Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d79c1a532ea05af8704526321055148bcaf6490fdda70fbc1e53a55128001d
+oid sha256:3f36e5a0b6d5e742c466322d76efee0b73370b5485024c67c77eac11f086f754
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:462f771addb789ccbc36694a1e92a30ad3301a708b5a9db1b053f5ea8e61d598
+oid sha256:3ab2d96aa7c14ac25f979268944fa39d11946c62f201537bea6172cdd553e3a3
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1fa92a659ce7b24b7bee26ef1c5b22af6de24bc71dca8f081d8a4d5484f829f
+oid sha256:d2b52d82f73e570b1698336d070d85ea4c32ca359687f3058f1f92bb220326cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ecad4e077043e9a33ee2c9fa361fb3094bb16b01b0de4558b66dacd551cb9c6
+oid sha256:b12b10cf3f340469d3096b69b56bd466b59c9a88eb55d010a305dd7220038dd5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20781379883624274,
+  "epoch": 0.41562759767248547,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,6 +14,13 @@
       "learning_rate": 1.917206982543641e-05,
       "loss": 0.7834,
       "step": 500
+    },
+    {
+      "epoch": 0.41562759767248547,
+      "grad_norm": 0.9406130313873291,
+      "learning_rate": 1.834081463009144e-05,
+      "loss": 0.4895,
+      "step": 1000
     }
   ],
   "logging_steps": 500,
@@ -33,7 +40,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1217915781120000.0,
+  "total_flos": 2435831562240000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null