Training in progress, step 250000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7a9d643fd165284c9d847051c171fdeb050ea172840f575f2857a0e22839d20
+oid sha256:2b3fa44918a15a26f0dab31b5f2ce128986e98b2f074732782ee3bafd1d9f761
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd72965584365f2678a23f0540f0298ff143ae7b5281c747f80901158bab7a9
+oid sha256:583b5b9533b7175aefb9aba5e44a7adf86d285464db931d087f2683ca555c176
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
+oid sha256:de53c7a27a7e52e3981c6372b23063352d2f700802159bb4f6fe1f3f73d293d5
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
+oid sha256:de53c7a27a7e52e3981c6372b23063352d2f700802159bb4f6fe1f3f73d293d5
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
+oid sha256:de53c7a27a7e52e3981c6372b23063352d2f700802159bb4f6fe1f3f73d293d5
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
+oid sha256:de53c7a27a7e52e3981c6372b23063352d2f700802159bb4f6fe1f3f73d293d5
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
+oid sha256:de53c7a27a7e52e3981c6372b23063352d2f700802159bb4f6fe1f3f73d293d5
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
+oid sha256:de53c7a27a7e52e3981c6372b23063352d2f700802159bb4f6fe1f3f73d293d5
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
+oid sha256:de53c7a27a7e52e3981c6372b23063352d2f700802159bb4f6fe1f3f73d293d5
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
+oid sha256:de53c7a27a7e52e3981c6372b23063352d2f700802159bb4f6fe1f3f73d293d5
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0271bea6149ce925d63296b146082378537ccb6d117e16172c4343f0cd0f3277
+oid sha256:91f2b533d9be93c6cd8cde2522968f253e93ba31177b2564989d91807f307fa6
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.705882352941176,
-  "global_step": 240000,
+  "epoch": 15.318627450980392,
+  "global_step": 250000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4806,11 +4806,211 @@
       "eval_samples_per_second": 748.984,
       "eval_steps_per_second": 11.984,
       "step": 240000
+    },
+    {
+      "epoch": 14.74,
+      "learning_rate": 1.232616311222906e-05,
+      "loss": 0.4402,
+      "step": 240500
+    },
+    {
+      "epoch": 14.77,
+      "learning_rate": 1.2088029177672978e-05,
+      "loss": 0.4401,
+      "step": 241000
+    },
+    {
+      "epoch": 14.77,
+      "eval_loss": 0.8008501529693604,
+      "eval_runtime": 1.2829,
+      "eval_samples_per_second": 779.48,
+      "eval_steps_per_second": 12.472,
+      "step": 241000
+    },
+    {
+      "epoch": 14.8,
+      "learning_rate": 1.1862708161623889e-05,
+      "loss": 0.4402,
+      "step": 241500
+    },
+    {
+      "epoch": 14.83,
+      "learning_rate": 1.165020992035296e-05,
+      "loss": 0.4401,
+      "step": 242000
+    },
+    {
+      "epoch": 14.83,
+      "eval_loss": 0.8015211224555969,
+      "eval_runtime": 1.2647,
+      "eval_samples_per_second": 790.696,
+      "eval_steps_per_second": 12.651,
+      "step": 242000
+    },
+    {
+      "epoch": 14.86,
+      "learning_rate": 1.1450543749221632e-05,
+      "loss": 0.4401,
+      "step": 242500
+    },
+    {
+      "epoch": 14.89,
+      "learning_rate": 1.126371838227509e-05,
+      "loss": 0.4401,
+      "step": 243000
+    },
+    {
+      "epoch": 14.89,
+      "eval_loss": 0.8009896278381348,
+      "eval_runtime": 1.3003,
+      "eval_samples_per_second": 769.043,
+      "eval_steps_per_second": 12.305,
+      "step": 243000
+    },
+    {
+      "epoch": 14.92,
+      "learning_rate": 1.1089741991860081e-05,
+      "loss": 0.44,
