Training in progress, step 10500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f50dfec7b348b398b16d49e0dd1b5d02944005adb5fa282d41d880b7743a85f
+oid sha256:d2eb707efd45838c999c2a5555ec9f4e3948d1f4bebf0270a24ea3404256d4cc
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a47f14c217dde4efbeced6d0ecf1b11f4ee8587e56f4b26d3f7cdb603d5217
+oid sha256:e3af0e4724c98927d8a051181e73393d7a65a3c727af1c5a91618fb92dd27408
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f3f920fee151f842583919a34cd3a487b202dcc03fce7b250a1108c0d5893e
+oid sha256:8305955eac22add53d91f06fc3781aadbba74448cb0b21c58a2f9dadbea85a43
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f157fb66e9f6bdea8c4e5f6e07a539c2ce54fcc9de0e2acd2a8bb7cdbb367f5
+oid sha256:4e3714e917b57b234e811d02cff6475eee9087a5c2b589dd59d17c8602540672
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6666666666666666,
+  "epoch": 0.7,
   "eval_steps": 500,
-  "global_step": 10000,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -707,6 +707,41 @@
       "learning_rate": 1.555688888888889e-05,
       "loss": 0.0694,
       "step": 10000
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 0.16695012152194977,
+      "learning_rate": 1.5512444444444446e-05,
+      "loss": 0.0722,
+      "step": 10100
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.07470796257257462,
+      "learning_rate": 1.5468e-05,
+      "loss": 0.0699,
+      "step": 10200
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 0.12706786394119263,
+      "learning_rate": 1.5423555555555557e-05,
+      "loss": 0.068,
+      "step": 10300
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.14934158325195312,
+      "learning_rate": 1.5379111111111112e-05,
+      "loss": 0.0643,
+      "step": 10400
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.34316006302833557,
+      "learning_rate": 1.5334666666666667e-05,
+      "loss": 0.0683,
+      "step": 10500
     }
   ],
   "logging_steps": 100,
@@ -726,7 +761,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.43583156224e+16,
+  "total_flos": 2.557623140352e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null