+    },
+    {
+      "epoch": 2.0070666666666668,
+      "grad_norm": 1.1616917848587036,
+      "learning_rate": 9.23401560845214e-07,
+      "loss": 0.22048572540283204,
+      "step": 26700
+    },
+    {
+      "epoch": 2.0087333333333333,
+      "grad_norm": 1.1124871969223022,
+      "learning_rate": 8.960104036060512e-07,
+      "loss": 0.22924829483032227,
+      "step": 26750
+    },
+    {
+      "epoch": 2.0104,
+      "grad_norm": 1.0723026990890503,
+      "learning_rate": 8.690191328044084e-07,
+      "loss": 0.26663469314575194,
+      "step": 26800
+    },
+    {
+      "epoch": 2.0120666666666667,
+      "grad_norm": 1.8677761554718018,
+      "learning_rate": 8.42428513716168e-07,
+      "loss": 0.42245777130126955,
+      "step": 26850
+    },
+    {
+      "epoch": 2.013733333333333,
+      "grad_norm": 1.3421262502670288,
+      "learning_rate": 8.162393002576496e-07,
+      "loss": 0.5923210144042969,
+      "step": 26900
+    },
+    {
+      "epoch": 2.0154,
+      "grad_norm": 2.0107803344726562,
+      "learning_rate": 7.904522349642312e-07,
+      "loss": 0.5859238433837891,
+      "step": 26950
+    },
+    {
+      "epoch": 3.0007333333333333,
+      "grad_norm": 1.6371034383773804,
+      "learning_rate": 7.650680489693051e-07,
+      "loss": 0.557980842590332,
+      "step": 27000
     }
   ],
   "logging_steps": 50,
@@ -3737,7 +3807,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.37679163923329e+18,
+  "total_flos": 2.4235554483508593e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null