Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2505e88b0a82388da6d8385ddc2b423be64283d12610f87792ca2a058e44892a
+oid sha256:c5f2187baabb9904c275d78cd86bbd2fc337fb0d54d6cdc0739b09108b51e7bf
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ec5726b17102540d1cf518de614c69ef3cd64ac316a2b8ee07030241290bfc
+oid sha256:08003f75f4afbceab970a79e288a43d47b7a5e300cd1f34cc0b2840ab4a130fb
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7240fd7a7fef23174636d23a112dffe186d187eae2f35ae7e0e17c53ea3679db
+oid sha256:c2aa0a679fd9b985f20fc73a4b26c11f7f4f8e724cefce7fed3d2c20549aa497
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4953537583c171fed6606a5b67ff141ae8b37530eae865be18180585423f010
+oid sha256:c9f10853fba0de0cc442d7091c6f2905c41b6f09944c21256911c835caa91508
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3117206982543641,
+  "epoch": 0.41562759767248547,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -28,6 +28,13 @@
       "learning_rate": 1.79260182876143e-05,
       "loss": 0.483,
       "step": 1500
+    },
+    {
+      "epoch": 0.41562759767248547,
+      "grad_norm": 1.4630037546157837,
+      "learning_rate": 1.7233305624826823e-05,
+      "loss": 0.4516,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -47,7 +54,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1826873671680000.0,
+  "total_flos": 2435831562240000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null