Training in progress, step 25500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3737e237db90c5232468e4d7aabb1556d27175ef52bd9ab944e75f0b65dedc7b
+oid sha256:a1238136af3e4a64c6bdfbbf614ceac7656c9b3b5d4d992d18af67c8b2eb5384
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dab6b44b4870bc5015e01bb9f2e217df28a763d1a692d0171e36246f156c8b5d
+oid sha256:a875d97e6ab9df1a7b3a478f269b8b6cb0dff0ee70c2b8f9b07526d529c9f736
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b9e6063de9ae98690b8b14fa3a559b833389d99881e1d6756d2a8f11ad80a5e
+oid sha256:d8e9bb6fca478bc46cc9aedfa2ff02f10ac93eb3ef848bec3ae25bcbbb5f8b50
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c73dc79ecd03a599fc2b5f8c7eff6116bb5dc54e45c322928c523dd89c33e7
+oid sha256:ed5ce3bb450508d9ce41dfe7bf644477c71a67379a8c95a958028da580bc80ac
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59b1a3a74319a6eae863dee6842ff3e0fc5765eba00c434de7faacdd29e2f451
+oid sha256:9cbc3f6d7e8afe37a06e20c2bdff03b3436d05f525ae467301d60d9b622a94d2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.001333333333333,
+  "epoch": 10.001366666666666,
   "eval_steps": 500,
-  "global_step": 25000,
+  "global_step": 25500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3508,6 +3508,76 @@
       "learning_rate": 2.0848056607906236e-06,
       "loss": 0.5570061111450195,
       "step": 25000
+    },
+    {
+      "epoch": 5.003166666666667,
+      "grad_norm": 1.8605475425720215,
+      "learning_rate": 2.0443679088382326e-06,
+      "loss": 0.7983790588378906,
+      "step": 25050
+    },
+    {
+      "epoch": 5.004833333333333,
+      "grad_norm": 1.5200269222259521,
+      "learning_rate": 2.0042974842670273e-06,
+      "loss": 0.8496729278564453,
+      "step": 25100
+    },
+    {
+      "epoch": 5.0065,
+      "grad_norm": 1.671268343925476,
+      "learning_rate": 1.9645955231824477e-06,
+      "loss": 0.8661923217773437,
+      "step": 25150
+    },
+    {
+      "epoch": 5.008166666666667,
+      "grad_norm": 1.4824550151824951,
+      "learning_rate": 1.926046169477867e-06,
+      "loss": 0.8316961669921875,
+      "step": 25200
+    },
+    {
+      "epoch": 5.009833333333333,
+      "grad_norm": 1.636396884918213,
+      "learning_rate": 1.8870770769158634e-06,
+      "loss": 0.8602359008789062,
+      "step": 25250
+    },
+    {
+      "epoch": 5.0115,
+      "grad_norm": 1.7281094789505005,
+      "learning_rate": 1.8484797713576217e-06,
+      "loss": 0.8439288330078125,
+      "step": 25300
+    },
+    {
+      "epoch": 5.013166666666667,
+      "grad_norm": 1.910600185394287,
+      "learning_rate": 1.8102553471416584e-06,
+      "loss": 0.9095307922363282,
+      "step": 25350
+    },
+    {
+      "epoch": 5.014833333333334,
+      "grad_norm": 1.7145682573318481,
+      "learning_rate": 1.772404888034283e-06,
+      "loss": 0.8995892333984375,
+      "step": 25400
+    },
+    {
+      "epoch": 5.0165,
+      "grad_norm": 4.496703624725342,
+      "learning_rate": 1.7349294671988892e-06,
+      "loss": 1.0104307556152343,
+      "step": 25450
+    },
+    {
+      "epoch": 6.001533333333334,
+      "grad_norm": 2.30837082862854,
+      "learning_rate": 1.6978301471655071e-06,
+      "loss": 1.1597572326660157,
+      "step": 25500
     }
   ],
   "logging_steps": 50,
@@ -3527,7 +3597,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2361609733164483e+18,
+  "total_flos": 2.2834083861004616e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null