Training in progress, step 200000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba65516926b4ff6cdfb50443e11a434cb503c7c65e74dc6127694de917095dae
+oid sha256:58f5bbc2fa5a6564ba72b2ae51852d2cf5c1476db0b209d90ec27efd86c1832a
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40af1c76beae3fcf68a183dcf22a7c21a89e9eb4f6548fe295f14d1acc603f3a
+oid sha256:814e92d04e78b6c50be49334aded8445cc7160900174a209d8b6a93d4efe04ca
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b742d11ad36723027991d2089e333cb5ecac7a190f975b5e786c90c8a60b34
+oid sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b742d11ad36723027991d2089e333cb5ecac7a190f975b5e786c90c8a60b34
+oid sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b742d11ad36723027991d2089e333cb5ecac7a190f975b5e786c90c8a60b34
+oid sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b742d11ad36723027991d2089e333cb5ecac7a190f975b5e786c90c8a60b34
+oid sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b742d11ad36723027991d2089e333cb5ecac7a190f975b5e786c90c8a60b34
+oid sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b742d11ad36723027991d2089e333cb5ecac7a190f975b5e786c90c8a60b34
+oid sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b742d11ad36723027991d2089e333cb5ecac7a190f975b5e786c90c8a60b34
+oid sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b742d11ad36723027991d2089e333cb5ecac7a190f975b5e786c90c8a60b34
+oid sha256:4761b20aad223fbddcacbd5ca8449487e62b55006b411c219bef6ce43077cf88
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:196e9b55e2db27c384076a5416088da2b3e045d13b4c3f579694349cd8bb530e
+oid sha256:c550723a62ae0c4012004470c1ebd8187b99ec43cbd02d108f19a1f1901da5d8
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.642156862745098,
-  "global_step": 190000,
+  "epoch": 12.254901960784313,
+  "global_step": 200000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3806,11 +3806,211 @@
       "eval_samples_per_second": 775.752,
       "eval_steps_per_second": 12.412,
       "step": 190000
+    },
+    {
+      "epoch": 11.67,
+      "learning_rate": 9.67486925578087e-05,
+      "loss": 0.4449,
+      "step": 190500
+    },
+    {
+      "epoch": 11.7,
+      "learning_rate": 9.537134606282964e-05,
+      "loss": 0.4448,
+      "step": 191000
+    },
+    {
+      "epoch": 11.7,
+      "eval_loss": 0.8036643266677856,
+      "eval_runtime": 1.3143,
+      "eval_samples_per_second": 760.834,
+      "eval_steps_per_second": 12.173,
+      "step": 191000
+    },
+    {
+      "epoch": 11.73,
+      "learning_rate": 9.400316940427652e-05,
+      "loss": 0.4447,
+      "step": 191500
+    },
+    {
+      "epoch": 11.76,
+      "learning_rate": 9.264422243062844e-05,
+      "loss": 0.4448,
+      "step": 192000
+    },
+    {
+      "epoch": 11.76,
+      "eval_loss": 0.8037863969802856,
+      "eval_runtime": 1.3425,
+      "eval_samples_per_second": 744.863,
+      "eval_steps_per_second": 11.918,
+      "step": 192000
+    },
+    {
+      "epoch": 11.8,
+      "learning_rate": 9.129456458662876e-05,
+      "loss": 0.4445,
+      "step": 192500
+    },
+    {
+      "epoch": 11.83,
+      "learning_rate": 8.995425491068365e-05,
+      "loss": 0.4445,
+      "step": 193000
+    },
+    {
+      "epoch": 11.83,
+      "eval_loss": 0.8010460734367371,
+      "eval_runtime": 1.3665,
+      "eval_samples_per_second": 731.803,
+      "eval_steps_per_second": 11.709,
+      "step": 193000
+    },
+    {
+      "epoch": 11.86,
+      "learning_rate": 8.862335203228025e-05,
+      "loss": 0.4444,
