Training in progress, step 30000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c29fbdf49be880cb6493988a94306303a92a77dfa3a5685c194a3ed9741dd7
+oid sha256:9a92335164a57171365050fd07a22cee199d87b5d4f31f9f266d934997806ef1
 size 50044241

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cab920afe4d207be60e60c397c80474cec3b0781a866712c960668a023bb8b59
+oid sha256:d17ced65414e5fa0fdf019e711ae42967ebbbc1772201d6c2fa0f444b22af2ac
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4daecf9b867e6b1022a006e977cc17780663921ebe9348f84c4f92fd1098fd3
+oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4daecf9b867e6b1022a006e977cc17780663921ebe9348f84c4f92fd1098fd3
+oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4daecf9b867e6b1022a006e977cc17780663921ebe9348f84c4f92fd1098fd3
+oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4daecf9b867e6b1022a006e977cc17780663921ebe9348f84c4f92fd1098fd3
+oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4daecf9b867e6b1022a006e977cc17780663921ebe9348f84c4f92fd1098fd3
+oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4daecf9b867e6b1022a006e977cc17780663921ebe9348f84c4f92fd1098fd3
+oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4daecf9b867e6b1022a006e977cc17780663921ebe9348f84c4f92fd1098fd3
+oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4daecf9b867e6b1022a006e977cc17780663921ebe9348f84c4f92fd1098fd3
+oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa6f3c4ec253d8129a7481e01148ec46428b7a6eb1631c7fb589fd92c25c12f
+oid sha256:285c70cc0b99f831fd558ed5749dae6f2d660f449e704cb70ab7d67faaef2748
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8922198429693077,
-  "global_step": 20000,
+  "epoch": 1.3383297644539613,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -406,11 +406,211 @@
       "eval_samples_per_second": 1070.586,
       "eval_steps_per_second": 16.779,
       "step": 20000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.000598349790079647,
+      "loss": 0.6773,
+      "step": 20500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.000598137291838376,
+      "loss": 0.6772,
+      "step": 21000
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.6761835217475891,
+      "eval_runtime": 2.1367,
+      "eval_samples_per_second": 1075.027,
+      "eval_steps_per_second": 16.848,
+      "step": 21000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.000597911970822327,
+      "loss": 0.6772,
+      "step": 21500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.000597673836887771,
+      "loss": 0.6773,
+      "step": 22000
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 0.6774830222129822,
+      "eval_runtime": 2.1107,
+      "eval_samples_per_second": 1088.282,
+      "eval_steps_per_second": 17.056,
+      "step": 22000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0005974229004514577,
+      "loss": 0.6773,
+      "step": 22500
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0005971591724901598,
+      "loss": 0.6773,
+      "step": 23000
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 0.6764113903045654,
+      "eval_runtime": 2.206,
+      "eval_samples_per_second": 1041.236,
+      "eval_steps_per_second": 16.319,
+      "step": 23000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0005968826645401927,
+      "loss": 0.6772,
+      "step": 23500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00059659338869691,
+      "loss": 0.6772,
+      "step": 24000
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.6768463253974915,
+      "eval_runtime": 2.2173,
+      "eval_samples_per_second": 1035.939,
+      "eval_steps_per_second": 16.236,
+      "step": 24000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0005962913576141742,
+      "loss": 0.6773,
+      "step": 24500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.000595976584503803,
+      "loss": 0.6772,
+      "step": 25000
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.6769193410873413,
+      "eval_runtime": 2.2077,
+      "eval_samples_per_second": 1040.465,
+      "eval_steps_per_second": 16.307,
+      "step": 25000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0005956490831349923,
+      "loss": 0.6773,
+      "step": 25500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0005953088678337129,
+      "loss": 0.6772,
+      "step": 26000
+    },
+    {
+      "epoch": 1.16,
+      "eval_loss": 0.6775402426719666,
+      "eval_runtime": 2.2094,
+      "eval_samples_per_second": 1039.671,
+      "eval_steps_per_second": 16.294,
+      "step": 26000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0005949559534820841,
+      "loss": 0.6772,
+      "step": 26500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0005945903555177229,
+      "loss": 0.6772,
+      "step": 27000
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.6775718331336975,
+      "eval_runtime": 2.1372,
+      "eval_samples_per_second": 1074.76,
+      "eval_steps_per_second": 16.844,
+      "step": 27000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0005942120899330687,
+      "loss": 0.6772,
+      "step": 27500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0005938211732746836,
+      "loss": 0.6772,
+      "step": 28000
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 0.6771659255027771,
+      "eval_runtime": 2.191,
+      "eval_samples_per_second": 1048.378,
+      "eval_steps_per_second": 16.431,
+      "step": 28000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0005934176226425286,
+      "loss": 0.6772,
+      "step": 28500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0005930014556892158,
+      "loss": 0.6772,
+      "step": 29000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.6768732666969299,
+      "eval_runtime": 2.2912,
+      "eval_samples_per_second": 1002.553,
+      "eval_steps_per_second": 15.713,
+      "step": 29000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0005925726906192357,
+      "loss": 0.6772,
+      "step": 29500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0005921313461881617,
+      "loss": 0.6773,
+      "step": 30000
+    },
+    {
+      "epoch": 1.34,
+      "eval_loss": 0.6772350072860718,
+      "eval_runtime": 2.2465,
+      "eval_samples_per_second": 1022.498,
+      "eval_steps_per_second": 16.025,
+      "step": 30000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 3.2033600573160817e+20,
+  "total_flos": 4.804968766152387e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cab920afe4d207be60e60c397c80474cec3b0781a866712c960668a023bb8b59
+oid sha256:d17ced65414e5fa0fdf019e711ae42967ebbbc1772201d6c2fa0f444b22af2ac
 size 25761253