Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66cae8324741bfb1c3cbb4cfed2559c012d8b417990bdb0c6e1b400f774dcc4e
+oid sha256:8367a24eb06a34cbf04ec05d49423cacadb43f1fbc7c9b46cd3bc8f7d202aeea
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9055ac327c15e228dd6a4caa71093d65f0ca825571af69e5994cc7332daa9be
+oid sha256:69cfb99a1d47731eb0bd0f0aa8008f24af3b21461df86591e07ee79decd04b36
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eba248c4c107e3630aeadfd11e69cd930737cf324d325de259160a726c9e173
+oid sha256:59297a887ee86d9ae2f8461a820add9f102e062ed6b208e7b0f014f86659cc1d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b394b8045eb22d77503865620f9a9d287ea2ba93ffd3839a0365feff6f4d8b
+oid sha256:7ece32524ff12cd47152c7073cf4a24f61bf2d3f6e989a1d942aaad706c29e5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9666666666666668,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 29500,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2080,6 +2080,41 @@
       "learning_rate": 6.893333333333334e-06,
       "loss": 0.0545,
       "step": 29500
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 0.3285749852657318,
+      "learning_rate": 6.849333333333333e-06,
+      "loss": 0.0566,
+      "step": 29600
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.2452673316001892,
+      "learning_rate": 6.80488888888889e-06,
+      "loss": 0.0501,
+      "step": 29700
+    },
+    {
+      "epoch": 1.9866666666666668,
+      "grad_norm": 0.06861041486263275,
+      "learning_rate": 6.760444444444445e-06,
+      "loss": 0.0554,
+      "step": 29800
+    },
+    {
+      "epoch": 1.9933333333333332,
+      "grad_norm": 0.2544171214103699,
+      "learning_rate": 6.716000000000001e-06,
+      "loss": 0.058,
+      "step": 29900
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.22868148982524872,
+      "learning_rate": 6.671555555555556e-06,
+      "loss": 0.0569,
+      "step": 30000
     }
   ],
   "logging_steps": 100,
@@ -2099,7 +2134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.185703108608e+16,
+  "total_flos": 7.30749468672e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null