Training in progress, step 850000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24859c623c6a5769d23a445d9e652805ef93ef8232d0532f3fafc5dad772c85e
+oid sha256:e51d88aff5257549a283e52c14c7816f109ed1c8f1cd4c0209be1013bd750037
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27758f4c4f1be46ca953f785452acae2687180a06e7c14c3b975c46e8947612
+oid sha256:0c2b61d52c517c0fe4a2eaad25ea86eca5fed6ebf386f54b8df5e3364654d10f
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
+oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
+oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
+oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
+oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
+oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
+oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
+oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4e2d13a0c0716c1c500a2d28a58a0073e425d28549a76ecb1f2b04513b7909
+oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b75da63b821a4c72c4b37f39fc301b88ce6e4d7dc37edf4f078b7f5706f736e3
+oid sha256:6fbbdae9c95471a40e6c6d019353b081fa6055bc839ed4f2163c0c1b80837934
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.011275554018937,
-  "global_step": 840000,
+  "epoch": 9.122804278241862,
+  "global_step": 850000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16806,11 +16806,211 @@
       "eval_samples_per_second": 870.984,
       "eval_steps_per_second": 13.651,
       "step": 840000
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 1.95137059427344e-05,
+      "loss": 0.1851,
+      "step": 840500
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 1.945553091971727e-05,
+      "loss": 0.1852,
+      "step": 841000
+    },
+    {
+      "epoch": 9.02,
+      "eval_loss": 0.17605267465114594,
+      "eval_runtime": 2.6415,
+      "eval_samples_per_second": 869.593,
+      "eval_steps_per_second": 13.629,
+      "step": 841000
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 1.93975214229667e-05,
+      "loss": 0.185,
+      "step": 841500
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 1.933967761107847e-05,
+      "loss": 0.1846,
+      "step": 842000
+    },
+    {
+      "epoch": 9.03,
+      "eval_loss": 0.17334681749343872,
+      "eval_runtime": 2.679,
+      "eval_samples_per_second": 857.418,
+      "eval_steps_per_second": 13.438,
+      "step": 842000
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 1.928199964219533e-05,
+      "loss": 0.1851,
+      "step": 842500
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 1.9224487674006694e-05,
+      "loss": 0.1848,
+      "step": 843000
+    },
+    {
+      "epoch": 9.04,
+      "eval_loss": 0.17702366411685944,
+      "eval_runtime": 2.7205,
+      "eval_samples_per_second": 844.336,
+      "eval_steps_per_second": 13.233,
+      "step": 843000
+    },
+    {
+      "epoch": 9.05,
+      "learning_rate": 1.9167141863748015e-05,
+      "loss": 0.1848,
+      "step": 843500
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 1.9109962368200602e-05,
+      "loss": 0.1846,
+      "step": 844000
+    },
+    {
+      "epoch": 9.06,
+      "eval_loss": 0.17539054155349731,
+      "eval_runtime": 2.6244,
+      "eval_samples_per_second": 875.248,
+      "eval_steps_per_second": 13.717,
+      "step": 844000
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 1.9052949343690977e-05,
+      "loss": 0.1848,
+      "step": 844500
+    },
+    {
+      "epoch": 9.07,
+      "learning_rate": 1.8996102946090586e-05,
+      "loss": 0.1846,
+      "step": 845000
+    },
+    {
+      "epoch": 9.07,
+      "eval_loss": 0.17318959534168243,
+      "eval_runtime": 2.7201,
+      "eval_samples_per_second": 844.445,
+      "eval_steps_per_second": 13.235,
+      "step": 845000
+    },
+    {
+      "epoch": 9.07,
+      "learning_rate": 1.8939423330815345e-05,
+      "loss": 0.1847,
+      "step": 845500
+    },
+    {
+      "epoch": 9.08,
+      "learning_rate": 1.888291065282509e-05,
+      "loss": 0.1847,
+      "step": 846000
+    },
+    {
+      "epoch": 9.08,
+      "eval_loss": 0.17560191452503204,
+      "eval_runtime": 2.7101,
+      "eval_samples_per_second": 847.565,
+      "eval_steps_per_second": 13.284,
+      "step": 846000
+    },
+    {
+      "epoch": 9.08,
+      "learning_rate": 1.882656506662338e-05,
+      "loss": 0.1846,
+      "step": 846500
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 1.8770386726256865e-05,
+      "loss": 0.1844,
+      "step": 847000
+    },
+    {
+      "epoch": 9.09,
+      "eval_loss": 0.17197825014591217,
+      "eval_runtime": 2.7201,
+      "eval_samples_per_second": 844.459,
+      "eval_steps_per_second": 13.235,
+      "step": 847000
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 1.8714375785315006e-05,
+      "loss": 0.1845,
+      "step": 847500
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 1.8658532396929565e-05,
+      "loss": 0.184,
+      "step": 848000
+    },
+    {
+      "epoch": 9.1,
+      "eval_loss": 0.17653484642505646,
+      "eval_runtime": 2.6616,
+      "eval_samples_per_second": 863.031,
+      "eval_steps_per_second": 13.526,
+      "step": 848000
+    },
+    {
+      "epoch": 9.11,
+      "learning_rate": 1.8602856713774208e-05,
+      "loss": 0.1843,
+      "step": 848500
+    },
+    {
+      "epoch": 9.11,
+      "learning_rate": 1.8547348888064178e-05,
+      "loss": 0.1848,
+      "step": 849000
+    },
+    {
+      "epoch": 9.11,
+      "eval_loss": 0.1734277456998825,
+      "eval_runtime": 2.6737,
+      "eval_samples_per_second": 859.112,
+      "eval_steps_per_second": 13.465,
+      "step": 849000
+    },
+    {
+      "epoch": 9.12,
+      "learning_rate": 1.8492009071555703e-05,
+      "loss": 0.1846,
+      "step": 849500
+    },
+    {
+      "epoch": 9.12,
+      "learning_rate": 1.8436837415545772e-05,
+      "loss": 0.1848,
+      "step": 850000
+    },
+    {
+      "epoch": 9.12,
+      "eval_loss": 0.17425018548965454,
+      "eval_runtime": 2.6779,
+      "eval_samples_per_second": 857.76,
+      "eval_steps_per_second": 13.443,
+      "step": 850000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 5.8883726385215196e+22,
+  "total_flos": 5.958472899551867e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27758f4c4f1be46ca953f785452acae2687180a06e7c14c3b975c46e8947612
+oid sha256:0c2b61d52c517c0fe4a2eaad25ea86eca5fed6ebf386f54b8df5e3364654d10f
 size 449471589