Training in progress, step 25000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3030d4ce44a28d2687854bece3d36dd11a2483143dc2362c64bdaf84a148a35c
+oid sha256:b8cc3b5dc11d4b2e43886ec06772cc1df8fb96be6f1f9a0270f9f6e971f6d0e2
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8336f578c2856a2611344b57de4fde614962159ed2c75eff7de5a881717f1aa8
+oid sha256:3972de8e85ec92a8ee5bab9415d6a3d3f55feb08f92a26b7359e3c1d72344bc5
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a44025f64c6f7ad3ba883de4c1f4995d535cdd50931b810e0a7d00e22e5cdc
+oid sha256:6fbd5b30263f6cc98f2bb34e98264f7dd554a2e53f93ad44d0666e3bd6bfb80c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9ad9a351ae61b83248fa17cb95ac2021f5fe42e6699ef47e0f8bde893c34bb
+oid sha256:c7471c9521805c24a8ce63003bd5efeaf8bf27814fa393d151be750f3265d98e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6333333333333333,
+  "epoch": 1.6666666666666665,
   "eval_steps": 500,
-  "global_step": 24500,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1730,6 +1730,41 @@
       "learning_rate": 9.114666666666668e-06,
       "loss": 0.0613,
       "step": 24500
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.25385352969169617,
+      "learning_rate": 9.070222222222223e-06,
+      "loss": 0.0599,
+      "step": 24600
+    },
+    {
+      "epoch": 1.6466666666666665,
+      "grad_norm": 0.1330012083053589,
+      "learning_rate": 9.025777777777778e-06,
+      "loss": 0.0601,
+      "step": 24700
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 0.40342622995376587,
+      "learning_rate": 8.981333333333333e-06,
+      "loss": 0.0599,
+      "step": 24800
+    },
+    {
+      "epoch": 1.6600000000000001,
+      "grad_norm": 0.21778804063796997,
+      "learning_rate": 8.93688888888889e-06,
+      "loss": 0.0537,
+      "step": 24900
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.17448577284812927,
+      "learning_rate": 8.892444444444445e-06,
+      "loss": 0.0566,
+      "step": 25000
     }
   ],
   "logging_steps": 100,
@@ -1749,7 +1784,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.967787327488e+16,
+  "total_flos": 6.0895789056e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null