Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e12d395d228986d4722c9bfdd3b7c1a0c87813d6c1948380328534f75ad454cd
+oid sha256:4c271689f6760d4359c2a43653eb4d2901456cbdb4b87714c22ec9cdaa2c8b8e
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad3401b5dfde1c4ac0b81be604349a5d0c27404fba8d352372bd54950216bb24
+oid sha256:5b2573858366c51da080dc52026b5cf706984e6769263fae62f35276ad423d25
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f87436d1ed788958cb08087900b45d6f1fbde14c0d7db3fa0e7c937f406062a
+oid sha256:265f7ddb321b2fa01d3a22602c4d8e894508ea8d4458f230512f39344ac67fcf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d166d24f789387f6695cee2a14320335faa00c9fa99f8038d6fcfa9ae735c9d
+oid sha256:944535d8118858ad045305f7f05f43c95ec4aaef08aedf918a1fec60acb21f30
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1666666666666667,
+  "epoch": 1.2,
   "eval_steps": 500,
-  "global_step": 17500,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1240,6 +1240,41 @@
       "learning_rate": 1.2224444444444445e-05,
       "loss": 0.0571,
       "step": 17500
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 0.16585813462734222,
+      "learning_rate": 1.218e-05,
+      "loss": 0.0646,
+      "step": 17600
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.204860657453537,
+      "learning_rate": 1.2135555555555556e-05,
+      "loss": 0.0632,
+      "step": 17700
+    },
+    {
+      "epoch": 1.1866666666666668,
+      "grad_norm": 0.25248029828071594,
+      "learning_rate": 1.209111111111111e-05,
+      "loss": 0.0603,
+      "step": 17800
+    },
+    {
+      "epoch": 1.1933333333333334,
+      "grad_norm": 0.1613234281539917,
+      "learning_rate": 1.204666666666667e-05,
+      "loss": 0.0611,
+      "step": 17900
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.29864856600761414,
+      "learning_rate": 1.2002222222222225e-05,
+      "loss": 0.0591,
+      "step": 18000
     }
   ],
   "logging_steps": 100,
@@ -1259,7 +1294,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.26270523392e+16,
+  "total_flos": 4.384496812032e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null