+      "step": 243500
+    },
+    {
+      "epoch": 14.95,
+      "learning_rate": 1.0928622188267536e-05,
+      "loss": 0.44,
+      "step": 244000
+    },
+    {
+      "epoch": 14.95,
+      "eval_loss": 0.799572765827179,
+      "eval_runtime": 1.3134,
+      "eval_samples_per_second": 761.387,
+      "eval_steps_per_second": 12.182,
+      "step": 244000
+    },
+    {
+      "epoch": 14.98,
+      "learning_rate": 1.0780366019399665e-05,
+      "loss": 0.4401,
+      "step": 244500
+    },
+    {
+      "epoch": 15.01,
+      "learning_rate": 1.0644979970461512e-05,
+      "loss": 0.4402,
+      "step": 245000
+    },
+    {
+      "epoch": 15.01,
+      "eval_loss": 0.8014461398124695,
+      "eval_runtime": 1.3153,
+      "eval_samples_per_second": 760.258,
+      "eval_steps_per_second": 12.164,
+      "step": 245000
+    },
+    {
+      "epoch": 15.04,
+      "learning_rate": 1.0522469963677483e-05,
+      "loss": 0.4401,
+      "step": 245500
+    },
+    {
+      "epoch": 15.07,
+      "learning_rate": 1.0412841358032126e-05,
+      "loss": 0.44,
+      "step": 246000
+    },
+    {
+      "epoch": 15.07,
+      "eval_loss": 0.800745964050293,
+      "eval_runtime": 1.3042,
+      "eval_samples_per_second": 766.776,
+      "eval_steps_per_second": 12.268,
+      "step": 246000
+    },
+    {
+      "epoch": 15.1,
+      "learning_rate": 1.0316098949035847e-05,
+      "loss": 0.44,
+      "step": 246500
+    },
+    {
+      "epoch": 15.13,
+      "learning_rate": 1.0232246968514984e-05,
+      "loss": 0.44,
+      "step": 247000
+    },
+    {
+      "epoch": 15.13,
+      "eval_loss": 0.7984172701835632,
+      "eval_runtime": 1.3184,
+      "eval_samples_per_second": 758.509,
+      "eval_steps_per_second": 12.136,
+      "step": 247000
+    },
+    {
+      "epoch": 15.17,
+      "learning_rate": 1.0161289084426815e-05,
+      "loss": 0.44,
+      "step": 247500
+    },
+    {
+      "epoch": 15.2,
+      "learning_rate": 1.0103228400699063e-05,
+      "loss": 0.44,
+      "step": 248000
+    },
+    {
+      "epoch": 15.2,
+      "eval_loss": 0.8008962273597717,
+      "eval_runtime": 1.3201,
+      "eval_samples_per_second": 757.502,
+      "eval_steps_per_second": 12.12,
+      "step": 248000
+    },
+    {
+      "epoch": 15.23,
+      "learning_rate": 1.0058067457094136e-05,
+      "loss": 0.44,
+      "step": 248500
+    },
+    {
+      "epoch": 15.26,
+      "learning_rate": 1.0025808229097982e-05,
+      "loss": 0.4399,
+      "step": 249000
+    },
+    {
+      "epoch": 15.26,
+      "eval_loss": 0.8005866408348083,
+      "eval_runtime": 1.3752,
+      "eval_samples_per_second": 727.163,
+      "eval_steps_per_second": 11.635,
+      "step": 249000
+    },
+    {
+      "epoch": 15.29,
+      "learning_rate": 1.0006452127833747e-05,
+      "loss": 0.4399,
+      "step": 249500
+    },
+    {
+      "epoch": 15.32,
+      "learning_rate": 1e-05,
+      "loss": 0.4399,
+      "step": 250000
+    },
+    {
+      "epoch": 15.32,
+      "eval_loss": 0.8015783429145813,
+      "eval_runtime": 1.3631,
+      "eval_samples_per_second": 733.637,
+      "eval_steps_per_second": 11.738,
+      "step": 250000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 16,
-  "total_flos": 3.843891921728687e+21,
+  "total_flos": 4.004049914090876e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd72965584365f2678a23f0540f0298ff143ae7b5281c747f80901158bab7a9
+oid sha256:583b5b9533b7175aefb9aba5e44a7adf86d285464db931d087f2683ca555c176
 size 25761253