Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadcb41aea0d881ec7489fc153864312daace23a87556e2dabeb7f00ab20de52
+oid sha256:437bdcfa884f243eb057db287fb27ac37ef2a0326b1d025d8ffcaaa891bad6ea
 size 50044241

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf773b1bedf0e3d4076d93eb3be69d1083c7a6321f77e59758b3adc872017b3a
+oid sha256:8d066230793a00e463dada238cbf68fe9a6e4506761309bbc7272fd63bd501d9
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39febded125ea43849ae44cc91a2089d4c554f45131ad78886b088e5c989bab9
+oid sha256:4b53ff89d37c2976f0dbf329b38e7e3851775fcd8b4f21d8e3166437bbe7a48e
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39febded125ea43849ae44cc91a2089d4c554f45131ad78886b088e5c989bab9
+oid sha256:4b53ff89d37c2976f0dbf329b38e7e3851775fcd8b4f21d8e3166437bbe7a48e
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39febded125ea43849ae44cc91a2089d4c554f45131ad78886b088e5c989bab9
+oid sha256:4b53ff89d37c2976f0dbf329b38e7e3851775fcd8b4f21d8e3166437bbe7a48e
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39febded125ea43849ae44cc91a2089d4c554f45131ad78886b088e5c989bab9
+oid sha256:4b53ff89d37c2976f0dbf329b38e7e3851775fcd8b4f21d8e3166437bbe7a48e
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39febded125ea43849ae44cc91a2089d4c554f45131ad78886b088e5c989bab9
+oid sha256:4b53ff89d37c2976f0dbf329b38e7e3851775fcd8b4f21d8e3166437bbe7a48e
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39febded125ea43849ae44cc91a2089d4c554f45131ad78886b088e5c989bab9
+oid sha256:4b53ff89d37c2976f0dbf329b38e7e3851775fcd8b4f21d8e3166437bbe7a48e
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39febded125ea43849ae44cc91a2089d4c554f45131ad78886b088e5c989bab9
+oid sha256:4b53ff89d37c2976f0dbf329b38e7e3851775fcd8b4f21d8e3166437bbe7a48e
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39febded125ea43849ae44cc91a2089d4c554f45131ad78886b088e5c989bab9
+oid sha256:4b53ff89d37c2976f0dbf329b38e7e3851775fcd8b4f21d8e3166437bbe7a48e
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9511edec0a698219a4fec94630f2bf1ec60055a31bda0393e6aadb5a36db13d
+oid sha256:6a14cae2e3d67695f0ffa4604dbaaa3f7147d70607921bb89c9afa09d57c87a5
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.063725490196078,
-  "global_step": 50000,
+  "epoch": 3.6764705882352944,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1006,11 +1006,211 @@
       "eval_samples_per_second": 775.099,
       "eval_steps_per_second": 12.402,
       "step": 50000
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 0.0005635104706129397,
+      "loss": 0.5189,
+      "step": 50500
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 0.0005625648765345228,
+      "loss": 0.5183,
+      "step": 51000
+    },
+    {
+      "epoch": 3.12,
+      "eval_loss": 0.8579334616661072,
+      "eval_runtime": 1.3546,
+      "eval_samples_per_second": 738.246,
+      "eval_steps_per_second": 11.812,
+      "step": 51000
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 0.0005616080157340118,
+      "loss": 0.5178,
+      "step": 51500
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 0.0005606399300675978,
+      "loss": 0.5175,
+      "step": 52000
+    },
+    {
+      "epoch": 3.19,
+      "eval_loss": 0.8597957491874695,
+      "eval_runtime": 1.3415,
+      "eval_samples_per_second": 745.449,
+      "eval_steps_per_second": 11.927,
+      "step": 52000
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 0.0005596606618824843,
+      "loss": 0.5186,
+      "step": 52500
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.0005586702540150338,
+      "loss": 0.5163,
+      "step": 53000
+    },
+    {
+      "epoch": 3.25,
+      "eval_loss": 0.8520950078964233,
+      "eval_runtime": 1.3505,
+      "eval_samples_per_second": 740.484,
+      "eval_steps_per_second": 11.848,
+      "step": 53000
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 0.000557668749788895,
+      "loss": 0.5159,
+      "step": 53500
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 0.0005566561930131072,
+      "loss": 0.5156,
+      "step": 54000
+    },
+    {
+      "epoch": 3.31,
+      "eval_loss": 0.8550420999526978,
+      "eval_runtime": 1.3983,
+      "eval_samples_per_second": 715.143,
+      "eval_steps_per_second": 11.442,
+      "step": 54000
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 0.000555632627980184,
+      "loss": 0.5153,
+      "step": 54500
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 0.0005545980994641758,
+      "loss": 0.5148,
+      "step": 55000
+    },
+    {
+      "epoch": 3.37,
+      "eval_loss": 0.8503537178039551,
+      "eval_runtime": 1.2794,
+      "eval_samples_per_second": 781.636,
+      "eval_steps_per_second": 12.506,
+      "step": 55000
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 0.0005535526527187115,
+      "loss": 0.5144,
+      "step": 55500
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 0.0005524963334750183,
+      "loss": 0.5139,
+      "step": 56000
+    },
+    {
+      "epoch": 3.43,
+      "eval_loss": 0.8530069589614868,
+      "eval_runtime": 1.2989,
+      "eval_samples_per_second": 769.886,
+      "eval_steps_per_second": 12.318,
+      "step": 56000
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 0.0005514291879399219,
+      "loss": 0.5136,
+      "step": 56500
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 0.000550351262793825,
+      "loss": 0.5133,
+      "step": 57000
+    },
+    {
+      "epoch": 3.49,
+      "eval_loss": 0.8588612675666809,
+      "eval_runtime": 1.2931,
+      "eval_samples_per_second": 773.351,
+      "eval_steps_per_second": 12.374,
+      "step": 57000
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 0.0005492626051886659,
+      "loss": 0.5129,
+      "step": 57500
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 0.0005481632627458546,
+      "loss": 0.5126,
+      "step": 58000
+    },
+    {
+      "epoch": 3.55,
+      "eval_loss": 0.8561201095581055,
+      "eval_runtime": 1.244,
+      "eval_samples_per_second": 803.841,
+      "eval_steps_per_second": 12.861,
+      "step": 58000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 0.0005470532835541911,
+      "loss": 0.5122,
+      "step": 58500
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 0.000545932716167761,
+      "loss": 0.5119,
+      "step": 59000
+    },
+    {
+      "epoch": 3.62,
+      "eval_loss": 0.8574157953262329,
+      "eval_runtime": 1.3446,
+      "eval_samples_per_second": 743.721,
+      "eval_steps_per_second": 11.9,
+      "step": 59000
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.000544801609603812,
+      "loss": 0.5115,
+      "step": 59500
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.0005436600133406095,
+      "loss": 0.5127,
+      "step": 60000
+    },
+    {
+      "epoch": 3.68,
+      "eval_loss": 0.8624024987220764,
+      "eval_runtime": 1.324,
+      "eval_samples_per_second": 755.286,
+      "eval_steps_per_second": 12.085,
+      "step": 60000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 16,
-  "total_flos": 8.008099828181752e+20,
+  "total_flos": 9.609779856839792e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf773b1bedf0e3d4076d93eb3be69d1083c7a6321f77e59758b3adc872017b3a
+oid sha256:8d066230793a00e463dada238cbf68fe9a6e4506761309bbc7272fd63bd501d9
 size 25761253