Training in progress, step 100000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b573222d9b319a3d487c0c578817b5195c7686b855d96946d89e10146ac2e0d
+oid sha256:c92252b3cd9dd7d41fd1e3e6f9555d8d595a367dcb3a12f334d23aa6d7f4be3a
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066b9aec11086e6d754392502c67c132273bd9e8c2079983d1d403167bb1695a
+oid sha256:9629991174b98bdc9c2004c23d8143dcb55e825714893b4fe878d212e3404d14
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f99dc9e42edd3c1d095b5820fe5dc8c8ab1d01c4fa0832268eb95913430929
+oid sha256:523db574847f79a66ca0c3ee491e7cb5f8ccda9a30ceceeeeb9a387933819100
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f42287d0188e0ca7518e7347c2cbcdfa5474b9d7f4514b250faba8c2dce24e04
+oid sha256:487b0fc983d2aea61209ee5a057485c5c06df1d2510fa4762ccbc37b48f414e6
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529d4dd93aa83bf4a63eacb44b8ee831aacefd449fd87e79fd39cb07ed7f8418
+oid sha256:5b9d090099ba96f6dced98144320a4b9bf47460bb589afeb514879b05a2d09ba
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.270938533867318,
-  "global_step": 95000,
+  "epoch": 8.706251088281386,
+  "global_step": 100000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1298,11 +1298,79 @@
       "eval_samples_per_second": 292.35,
       "eval_steps_per_second": 4.619,
       "step": 95000
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 1.0460094397410629e-05,
+      "loss": 0.4004,
+      "step": 95500
+    },
+    {
+      "epoch": 8.36,
+      "learning_rate": 1.0364381490129294e-05,
+      "loss": 0.4006,
+      "step": 96000
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 1.0279778134691878e-05,
+      "loss": 0.4007,
+      "step": 96500
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 1.0206441030895691e-05,
+      "loss": 0.4001,
+      "step": 97000
+    },
+    {
+      "epoch": 8.49,
+      "learning_rate": 1.0144094343341912e-05,
+      "loss": 0.4005,
+      "step": 97500
+    },
+    {
+      "epoch": 8.53,
+      "learning_rate": 1.0092911560189286e-05,
+      "loss": 0.3995,
+      "step": 98000
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 1.0052905310023697e-05,
+      "loss": 0.401,
+      "step": 98500
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 1.0024085463788748e-05,
+      "loss": 0.4002,
+      "step": 99000
+    },
+    {
+      "epoch": 8.66,
+      "learning_rate": 1.0006483210534733e-05,
+      "loss": 0.4,
+      "step": 99500
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 1.0000032344694547e-05,
+      "loss": 0.3999,
+      "step": 100000
+    },
+    {
+      "epoch": 8.71,
+      "eval_loss": 0.3816235363483429,
+      "eval_runtime": 41.2453,
+      "eval_samples_per_second": 121.226,
+      "eval_steps_per_second": 1.915,
+      "step": 100000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 4.474219316873905e+21,
+  "total_flos": 4.7097123842386664e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066b9aec11086e6d754392502c67c132273bd9e8c2079983d1d403167bb1695a
+oid sha256:9629991174b98bdc9c2004c23d8143dcb55e825714893b4fe878d212e3404d14
 size 449471589