Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f2187baabb9904c275d78cd86bbd2fc337fb0d54d6cdc0739b09108b51e7bf
+oid sha256:17e1a7f1302ef5433741a3ee69a87b4b4e833bfd4fd9c9a254b9140e53e23766
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08003f75f4afbceab970a79e288a43d47b7a5e300cd1f34cc0b2840ab4a130fb
+oid sha256:91d9926d3f133af82ae7e4a4ccbc0aea9433213d10d4c711532077bc5fa16be8
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2aa0a679fd9b985f20fc73a4b26c11f7f4f8e724cefce7fed3d2c20549aa497
+oid sha256:30dc60382167de3458c5c0efd3fe3f40ca4cde794d0fe66663ca9a8bcee0d065
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9f10853fba0de0cc442d7091c6f2905c41b6f09944c21256911c835caa91508
+oid sha256:5d9e707c93d930eada5d65eeb12d5abae9fff751224d824839cf7f999a563f5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.41562759767248547,
+  "epoch": 0.5195344970906068,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,13 @@
       "learning_rate": 1.7233305624826823e-05,
       "loss": 0.4516,
       "step": 2000
+    },
+    {
+      "epoch": 0.5195344970906068,
+      "grad_norm": 0.854028046131134,
+      "learning_rate": 1.6540592962039347e-05,
+      "loss": 0.4387,
+      "step": 2500
     }
   ],
   "logging_steps": 500,
@@ -54,7 +61,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2435831562240000.0,
+  "total_flos": 3044789452800000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null