Training in progress, step 36000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37250fd25ac520b5292199088ef27546da88796721ea4eb40695113400ccfa7b
+oid sha256:61dce64509302181dbd0102d94f8e63119a5e468f1ab30981e6b95a40a16a0f7
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad6751a841c8864f7c7c1ceb77b425b700e73e59e70f845d753c55a66facc1b6
+oid sha256:8aee7a7bb130bc58eccba7310fd2e1c0ff9bc9a9460551dab2ac36a3c09f233f
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2920a601864c0632a370a1ac1dcdad5f1e27e566971eb45ef713c65fc1086f00
+oid sha256:d52b5d54b1b44c26afdd58b8aa610c5f355b531f51747715e0d2588d67b0dd03
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc3d0c5d65fdec57f5db591d38345123ff409f36daf00beadf6d67548eb0bd8
+oid sha256:3545c32cd08bfe14c5940277cc90a883188128e319d14e37ac1ae89581718ce4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3666666666666667,
+  "epoch": 2.4,
   "eval_steps": 500,
-  "global_step": 35500,
+  "global_step": 36000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2508,6 +2508,41 @@
       "learning_rate": 4.228444444444445e-06,
       "loss": 0.0529,
       "step": 35500
+    },
+    {
+      "epoch": 2.3733333333333335,
+      "grad_norm": 0.1506161242723465,
+      "learning_rate": 4.184e-06,
+      "loss": 0.0508,
+      "step": 35600
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.16037747263908386,
+      "learning_rate": 4.139555555555556e-06,
+      "loss": 0.0517,
+      "step": 35700
+    },
+    {
+      "epoch": 2.3866666666666667,
+      "grad_norm": 0.2298995554447174,
+      "learning_rate": 4.095111111111111e-06,
+      "loss": 0.0516,
+      "step": 35800
+    },
+    {
+      "epoch": 2.3933333333333335,
+      "grad_norm": 0.18646371364593506,
+      "learning_rate": 4.0506666666666675e-06,
+      "loss": 0.0552,
+      "step": 35900
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.1472606658935547,
+      "learning_rate": 4.006222222222223e-06,
+      "loss": 0.0523,
+      "step": 36000
     }
   ],
   "logging_steps": 100,
@@ -2527,7 +2562,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.647202045952e+16,
+  "total_flos": 8.768993624064e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null