Training in progress, step 950000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c72fdd0154d524cda12334954eb1e4f193d30dc2134990578a195ba70ede7f
+oid sha256:555f1620da14174bf24cf8a2c50966c673718f13caf9ff9216cb282d58986be2
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0068dc2eb70214cc7f3762f96ca920a8342113b2f223dfdea92c9f41e6012f4
+oid sha256:92c3d51ab918ac4532e1d6eeab8c0b6a6ea719ff69a5dc804d4995968ab632fc
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
+oid sha256:0f56e4ab7d580b4bb483b5af1e3c9da40dee5bbb1c90ae3bbc38d37f787d0e30
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
+oid sha256:0f56e4ab7d580b4bb483b5af1e3c9da40dee5bbb1c90ae3bbc38d37f787d0e30
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
+oid sha256:0f56e4ab7d580b4bb483b5af1e3c9da40dee5bbb1c90ae3bbc38d37f787d0e30
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
+oid sha256:0f56e4ab7d580b4bb483b5af1e3c9da40dee5bbb1c90ae3bbc38d37f787d0e30
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
+oid sha256:0f56e4ab7d580b4bb483b5af1e3c9da40dee5bbb1c90ae3bbc38d37f787d0e30
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
+oid sha256:0f56e4ab7d580b4bb483b5af1e3c9da40dee5bbb1c90ae3bbc38d37f787d0e30
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
+oid sha256:0f56e4ab7d580b4bb483b5af1e3c9da40dee5bbb1c90ae3bbc38d37f787d0e30
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
+oid sha256:0f56e4ab7d580b4bb483b5af1e3c9da40dee5bbb1c90ae3bbc38d37f787d0e30
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dab84d4b75593cd9349f424c4371ea8ac2493751bc544a294c8ef74a18b08e9
+oid sha256:76d771b6aa86b6db5c1d3a18a5ba01d5f7ff8a339c98c29586734738700dc44c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.126562796248173,
-  "global_step": 940000,
+  "epoch": 10.238091520471098,
+  "global_step": 950000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18806,11 +18806,211 @@
       "eval_samples_per_second": 888.512,
       "eval_steps_per_second": 13.925,
       "step": 940000
+    },
+    {
+      "epoch": 10.13,
+      "learning_rate": 1.1350681316526965e-05,
+      "loss": 0.1805,
+      "step": 940500
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 1.1328147928906494e-05,
+      "loss": 0.1809,
+      "step": 941000
+    },
+    {
+      "epoch": 10.14,
+      "eval_loss": 0.1728110909461975,
+      "eval_runtime": 2.6803,
+      "eval_samples_per_second": 857.002,
+      "eval_steps_per_second": 13.431,
+      "step": 941000
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 1.1305802287507358e-05,
+      "loss": 0.1806,
+      "step": 941500
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 1.1283644453421678e-05,
+      "loss": 0.1806,
+      "step": 942000
+    },
+    {
+      "epoch": 10.15,
+      "eval_loss": 0.17073097825050354,
+      "eval_runtime": 2.5804,
+      "eval_samples_per_second": 890.183,
+      "eval_steps_per_second": 13.951,
+      "step": 942000
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 1.1261674487228149e-05,
+      "loss": 0.1805,
+      "step": 942500
+    },
+    {
+      "epoch": 10.16,
+      "learning_rate": 1.1239892448991798e-05,
+      "loss": 0.1806,
+      "step": 943000
+    },
+    {
+      "epoch": 10.16,
+      "eval_loss": 0.17256046831607819,
+      "eval_runtime": 2.657,
+      "eval_samples_per_second": 864.515,
+      "eval_steps_per_second": 13.549,
+      "step": 943000
+    },
+    {
+      "epoch": 10.17,
+      "learning_rate": 1.1218298398263894e-05,
+      "loss": 0.1808,
+      "step": 943500
