Training in progress, step 1600, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b1414405c6569082ce4c89ffc35e400efabe527d1fbfaf811626cb9b7be419
+oid sha256:40095725fc0786a3c912798bc42b665ef77af7017cc5a4773c5369b9374cfaaf
 size 2471218763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad85e280d5a5bb25ea74c35cf3277ee0dc8ea6fc4405d02f6e2c57f852fa261
+oid sha256:684e33945d5e9615d67982f907b4bd5b55d412c2b48b33613fdd4ef1c4d053c4
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4d4bc05efa244f95b3aea452c294bae8df3a3f92048af90e4124e1d08e77d7
+oid sha256:12b3905bb99561ce66746740b1de5588d55bd3f6f12bc854dc34c827aebf5528
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03,
+  "epoch": 1.002,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1058,6 +1058,76 @@
       "learning_rate": 0.0002915891783567134,
       "loss": 77.63518676757812,
       "step": 1500
+    },
+    {
+      "epoch": 1.0002,
+      "grad_norm": NaN,
+      "learning_rate": 0.00029152905811623243,
+      "loss": 107136583467008.0,
+      "step": 1510
+    },
+    {
+      "epoch": 1.0004,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002914689378757515,
+      "loss": 3583383070310.4,
+      "step": 1520
+    },
+    {
+      "epoch": 1.0006,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002914088176352705,
+      "loss": 36528589478297.6,
+      "step": 1530
+    },
+    {
+      "epoch": 1.0008,
+      "grad_norm": NaN,
+      "learning_rate": 0.00029134869739478957,
+      "loss": 1132657744281.6,
+      "step": 1540
+    },
+    {
+      "epoch": 1.001,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002912885771543086,
+      "loss": 9138627379.2,
+      "step": 1550
+    },
+    {
+      "epoch": 1.0012,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002912284569138276,
+      "loss": 1681122891975884.8,
+      "step": 1560
+    },
+    {
+      "epoch": 1.0014,
+      "grad_norm": NaN,
+      "learning_rate": 0.00029116833667334666,
+      "loss": 929300570596966.4,
+      "step": 1570
+    },
+    {
+      "epoch": 1.0016,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002911082164328657,
+      "loss": 9330961573478.4,
+      "step": 1580
+    },
+    {
+      "epoch": 1.0018,
+      "grad_norm": NaN,
+      "learning_rate": 0.00029104809619238476,
+      "loss": 63892658271027.2,
+      "step": 1590
+    },
+    {
+      "epoch": 1.002,
+      "grad_norm": NaN,
+      "learning_rate": 0.00029098797595190375,
+      "loss": 3103321489408.0,
+      "step": 1600
     }
   ],
   "logging_steps": 10,
@@ -1077,7 +1147,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.503701404508672e+16,
+  "total_flos": 2.66012131885056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null