+      "step": 193500
+    },
+    {
+      "epoch": 11.89,
+      "learning_rate": 8.73019141694222e-05,
+      "loss": 0.4442,
+      "step": 194000
+    },
+    {
+      "epoch": 11.89,
+      "eval_loss": 0.7977059483528137,
+      "eval_runtime": 1.3628,
+      "eval_samples_per_second": 733.81,
+      "eval_steps_per_second": 11.741,
+      "step": 194000
+    },
+    {
+      "epoch": 11.92,
+      "learning_rate": 8.598999912608229e-05,
+      "loss": 0.4442,
+      "step": 194500
+    },
+    {
+      "epoch": 11.95,
+      "learning_rate": 8.468766428967468e-05,
+      "loss": 0.4443,
+      "step": 195000
+    },
+    {
+      "epoch": 11.95,
+      "eval_loss": 0.80078125,
+      "eval_runtime": 1.316,
+      "eval_samples_per_second": 759.905,
+      "eval_steps_per_second": 12.158,
+      "step": 195000
+    },
+    {
+      "epoch": 11.98,
+      "learning_rate": 8.339496662854397e-05,
+      "loss": 0.444,
+      "step": 195500
+    },
+    {
+      "epoch": 12.01,
+      "learning_rate": 8.211196268947367e-05,
+      "loss": 0.4441,
+      "step": 196000
+    },
+    {
+      "epoch": 12.01,
+      "eval_loss": 0.8048492670059204,
+      "eval_runtime": 1.3312,
+      "eval_samples_per_second": 751.193,
+      "eval_steps_per_second": 12.019,
+      "step": 196000
+    },
+    {
+      "epoch": 12.04,
+      "learning_rate": 8.083870859521251e-05,
+      "loss": 0.4441,
+      "step": 196500
+    },
+    {
+      "epoch": 12.07,
+      "learning_rate": 7.95752600420192e-05,
+      "loss": 0.4439,
+      "step": 197000
+    },
+    {
+      "epoch": 12.07,
+      "eval_loss": 0.8033810257911682,
+      "eval_runtime": 1.3277,
+      "eval_samples_per_second": 753.203,
+      "eval_steps_per_second": 12.051,
+      "step": 197000
+    },
+    {
+      "epoch": 12.1,
+      "learning_rate": 7.832167229722666e-05,
+      "loss": 0.4438,
+      "step": 197500
+    },
+    {
+      "epoch": 12.13,
+      "learning_rate": 7.707800019682362e-05,
+      "loss": 0.4438,
+      "step": 198000
+    },
+    {
+      "epoch": 12.13,
+      "eval_loss": 0.8051833510398865,
+      "eval_runtime": 1.2928,
+      "eval_samples_per_second": 773.488,
+      "eval_steps_per_second": 12.376,
+      "step": 198000
+    },
+    {
+      "epoch": 12.16,
+      "learning_rate": 7.5844298143057e-05,
+      "loss": 0.4437,
+      "step": 198500
+    },
+    {
+      "epoch": 12.19,
+      "learning_rate": 7.462062010205106e-05,
+      "loss": 0.4437,
+      "step": 199000
+    },
+    {
+      "epoch": 12.19,
+      "eval_loss": 0.8041102290153503,
+      "eval_runtime": 1.3104,
+      "eval_samples_per_second": 763.133,
+      "eval_steps_per_second": 12.21,
+      "step": 199000
+    },
+    {
+      "epoch": 12.22,
+      "learning_rate": 7.340701960144751e-05,
+      "loss": 0.4437,
+      "step": 199500
+    },
+    {
+      "epoch": 12.25,
+      "learning_rate": 7.220354972806392e-05,
+      "loss": 0.4434,
+      "step": 200000
+    },
+    {
+      "epoch": 12.25,
+      "eval_loss": 0.8000948429107666,
+      "eval_runtime": 1.2692,
+      "eval_samples_per_second": 787.882,
+      "eval_steps_per_second": 12.606,
+      "step": 200000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 16,
-  "total_flos": 3.0430819389105116e+21,
+  "total_flos": 3.2032399312727006e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40af1c76beae3fcf68a183dcf22a7c21a89e9eb4f6548fe295f14d1acc603f3a
+oid sha256:814e92d04e78b6c50be49334aded8445cc7160900174a209d8b6a93d4efe04ca
 size 25761253