+    },
+    {
+      "epoch": 10.17,
+      "learning_rate": 1.1196892394081743e-05,
+      "loss": 0.1803,
+      "step": 944000
+    },
+    {
+      "epoch": 10.17,
+      "eval_loss": 0.1697072833776474,
+      "eval_runtime": 2.5585,
+      "eval_samples_per_second": 897.801,
+      "eval_steps_per_second": 14.071,
+      "step": 944000
+    },
+    {
+      "epoch": 10.18,
+      "learning_rate": 1.1175674494968552e-05,
+      "loss": 0.1803,
+      "step": 944500
+    },
+    {
+      "epoch": 10.18,
+      "learning_rate": 1.1154644758933235e-05,
+      "loss": 0.1807,
+      "step": 945000
+    },
+    {
+      "epoch": 10.18,
+      "eval_loss": 0.17261387407779694,
+      "eval_runtime": 2.6868,
+      "eval_samples_per_second": 854.925,
+      "eval_steps_per_second": 13.399,
+      "step": 945000
+    },
+    {
+      "epoch": 10.19,
+      "learning_rate": 1.11338032434703e-05,
+      "loss": 0.1804,
+      "step": 945500
+    },
+    {
+      "epoch": 10.19,
+      "learning_rate": 1.1113150005559644e-05,
+      "loss": 0.1808,
+      "step": 946000
+    },
+    {
+      "epoch": 10.19,
+      "eval_loss": 0.17092828452587128,
+      "eval_runtime": 2.6611,
+      "eval_samples_per_second": 863.19,
+      "eval_steps_per_second": 13.528,
+      "step": 946000
+    },
+    {
+      "epoch": 10.2,
+      "learning_rate": 1.1092685101666438e-05,
+      "loss": 0.1806,
+      "step": 946500
+    },
+    {
+      "epoch": 10.2,
+      "learning_rate": 1.1072408587740942e-05,
+      "loss": 0.1804,
+      "step": 947000
+    },
+    {
+      "epoch": 10.2,
+      "eval_loss": 0.17135068774223328,
+      "eval_runtime": 2.7301,
+      "eval_samples_per_second": 841.37,
+      "eval_steps_per_second": 13.186,
+      "step": 947000
+    },
+    {
+      "epoch": 10.21,
+      "learning_rate": 1.1052320519218383e-05,
+      "loss": 0.1804,
+      "step": 947500
+    },
+    {
+      "epoch": 10.22,
+      "learning_rate": 1.1032420951018755e-05,
+      "loss": 0.1806,
+      "step": 948000
+    },
+    {
+      "epoch": 10.22,
+      "eval_loss": 0.16970402002334595,
+      "eval_runtime": 2.5839,
+      "eval_samples_per_second": 888.964,
+      "eval_steps_per_second": 13.932,
+      "step": 948000
+    },
+    {
+      "epoch": 10.22,
+      "learning_rate": 1.1012709937546722e-05,
+      "loss": 0.1805,
+      "step": 948500
+    },
+    {
+      "epoch": 10.23,
+      "learning_rate": 1.0993187532691458e-05,
+      "loss": 0.1804,
+      "step": 949000
+    },
+    {
+      "epoch": 10.23,
+      "eval_loss": 0.17099051177501678,
+      "eval_runtime": 2.7073,
+      "eval_samples_per_second": 848.444,
+      "eval_steps_per_second": 13.297,
+      "step": 949000
+    },
+    {
+      "epoch": 10.23,
+      "learning_rate": 1.0973853789826454e-05,
+      "loss": 0.1804,
+      "step": 949500
+    },
+    {
+      "epoch": 10.24,
+      "learning_rate": 1.0954708761809438e-05,
+      "loss": 0.1806,
+      "step": 950000
+    },
+    {
+      "epoch": 10.24,
+      "eval_loss": 0.1725110560655594,
+      "eval_runtime": 2.6133,
+      "eval_samples_per_second": 878.965,
+      "eval_steps_per_second": 13.776,
+      "step": 950000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 6.589369772377475e+22,
+  "total_flos": 6.6594700334078225e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0068dc2eb70214cc7f3762f96ca920a8342113b2f223dfdea92c9f41e6012f4
+oid sha256:92c3d51ab918ac4532e1d6eeab8c0b6a6ea719ff69a5dc804d4995968ab632fc
 size 449471589