Training in progress, step 450000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38e96dc800b8071588a25548ce196afd6691c407f883f1ee47078f41d437f6cc
+oid sha256:48da217ea188770413b01ab5847a04b2b361555bd731533e7a2791bedfd928dd
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5997fc3c43be6a9667fa07314f7e899550168c519b5f1cc4e4addad00b4f02db
+oid sha256:2291b66065799571b4264696030000d7ec1a0e86601a7f2aefc345f1b8fac97d
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7888d98a0e63278076119528e69fae749a8a6dd4d788341bc14abb08d306def4
+oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7888d98a0e63278076119528e69fae749a8a6dd4d788341bc14abb08d306def4
+oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7888d98a0e63278076119528e69fae749a8a6dd4d788341bc14abb08d306def4
+oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7888d98a0e63278076119528e69fae749a8a6dd4d788341bc14abb08d306def4
+oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7888d98a0e63278076119528e69fae749a8a6dd4d788341bc14abb08d306def4
+oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7888d98a0e63278076119528e69fae749a8a6dd4d788341bc14abb08d306def4
+oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7888d98a0e63278076119528e69fae749a8a6dd4d788341bc14abb08d306def4
+oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7888d98a0e63278076119528e69fae749a8a6dd4d788341bc14abb08d306def4
+oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
 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": 11.213619450532647,
-  "global_step": 440000,
+  "epoch": 11.468474438044753,
+  "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": 822.887,
       "eval_steps_per_second": 13.166,
       "step": 440000
+    },
+    {
+      "epoch": 11.23,
+      "learning_rate": 2.1083388335824145e-05,
+      "loss": 0.2689,
+      "step": 440500
+    },
+    {
+      "epoch": 11.24,
+      "learning_rate": 2.0900255633978873e-05,
+      "loss": 0.2689,
+      "step": 441000
+    },
+    {
+      "epoch": 11.24,
+      "eval_loss": 0.8037525415420532,
+      "eval_runtime": 1.2548,
+      "eval_samples_per_second": 796.966,
+      "eval_steps_per_second": 12.751,
+      "step": 441000
+    },
+    {
+      "epoch": 11.25,
+      "learning_rate": 2.0718589425453314e-05,
+      "loss": 0.2686,
+      "step": 441500
+    },
+    {
+      "epoch": 11.26,
+      "learning_rate": 2.0538391696920015e-05,
+      "loss": 0.2687,
+      "step": 442000
+    },
+    {
+      "epoch": 11.26,
+      "eval_loss": 0.8066098690032959,
+      "eval_runtime": 1.3012,
+      "eval_samples_per_second": 768.545,
+      "eval_steps_per_second": 12.297,
+      "step": 442000
+    },
+    {
+      "epoch": 11.28,
+      "learning_rate": 2.035966441899249e-05,
+      "loss": 0.2687,
+      "step": 442500
+    },
+    {
+      "epoch": 11.29,
+      "learning_rate": 2.0182409546203555e-05,
+      "loss": 0.2688,
+      "step": 443000
+    },
+    {
+      "epoch": 11.29,
+      "eval_loss": 0.812473714351654,
+      "eval_runtime": 1.3079,
+      "eval_samples_per_second": 764.56,
+      "eval_steps_per_second": 12.233,
+      "step": 443000
+    },
+    {
+      "epoch": 11.3,
+      "learning_rate": 2.000662901698415e-05,
+      "loss": 0.2689,
+      "step": 443500
+    },
+    {
+      "epoch": 11.32,
+      "learning_rate": 1.983232475364195e-05,
+      "loss": 0.2686,
+      "step": 444000
+    },
+    {
+      "epoch": 11.32,
+      "eval_loss": 0.8055201768875122,
+      "eval_runtime": 1.3423,
+      "eval_samples_per_second": 744.998,
+      "eval_steps_per_second": 11.92,
+      "step": 444000
+    },
+    {
+      "epoch": 11.33,
+      "learning_rate": 1.9659498662340474e-05,
+      "loss": 0.2686,
+      "step": 444500
+    },
+    {
+      "epoch": 11.34,
+      "learning_rate": 1.948815263307819e-05,
+      "loss": 0.2686,
+      "step": 445000
+    },
+    {
+      "epoch": 11.34,
+      "eval_loss": 0.8064922094345093,
+      "eval_runtime": 1.2899,
+      "eval_samples_per_second": 775.27,
+      "eval_steps_per_second": 12.404,
+      "step": 445000
+    },
+    {
+      "epoch": 11.35,
+      "learning_rate": 1.9318288539667765e-05,
+      "loss": 0.2686,
+      "step": 445500
+    },
+    {
+      "epoch": 11.37,
+      "learning_rate": 1.914990823971574e-05,
+      "loss": 0.2685,
+      "step": 446000
+    },
+    {
+      "epoch": 11.37,
+      "eval_loss": 0.813357412815094,
+      "eval_runtime": 1.286,
+      "eval_samples_per_second": 777.596,
+      "eval_steps_per_second": 12.442,
+      "step": 446000
+    },
+    {
+      "epoch": 11.38,
+      "learning_rate": 1.8983013574602096e-05,
+      "loss": 0.2687,
+      "step": 446500
+    },
+    {
+      "epoch": 11.39,
+      "learning_rate": 1.8817606369460156e-05,
+      "loss": 0.2684,
+      "step": 447000
+    },
+    {
+      "epoch": 11.39,
+      "eval_loss": 0.806776225566864,
+      "eval_runtime": 1.2826,
+      "eval_samples_per_second": 779.686,
+      "eval_steps_per_second": 12.475,
+      "step": 447000
+    },
+    {
+      "epoch": 11.4,
+      "learning_rate": 1.865368843315663e-05,
+      "loss": 0.2684,
+      "step": 447500
+    },
+    {
+      "epoch": 11.42,
+      "learning_rate": 1.8491261558271762e-05,
+      "loss": 0.2683,
+      "step": 448000
+    },
+    {
+      "epoch": 11.42,
+      "eval_loss": 0.808623194694519,
+      "eval_runtime": 1.2653,
+      "eval_samples_per_second": 790.357,
+      "eval_steps_per_second": 12.646,
+      "step": 448000
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 1.833032752107986e-05,
+      "loss": 0.2682,
+      "step": 448500
+    },
+    {
+      "epoch": 11.44,
+      "learning_rate": 1.817088808152978e-05,
+      "loss": 0.2684,
+      "step": 449000
+    },
+    {
+      "epoch": 11.44,
+      "eval_loss": 0.8024921417236328,
+      "eval_runtime": 1.2578,
+      "eval_samples_per_second": 795.067,
+      "eval_steps_per_second": 12.721,
+      "step": 449000
+    },
+    {
+      "epoch": 11.46,
+      "learning_rate": 1.801294498322569e-05,
+      "loss": 0.2685,
+      "step": 449500
+    },
+    {
+      "epoch": 11.47,
+      "learning_rate": 1.7856499953407978e-05,
+      "loss": 0.2682,
+      "step": 450000
+    },
+    {
+      "epoch": 11.47,
+      "eval_loss": 0.8072661757469177,
+      "eval_runtime": 1.2702,
+      "eval_samples_per_second": 787.258,
+      "eval_steps_per_second": 12.596,
+      "step": 450000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.4057285838034505e+22,
+  "total_flos": 1.4376772976809005e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5997fc3c43be6a9667fa07314f7e899550168c519b5f1cc4e4addad00b4f02db
+oid sha256:2291b66065799571b4264696030000d7ec1a0e86601a7f2aefc345f1b8fac97d
 size 102501541