Training in progress, step 200000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564dabf1934e46cc7ba6a8d36285b89de4adb73c031fca3ba9a7a2cd768c72d1
+oid sha256:1fdc18a3a07dc1829b889359b7e8a5532af1f5ff31ef1547a2371fed9f04234c
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93645087c6aeead636db9d9e4b7cbf206d1b0f761762ede97a32712b0dcff1ba
+oid sha256:f6f1a20ef47ec44509fdf200456c5d0dab5065c5747882695a1fa6a6507e69b1
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
+oid sha256:0d06e0985627e05f775a3ba05c980d5f591b2564a72af07a844dfcb127f862fb
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
+oid sha256:0d06e0985627e05f775a3ba05c980d5f591b2564a72af07a844dfcb127f862fb
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
+oid sha256:0d06e0985627e05f775a3ba05c980d5f591b2564a72af07a844dfcb127f862fb
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
+oid sha256:0d06e0985627e05f775a3ba05c980d5f591b2564a72af07a844dfcb127f862fb
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
+oid sha256:0d06e0985627e05f775a3ba05c980d5f591b2564a72af07a844dfcb127f862fb
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
+oid sha256:0d06e0985627e05f775a3ba05c980d5f591b2564a72af07a844dfcb127f862fb
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
+oid sha256:0d06e0985627e05f775a3ba05c980d5f591b2564a72af07a844dfcb127f862fb
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
+oid sha256:0d06e0985627e05f775a3ba05c980d5f591b2564a72af07a844dfcb127f862fb
 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": 8.476088508208422,
-  "global_step": 190000,
+  "epoch": 8.922198429693076,
+  "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": 1031.502,
       "eval_steps_per_second": 16.166,
       "step": 190000
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 9.67486925578087e-05,
+      "loss": 0.3686,
+      "step": 190500
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 9.537134606282964e-05,
+      "loss": 0.369,
+      "step": 191000
+    },
+    {
+      "epoch": 8.52,
+      "eval_loss": 0.3414945900440216,
+      "eval_runtime": 2.186,
+      "eval_samples_per_second": 1050.801,
+      "eval_steps_per_second": 16.469,
+      "step": 191000
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 9.400316940427652e-05,
+      "loss": 0.3688,
+      "step": 191500
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 9.264422243062844e-05,
+      "loss": 0.3685,
+      "step": 192000
+    },
+    {
+      "epoch": 8.57,
+      "eval_loss": 0.34313786029815674,
+      "eval_runtime": 2.2429,
+      "eval_samples_per_second": 1024.133,
+      "eval_steps_per_second": 16.051,
+      "step": 192000
+    },
+    {
+      "epoch": 8.59,
+      "learning_rate": 9.129456458662876e-05,
+      "loss": 0.3684,
+      "step": 192500
+    },
+    {
+      "epoch": 8.61,
+      "learning_rate": 8.995425491068365e-05,
+      "loss": 0.3684,
+      "step": 193000
+    },
+    {
+      "epoch": 8.61,
+      "eval_loss": 0.341512531042099,
+      "eval_runtime": 2.1692,
+      "eval_samples_per_second": 1058.928,
+      "eval_steps_per_second": 16.596,
+      "step": 193000
+    },
+    {
+      "epoch": 8.63,
+      "learning_rate": 8.862335203228025e-05,
+      "loss": 0.3683,
+      "step": 193500
+    },
+    {
+      "epoch": 8.65,
+      "learning_rate": 8.73019141694222e-05,
+      "loss": 0.3683,
+      "step": 194000
+    },
+    {
+      "epoch": 8.65,
+      "eval_loss": 0.3420671820640564,
+      "eval_runtime": 2.2415,
+      "eval_samples_per_second": 1024.765,
+      "eval_steps_per_second": 16.061,
+      "step": 194000
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 8.598999912608229e-05,
+      "loss": 0.3681,
+      "step": 194500
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 8.468766428967468e-05,
+      "loss": 0.368,
+      "step": 195000
+    },
+    {
+      "epoch": 8.7,
+      "eval_loss": 0.3422170877456665,
+      "eval_runtime": 2.2216,
+      "eval_samples_per_second": 1033.959,
+      "eval_steps_per_second": 16.205,
+      "step": 195000
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 8.339496662854397e-05,
+      "loss": 0.3682,
+      "step": 195500
+    },
+    {
+      "epoch": 8.74,
+      "learning_rate": 8.211196268947367e-05,
+      "loss": 0.3719,
+      "step": 196000
+    },
+    {
+      "epoch": 8.74,
+      "eval_loss": 0.3433374762535095,
+      "eval_runtime": 2.2305,
+      "eval_samples_per_second": 1029.81,
+      "eval_steps_per_second": 16.14,
+      "step": 196000
+    },
+    {
+      "epoch": 8.77,
+      "learning_rate": 8.083870859521251e-05,
+      "loss": 0.368,
+      "step": 196500
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 7.95752600420192e-05,
+      "loss": 0.3678,
+      "step": 197000
+    },
+    {
+      "epoch": 8.79,
+      "eval_loss": 0.33997857570648193,
+      "eval_runtime": 2.2361,
+      "eval_samples_per_second": 1027.215,
+      "eval_steps_per_second": 16.099,
+      "step": 197000
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 7.832167229722666e-05,
+      "loss": 0.3677,
+      "step": 197500
+    },
+    {
+      "epoch": 8.83,
+      "learning_rate": 7.707800019682362e-05,
+      "loss": 0.3675,
+      "step": 198000
+    },
+    {
+      "epoch": 8.83,
+      "eval_loss": 0.3419722616672516,
+      "eval_runtime": 2.2466,
+      "eval_samples_per_second": 1022.412,
+      "eval_steps_per_second": 16.024,
+      "step": 198000
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 7.5844298143057e-05,
+      "loss": 0.3676,
+      "step": 198500
+    },
+    {
+      "epoch": 8.88,
+      "learning_rate": 7.462062010205106e-05,
+      "loss": 0.3676,
+      "step": 199000
+    },
+    {
+      "epoch": 8.88,
+      "eval_loss": 0.3425526022911072,
+      "eval_runtime": 2.2092,
+      "eval_samples_per_second": 1039.756,
+      "eval_steps_per_second": 16.296,
+      "step": 199000
+    },
+    {
+      "epoch": 8.9,
+      "learning_rate": 7.340701960144751e-05,
+      "loss": 0.3676,
+      "step": 199500
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 7.220354972806392e-05,
+      "loss": 0.3674,
+      "step": 200000
+    },
+    {
+      "epoch": 8.92,
+      "eval_loss": 0.33957439661026,
+      "eval_runtime": 2.28,
+      "eval_samples_per_second": 1007.437,
+      "eval_steps_per_second": 15.789,
+      "step": 200000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 3.043134998592889e+21,
+  "total_flos": 3.203303001458693e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93645087c6aeead636db9d9e4b7cbf206d1b0f761762ede97a32712b0dcff1ba
+oid sha256:f6f1a20ef47ec44509fdf200456c5d0dab5065c5747882695a1fa6a6507e69b1
 size 25761253