Training in progress, step 35500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c3b650aacadef454b8db2ad2f4748bd2cc9caa9988d9586a8661ac87876f39
+oid sha256:37250fd25ac520b5292199088ef27546da88796721ea4eb40695113400ccfa7b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3300d0ac109580f5456c1f0fcf9e3276c33da9efc5df83c8e4bc2c715849e9ac
+oid sha256:ad6751a841c8864f7c7c1ceb77b425b700e73e59e70f845d753c55a66facc1b6
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c640612ca6874adba07e3028442a5de517f2bd82ce8dc7d5cdd1701c4e1b1ee5
+oid sha256:2920a601864c0632a370a1ac1dcdad5f1e27e566971eb45ef713c65fc1086f00
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec6550e2fb94624e4937a6e7d695ee415ac08cd206a873e9804651b6a923373
+oid sha256:0cc3d0c5d65fdec57f5db591d38345123ff409f36daf00beadf6d67548eb0bd8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3333333333333335,
+  "epoch": 2.3666666666666667,
   "eval_steps": 500,
-  "global_step": 35000,
+  "global_step": 35500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2473,6 +2473,41 @@
       "learning_rate": 4.450222222222222e-06,
       "loss": 0.0558,
       "step": 35000
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.23494431376457214,
+      "learning_rate": 4.405777777777778e-06,
+      "loss": 0.0521,
+      "step": 35100
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 0.19245880842208862,
+      "learning_rate": 4.3613333333333335e-06,
+      "loss": 0.0516,
+      "step": 35200
+    },
+    {
+      "epoch": 2.3533333333333335,
+      "grad_norm": 0.30625805258750916,
+      "learning_rate": 4.3173333333333336e-06,
+      "loss": 0.0519,
+      "step": 35300
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.30782145261764526,
+      "learning_rate": 4.272888888888889e-06,
+      "loss": 0.0495,
+      "step": 35400
+    },
+    {
+      "epoch": 2.3666666666666667,
+      "grad_norm": 0.25636398792266846,
+      "learning_rate": 4.228444444444445e-06,
+      "loss": 0.0529,
+      "step": 35500
     }
   ],
   "logging_steps": 100,
@@ -2492,7 +2527,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.52541046784e+16,
+  "total_flos": 8.647202045952e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null