Training in progress, step 840000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f349542b4533abe4453e0adeb6aff6cd875b986f4117c2f333ebbbb94148a468
+oid sha256:24859c623c6a5769d23a445d9e652805ef93ef8232d0532f3fafc5dad772c85e
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8915b38c77403d5b3caf94070565cc919cba4e372d557eb5c40dbe89ac1681
+oid sha256:b27758f4c4f1be46ca953f785452acae2687180a06e7c14c3b975c46e8947612
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87068f53b7dee620f289e61f6508b8ae2aca3d5b7cb2a5e745862a635059c762
+oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87068f53b7dee620f289e61f6508b8ae2aca3d5b7cb2a5e745862a635059c762
+oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87068f53b7dee620f289e61f6508b8ae2aca3d5b7cb2a5e745862a635059c762
+oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87068f53b7dee620f289e61f6508b8ae2aca3d5b7cb2a5e745862a635059c762
+oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87068f53b7dee620f289e61f6508b8ae2aca3d5b7cb2a5e745862a635059c762
+oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87068f53b7dee620f289e61f6508b8ae2aca3d5b7cb2a5e745862a635059c762
+oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87068f53b7dee620f289e61f6508b8ae2aca3d5b7cb2a5e745862a635059c762
+oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87068f53b7dee620f289e61f6508b8ae2aca3d5b7cb2a5e745862a635059c762
+oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b44f4d1ea700e774f5dee0343ba4324675c77c29852dd54fec6a281d849ccd3b
+oid sha256:b75da63b821a4c72c4b37f39fc301b88ce6e4d7dc37edf4f078b7f5706f736e3
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.899746829796014,
-  "global_step": 830000,
+  "epoch": 9.011275554018937,
+  "global_step": 840000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16606,11 +16606,211 @@
       "eval_samples_per_second": 864.555,
       "eval_steps_per_second": 13.55,
       "step": 830000
+    },
+    {
+      "epoch": 8.91,
+      "learning_rate": 2.0711718689098057e-05,
+      "loss": 0.1858,
+      "step": 830500
+    },
+    {
+      "epoch": 8.91,
+      "learning_rate": 2.0650267139558772e-05,
+      "loss": 0.1854,
+      "step": 831000
+    },
+    {
+      "epoch": 8.91,
+      "eval_loss": 0.17501012980937958,
+      "eval_runtime": 2.6667,
+      "eval_samples_per_second": 861.35,
+      "eval_steps_per_second": 13.5,
+      "step": 831000
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 2.058897784992289e-05,
+      "loss": 0.1855,
+      "step": 831500
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 2.052785098775293e-05,
+      "loss": 0.1855,
+      "step": 832000
+    },
+    {
+      "epoch": 8.92,
+      "eval_loss": 0.17379425466060638,
+      "eval_runtime": 2.675,
+      "eval_samples_per_second": 858.689,
+      "eval_steps_per_second": 13.458,
+      "step": 832000
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 2.0466886720167436e-05,
+      "loss": 0.1847,
+      "step": 832500
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 2.04060852138404e-05,
+      "loss": 0.1854,
+      "step": 833000
+    },
+    {
+      "epoch": 8.93,
+      "eval_loss": 0.1764400452375412,
+      "eval_runtime": 2.6031,
+      "eval_samples_per_second": 882.425,
+      "eval_steps_per_second": 13.83,
+      "step": 833000
+    },
+    {
+      "epoch": 8.94,
+      "learning_rate": 2.0345446635000783e-05,
+      "loss": 0.1856,
+      "step": 833500
+    },
+    {
+      "epoch": 8.94,
+      "learning_rate": 2.028497114943219e-05,
+      "loss": 0.1851,
+      "step": 834000
+    },
+    {
+      "epoch": 8.94,
+      "eval_loss": 0.17593778669834137,
+      "eval_runtime": 2.5824,
+      "eval_samples_per_second": 889.497,
+      "eval_steps_per_second": 13.941,
+      "step": 834000
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 2.022465892247223e-05,
+      "loss": 0.1855,
+      "step": 834500
+    },
+    {
+      "epoch": 8.96,
+      "learning_rate": 2.0164510119012263e-05,
+      "loss": 0.1849,
+      "step": 835000
+    },
+    {
+      "epoch": 8.96,
+      "eval_loss": 0.1772100031375885,
+      "eval_runtime": 2.6877,
+      "eval_samples_per_second": 854.619,
+      "eval_steps_per_second": 13.394,
+      "step": 835000
+    },
+    {
+      "epoch": 8.96,
+      "learning_rate": 2.0104524903496834e-05,
+      "loss": 0.1852,
+      "step": 835500
+    },
+    {
+      "epoch": 8.97,
+      "learning_rate": 2.0044703439923217e-05,
+      "loss": 0.1854,
+      "step": 836000
+    },
+    {
+      "epoch": 8.97,
+      "eval_loss": 0.17744192481040955,
+      "eval_runtime": 2.6114,
+      "eval_samples_per_second": 879.619,
+      "eval_steps_per_second": 13.786,
+      "step": 836000
+    },
+    {
+      "epoch": 8.97,
+      "learning_rate": 1.998504589184101e-05,
+      "loss": 0.1851,
+      "step": 836500
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 1.9925552422351654e-05,
+      "loss": 0.1849,
+      "step": 837000
+    },
+    {
+      "epoch": 8.98,
+      "eval_loss": 0.1755765676498413,
+      "eval_runtime": 2.6326,
+      "eval_samples_per_second": 872.529,
+      "eval_steps_per_second": 13.675,
+      "step": 837000
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 1.9866223194108028e-05,
+      "loss": 0.1851,
+      "step": 837500
+    },
+    {
+      "epoch": 8.99,
+      "learning_rate": 1.9807058369314016e-05,
+      "loss": 0.1845,
+      "step": 838000
+    },
+    {
+      "epoch": 8.99,
+      "eval_loss": 0.17676672339439392,
+      "eval_runtime": 2.6846,
+      "eval_samples_per_second": 855.61,
+      "eval_steps_per_second": 13.41,
+      "step": 838000
+    },
+    {
+      "epoch": 8.99,
+      "learning_rate": 1.9748058109723953e-05,
+      "loss": 0.1852,
+      "step": 838500
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.968922257664231e-05,
+      "loss": 0.1853,
+      "step": 839000
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.17678546905517578,
+      "eval_runtime": 2.6872,
+      "eval_samples_per_second": 854.778,
+      "eval_steps_per_second": 13.397,
+      "step": 839000
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 1.9630551930923155e-05,
+      "loss": 0.1851,
+      "step": 839500
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 1.9572046332969825e-05,
+      "loss": 0.1848,
+      "step": 840000
+    },
+    {
+      "epoch": 9.01,
+      "eval_loss": 0.1751183122396469,
+      "eval_runtime": 2.6372,
+      "eval_samples_per_second": 870.984,
+      "eval_steps_per_second": 13.651,
+      "step": 840000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 5.818277853938688e+22,
+  "total_flos": 5.8883726385215196e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8915b38c77403d5b3caf94070565cc919cba4e372d557eb5c40dbe89ac1681
+oid sha256:b27758f4c4f1be46ca953f785452acae2687180a06e7c14c3b975c46e8947612
 size 449471589