Training in progress, step 450000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2088799669b8cbfd210d30dfce8989698daa830165d0ca944114a10a59871693
+oid sha256:c7cf25044f894af33b58ee33e839ca67a9010ce216694a7f4c91e8f90caf02e3
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7b0c7d08046c0c4e1a91c3f9d63b1d7bdf393ee4dbbd4736af162b969bdfb9
+oid sha256:1f48e297dd8d43fe26955c08bdc18374b43b5c5c7bf58df74b63ccfce891d130
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e233a8ef519d9d16a9b95d7a7171d6def7872349c82be02599284c8c6acffd
+oid sha256:0d0eaf38f8d76dc97fc60763011f1de34c7a2cb3c95faaa0610cc0f4af72cd60
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be16f8037c6901bc41919bcc8cb1118de728673c68c18b0ae386bea63c0e3e3d
+oid sha256:1aee1e0607f38b87a3b735ae98b8e01339f7cc72ffa6ccf3c213d28824ed54a9
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be92d6d899a07c4671d400b60ab95a700562ae501c22a4fee8fa76e7589e996f
+oid sha256:cceb842179d613224b3b5f8d750e75368fc012474b9befae3962586a3fa07c34
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8770268f899c830767a9d97c2302203be584e1c1cc37d9570826bfabc17c0fa2
+oid sha256:e777f0df33e0c44b8c16c09cacb56ca419e02a262aa3b9ece5534f0249ba6105
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc40f97d6fc7a436b02585a6f0d5affbb2d92e52b230fd202e6e0bc79392801
+oid sha256:44ab8fd99918dee712abc63025e4d8d70437de212ab6324f5ae0cbe74ed24f94
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593a229cfaacb8e002eb9c5c553875fab30c88f8d710b8359f369800ad7eef0c
+oid sha256:ef227953f09853ae7340813887aac1a30150643cccf7844f37d1f0ff5cb9042d
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d4f52680b07fe7330a884622b4d2a5e39ee242550e8d535f6458b2b4ab42b35
+oid sha256:7caa6c821a93c7fa5649d2fba3a2ebec3c3cd1a1620660f06157dc5569333b5a
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3181d4c08032a76433b86390db671ed6c1b5ecc3604448dc1685a0d499892b2
+oid sha256:ee0e57d5d9717a7b27c7acd3b2ffc6fc1518aa4d2ebf016d3b2d036634f60df0
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1894f32b2441ea8820978bbb44f8f2d9ce0a579e669301efbd1655378591798a
+oid sha256:bc29c434fb0390a8f4f90d65ac745a0b4f381dbd06e857762d450d4a464c7045
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.480805171727075,
-  "global_step": 440000,
+  "epoch": 13.787187107448144,
+  "global_step": 450000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8806,11 +8806,211 @@
       "eval_samples_per_second": 1931.767,
       "eval_steps_per_second": 30.908,
       "step": 440000
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 2.1083388335824145e-05,
+      "loss": 0.315,
+      "step": 440500
+    },
+    {
+      "epoch": 13.51,
+      "learning_rate": 2.0900255633978873e-05,
+      "loss": 0.3147,
+      "step": 441000
+    },
+    {
+      "epoch": 13.51,
+      "eval_loss": 0.7775884866714478,
+      "eval_runtime": 0.5109,
+      "eval_samples_per_second": 1957.402,
+      "eval_steps_per_second": 31.318,
+      "step": 441000
+    },
+    {
+      "epoch": 13.53,
+      "learning_rate": 2.0718589425453314e-05,
+      "loss": 0.3145,
+      "step": 441500
+    },
+    {
+      "epoch": 13.54,
+      "learning_rate": 2.0538391696920015e-05,
+      "loss": 0.3145,
+      "step": 442000
+    },
+    {
+      "epoch": 13.54,
+      "eval_loss": 0.7738910913467407,
+      "eval_runtime": 0.5137,
+      "eval_samples_per_second": 1946.745,
+      "eval_steps_per_second": 31.148,
+      "step": 442000
+    },
+    {
+      "epoch": 13.56,
+      "learning_rate": 2.035966441899249e-05,
+      "loss": 0.3148,
+      "step": 442500
+    },
+    {
+      "epoch": 13.57,
+      "learning_rate": 2.0182409546203555e-05,
+      "loss": 0.3145,
+      "step": 443000
+    },
+    {
+      "epoch": 13.57,
+      "eval_loss": 0.7752822041511536,
