Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d948451e5922cc308cd8a10cf8844777bbe3eeeccc2dc67b9a6ce79b72d2e0
+oid sha256:25c76f349cf7916b8a526a00272e9e9774693824420168081f1d0d14d27ec477
 size 557912620

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfaabb05a95a662d8c7f2b443387597a915505fea3f5272e20297b4175887ada
+oid sha256:819d88698704f79e890c488b84907a8531f4eec5200d16b4066829b7b5b359bb
 size 1115579834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240e6a8ec9456bd6463406cd6d4517d0833e6ea5d37262a07e1e58851593128e
+oid sha256:a44a7d01e7a1e697bee1e2fac088fa92d9b6d757f620da1c95ab22db79f4ff3d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c8da14363ee970453deb0abfc423b52e8f626b95704d94bd6a144124c361a4
+oid sha256:1d9ea3d03d222f67be1c1c3ebbcd1c13a13e443e03074a240028e9e3ec52cb98
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3526093088857546,
+  "epoch": 0.7052186177715092,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,34 @@
       "learning_rate": 3.2387165021156564e-05,
       "loss": 0.0013,
       "step": 1000
+    },
+    {
+      "epoch": 0.4407616361071932,
+      "grad_norm": 9583.7470703125,
+      "learning_rate": 2.7979548660084627e-05,
+      "loss": 0.0011,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5289139633286318,
+      "grad_norm": 0.8403513431549072,
+      "learning_rate": 2.3571932299012694e-05,
+      "loss": 0.0009,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6170662905500706,
+      "grad_norm": 1.9435118436813354,
+      "learning_rate": 1.9164315937940765e-05,
+      "loss": 0.0007,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7052186177715092,
+      "grad_norm": 1.006479263305664,
+      "learning_rate": 1.4756699576868829e-05,
+      "loss": 0.0009,
+      "step": 2000
     }
   ],
   "logging_steps": 250,
@@ -55,7 +83,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2438945832960000.0,
+  "total_flos": 4877891665920000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null