Training in progress, step 110000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a8740e850a7025efc4240518d5b20a0266625ee7a4df5824989ffd90a771e4
+oid sha256:d58137113791019cd3d543973897cce79aa9a3f674e715923996321558c96b13
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9743dfff2c56ecc42fa49782ae324bef5653923fd6c7bcd04473781c4c5cb59f
+oid sha256:4f59c2ef88b3bc3cd7bdeb23ee182242569e553f7337d36848967067fc05c479
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
+oid sha256:247f1776d14aa6bf405e1cbe9b3a20de5077a4212ea5f0a4e1ce51dbf43de0f2
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
+oid sha256:247f1776d14aa6bf405e1cbe9b3a20de5077a4212ea5f0a4e1ce51dbf43de0f2
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
+oid sha256:247f1776d14aa6bf405e1cbe9b3a20de5077a4212ea5f0a4e1ce51dbf43de0f2
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
+oid sha256:247f1776d14aa6bf405e1cbe9b3a20de5077a4212ea5f0a4e1ce51dbf43de0f2
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
+oid sha256:247f1776d14aa6bf405e1cbe9b3a20de5077a4212ea5f0a4e1ce51dbf43de0f2
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
+oid sha256:247f1776d14aa6bf405e1cbe9b3a20de5077a4212ea5f0a4e1ce51dbf43de0f2
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
+oid sha256:247f1776d14aa6bf405e1cbe9b3a20de5077a4212ea5f0a4e1ce51dbf43de0f2
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
+oid sha256:247f1776d14aa6bf405e1cbe9b3a20de5077a4212ea5f0a4e1ce51dbf43de0f2
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7786e0d240c1817a80f936fe537093f6b0f81238abcccea2c0e618f1ac9e9438
+oid sha256:a36392859753540b5ff28a6690e0fb35c1157de322529d1ae210898db91ddda7
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.329970409375801,
-  "global_step": 100000,
+  "epoch": 2.562967450313381,
+  "global_step": 110000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2006,11 +2006,211 @@
       "eval_samples_per_second": 1563.737,
       "eval_steps_per_second": 24.9,
       "step": 100000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.0002822947773032956,
+      "loss": 0.3022,
+      "step": 100500
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.0002820644686063602,
+      "loss": 0.3023,
+      "step": 101000
+    },
+    {
+      "epoch": 2.35,
+      "eval_loss": 0.2856578528881073,
+      "eval_runtime": 1.4144,
+      "eval_samples_per_second": 1553.982,
+      "eval_steps_per_second": 24.745,
+      "step": 101000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.00028183277035275363,
+      "loss": 0.3022,
+      "step": 101500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.0002815996850762909,
+      "loss": 0.3024,
+      "step": 102000
+    },
+    {
+      "epoch": 2.38,
+      "eval_loss": 0.28789734840393066,
+      "eval_runtime": 1.8256,
+      "eval_samples_per_second": 1203.971,
+      "eval_steps_per_second": 19.172,
+      "step": 102000
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 0.00028136521532595515,
+      "loss": 0.3022,
+      "step": 102500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.00028112936366587023,
+      "loss": 0.3018,
+      "step": 103000
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.28655195236206055,
+      "eval_runtime": 1.4347,
+      "eval_samples_per_second": 1532.011,
+      "eval_steps_per_second": 24.395,
+      "step": 103000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.00028089213267527184,
+      "loss": 0.3018,
+      "step": 103500
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 0.0002806535249484803,
+      "loss": 0.3015,
+      "step": 104000
+    },
+    {
+      "epoch": 2.42,
+      "eval_loss": 0.2860538959503174,
+      "eval_runtime": 1.4232,
+      "eval_samples_per_second": 1544.364,
+      "eval_steps_per_second": 24.592,
+      "step": 104000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 0.00028041354309487135,
+      "loss": 0.3013,
+      "step": 104500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 0.0002801721897388482,
+      "loss": 0.301,
+      "step": 105000
+    },
+    {
+      "epoch": 2.45,
+      "eval_loss": 0.28530260920524597,
+      "eval_runtime": 1.4494,
+      "eval_samples_per_second": 1516.459,
+      "eval_steps_per_second": 24.147,
+      "step": 105000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.0002799294675198124,
+      "loss": 0.3018,
+      "step": 105500
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 0.00027968537909213524,
+      "loss": 0.3008,
+      "step": 106000
+    },
+    {
+      "epoch": 2.47,
+      "eval_loss": 0.285876989364624,
+      "eval_runtime": 1.4506,
+      "eval_samples_per_second": 1515.222,
+      "eval_steps_per_second": 24.128,
+      "step": 106000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0002794399271251287,
+      "loss": 0.3013,
+      "step": 106500
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 0.0002791931143030162,
+      "loss": 0.3006,
+      "step": 107000
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 0.28289294242858887,
+      "eval_runtime": 1.4223,
+      "eval_samples_per_second": 1545.438,
+      "eval_steps_per_second": 24.609,
+      "step": 107000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00027894494332490315,
+      "loss": 0.3001,
+      "step": 107500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 0.0002786954169047476,
+      "loss": 0.3003,
+      "step": 108000
+    },
+    {
+      "epoch": 2.52,
+      "eval_loss": 0.2835444509983063,
+      "eval_runtime": 1.4445,
+      "eval_samples_per_second": 1521.603,
+      "eval_steps_per_second": 24.229,
+      "step": 108000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002784445377713306,
+      "loss": 0.2999,
+      "step": 108500
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.0002781923086682261,
+      "loss": 0.2998,
+      "step": 109000
+    },
+    {
+      "epoch": 2.54,
+      "eval_loss": 0.27993467450141907,
+      "eval_runtime": 1.4177,
+      "eval_samples_per_second": 1550.426,
+      "eval_steps_per_second": 24.688,
+      "step": 109000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002779387323537711,
+      "loss": 0.2994,
+      "step": 109500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.0002776838116010356,
+      "loss": 0.3001,
+      "step": 110000
+    },
+    {
+      "epoch": 2.56,
+      "eval_loss": 0.28160494565963745,
+      "eval_runtime": 1.4324,
+      "eval_samples_per_second": 1534.54,
+      "eval_steps_per_second": 24.435,
+      "step": 110000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 3.1948663937631865e+21,
+  "total_flos": 3.5143535325376865e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9743dfff2c56ecc42fa49782ae324bef5653923fd6c7bcd04473781c4c5cb59f
+oid sha256:4f59c2ef88b3bc3cd7bdeb23ee182242569e553f7337d36848967067fc05c479
 size 102501541