+      "eval_runtime": 0.5041,
+      "eval_samples_per_second": 1983.895,
+      "eval_steps_per_second": 31.742,
+      "step": 443000
+    },
+    {
+      "epoch": 13.59,
+      "learning_rate": 2.000662901698415e-05,
+      "loss": 0.3143,
+      "step": 443500
+    },
+    {
+      "epoch": 13.6,
+      "learning_rate": 1.983232475364195e-05,
+      "loss": 0.3145,
+      "step": 444000
+    },
+    {
+      "epoch": 13.6,
+      "eval_loss": 0.7770563960075378,
+      "eval_runtime": 0.5102,
+      "eval_samples_per_second": 1959.954,
+      "eval_steps_per_second": 31.359,
+      "step": 444000
+    },
+    {
+      "epoch": 13.62,
+      "learning_rate": 1.9659498662340474e-05,
+      "loss": 0.3144,
+      "step": 444500
+    },
+    {
+      "epoch": 13.63,
+      "learning_rate": 1.948815263307819e-05,
+      "loss": 0.3146,
+      "step": 445000
+    },
+    {
+      "epoch": 13.63,
+      "eval_loss": 0.7755433917045593,
+      "eval_runtime": 0.5167,
+      "eval_samples_per_second": 1935.403,
+      "eval_steps_per_second": 30.966,
+      "step": 445000
+    },
+    {
+      "epoch": 13.65,
+      "learning_rate": 1.9318288539667765e-05,
+      "loss": 0.3144,
+      "step": 445500
+    },
+    {
+      "epoch": 13.66,
+      "learning_rate": 1.914990823971574e-05,
+      "loss": 0.3144,
+      "step": 446000
+    },
+    {
+      "epoch": 13.66,
+      "eval_loss": 0.7735174298286438,
+      "eval_runtime": 0.5138,
+      "eval_samples_per_second": 1946.362,
+      "eval_steps_per_second": 31.142,
+      "step": 446000
+    },
+    {
+      "epoch": 13.68,
+      "learning_rate": 1.8983013574602096e-05,
+      "loss": 0.314,
+      "step": 446500
+    },
+    {
+      "epoch": 13.7,
+      "learning_rate": 1.8817606369460156e-05,
+      "loss": 0.3143,
+      "step": 447000
+    },
+    {
+      "epoch": 13.7,
+      "eval_loss": 0.7771323323249817,
+      "eval_runtime": 0.5128,
+      "eval_samples_per_second": 1950.249,
+      "eval_steps_per_second": 31.204,
+      "step": 447000
+    },
+    {
+      "epoch": 13.71,
+      "learning_rate": 1.865368843315663e-05,
+      "loss": 0.3147,
+      "step": 447500
+    },
+    {
+      "epoch": 13.73,
+      "learning_rate": 1.8491261558271762e-05,
+      "loss": 0.314,
+      "step": 448000
+    },
+    {
+      "epoch": 13.73,
+      "eval_loss": 0.7759497165679932,
+      "eval_runtime": 0.5133,
+      "eval_samples_per_second": 1948.013,
+      "eval_steps_per_second": 31.168,
+      "step": 448000
+    },
+    {
+      "epoch": 13.74,
+      "learning_rate": 1.833032752107986e-05,
+      "loss": 0.3143,
+      "step": 448500
+    },
+    {
+      "epoch": 13.76,
+      "learning_rate": 1.817088808152978e-05,
+      "loss": 0.3143,
+      "step": 449000
+    },
+    {
+      "epoch": 13.76,
+      "eval_loss": 0.7774102687835693,
+      "eval_runtime": 0.5028,
+      "eval_samples_per_second": 1988.858,
+      "eval_steps_per_second": 31.822,
+      "step": 449000
+    },
+    {
+      "epoch": 13.77,
+      "learning_rate": 1.801294498322569e-05,
+      "loss": 0.3141,
+      "step": 449500
+    },
+    {
+      "epoch": 13.79,
+      "learning_rate": 1.7856499953407978e-05,
+      "loss": 0.3142,
+      "step": 450000
+    },
+    {
+      "epoch": 13.79,
+      "eval_loss": 0.7757880687713623,
+      "eval_runtime": 0.5025,
+      "eval_samples_per_second": 1989.909,
+      "eval_steps_per_second": 31.839,
+      "step": 450000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 1.4057330262702314e+22,
+  "total_flos": 1.4376817401476814e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7b0c7d08046c0c4e1a91c3f9d63b1d7bdf393ee4dbbd4736af162b969bdfb9
+oid sha256:1f48e297dd8d43fe26955c08bdc18374b43b5c5c7bf58df74b63ccfce891d130
 size 102501541