Training in progress, step 95000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0288be0c1235e777c27dd9047a36eedfe264bb488a4c0e0bed0c34a7672a27
+oid sha256:1b573222d9b319a3d487c0c578817b5195c7686b855d96946d89e10146ac2e0d
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7eecde17cb6e9aa8cd7b4552f91801dbea59bd9f43564420f17d5094be8ecd0
+oid sha256:066b9aec11086e6d754392502c67c132273bd9e8c2079983d1d403167bb1695a
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05d03c073f727785714559ddd963d68941172e2660ea09c2fa916687be15d30
+oid sha256:a4f99dc9e42edd3c1d095b5820fe5dc8c8ab1d01c4fa0832268eb95913430929
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a253357a0f0cc613ebf9506b97610f90339ebe2be5f931702becbaf171e782d
+oid sha256:f42287d0188e0ca7518e7347c2cbcdfa5474b9d7f4514b250faba8c2dce24e04
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c584c5bb4a0182ed3950a23caf01b869cbb053591dee4ffba4c62961e6b03ec
+oid sha256:529d4dd93aa83bf4a63eacb44b8ee831aacefd449fd87e79fd39cb07ed7f8418
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.835625979453248,
-  "global_step": 90000,
+  "epoch": 8.270938533867318,
+  "global_step": 95000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1230,11 +1230,79 @@
       "eval_samples_per_second": 302.358,
       "eval_steps_per_second": 4.777,
       "step": 90000
+    },
+    {
+      "epoch": 7.88,
+      "learning_rate": 1.2020863570515961e-05,
+      "loss": 0.4009,
+      "step": 90500
+    },
+    {
+      "epoch": 7.92,
+      "learning_rate": 1.1815845782614282e-05,
+      "loss": 0.4028,
+      "step": 91000
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 1.162157941946108e-05,
+      "loss": 0.4015,
+      "step": 91500
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 1.1438112413374588e-05,
+      "loss": 0.4016,
+      "step": 92000
+    },
+    {
+      "epoch": 8.05,
+      "learning_rate": 1.1265490032093274e-05,
+      "loss": 0.4015,
+      "step": 92500
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 1.1103754867606732e-05,
+      "loss": 0.4009,
+      "step": 93000
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 1.0953237511280449e-05,
+      "loss": 0.4,
+      "step": 93500
+    },
+    {
+      "epoch": 8.18,
+      "learning_rate": 1.0813640603098685e-05,
+      "loss": 0.4012,
+      "step": 94000
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 1.0684751669305436e-05,
+      "loss": 0.4014,
+      "step": 94500
+    },
+    {
+      "epoch": 8.27,
+      "learning_rate": 1.0566893240808188e-05,
+      "loss": 0.3998,
+      "step": 95000
+    },
+    {
+      "epoch": 8.27,
+      "eval_loss": 0.38168150186538696,
+      "eval_runtime": 17.1028,
+      "eval_samples_per_second": 292.35,
+      "eval_steps_per_second": 4.619,
+      "step": 95000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 4.238744869891214e+21,
+  "total_flos": 4.474219316873905e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7eecde17cb6e9aa8cd7b4552f91801dbea59bd9f43564420f17d5094be8ecd0
+oid sha256:066b9aec11086e6d754392502c67c132273bd9e8c2079983d1d403167bb1695a
 size 449471589