Training in progress, step 370000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c017dc7aa51a43ed67b54be4391afb3209331a95386c7a0f1faefbfda3688b82
+oid sha256:8884578ecff20bdc143758e28e0d85c34dad8dbfa37132c1e5318c8f80a9a1be
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d6df4782178506acacd0c83df02e5b041758e0dad6be6ff1fb20dae19c22b2
+oid sha256:797df8ba5787bd4a5fbf872ca4b3fe3fdb3db1dba64902a8c55adee164838ae0
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9e7aa2b8e2ccb71915d50d53e92b984c37ae39fd879c08b1e03ec5f916c1ce
+oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9e7aa2b8e2ccb71915d50d53e92b984c37ae39fd879c08b1e03ec5f916c1ce
+oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9e7aa2b8e2ccb71915d50d53e92b984c37ae39fd879c08b1e03ec5f916c1ce
+oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9e7aa2b8e2ccb71915d50d53e92b984c37ae39fd879c08b1e03ec5f916c1ce
+oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9e7aa2b8e2ccb71915d50d53e92b984c37ae39fd879c08b1e03ec5f916c1ce
+oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9e7aa2b8e2ccb71915d50d53e92b984c37ae39fd879c08b1e03ec5f916c1ce
+oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9e7aa2b8e2ccb71915d50d53e92b984c37ae39fd879c08b1e03ec5f916c1ce
+oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9e7aa2b8e2ccb71915d50d53e92b984c37ae39fd879c08b1e03ec5f916c1ce
+oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6e54422706a010aa16b679660182e5a0c0f546c43656852cb88a82c1d45dccf
+oid sha256:580594f4768ecd1bd92e87dca92e874365a397305161c1f8781b79f1f0b613ba
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.174779550435803,
-  "global_step": 360000,
+  "epoch": 9.429634537947909,
+  "global_step": 370000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7206,11 +7206,211 @@
       "eval_samples_per_second": 733.817,
       "eval_steps_per_second": 11.741,
       "step": 360000
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 6.746049527150238e-05,
+      "loss": 0.276,
+      "step": 360500
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 6.707871421704209e-05,
+      "loss": 0.2757,
+      "step": 361000
+    },
+    {
+      "epoch": 9.2,
+      "eval_loss": 0.8061186075210571,
+      "eval_runtime": 1.2926,
+      "eval_samples_per_second": 773.629,
+      "eval_steps_per_second": 12.378,
+      "step": 361000
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 6.669789465567683e-05,
+      "loss": 0.2754,
+      "step": 361500
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 6.631804075198838e-05,
+      "loss": 0.2754,
+      "step": 362000
+    },
+    {
+      "epoch": 9.23,
+      "eval_loss": 0.8106433153152466,
+      "eval_runtime": 1.3154,
+      "eval_samples_per_second": 760.201,
+      "eval_steps_per_second": 12.163,
+      "step": 362000
+    },
+    {
+      "epoch": 9.24,
+      "learning_rate": 6.593915665999816e-05,
+      "loss": 0.275,
+      "step": 362500
+    },
+    {
+      "epoch": 9.25,
+      "learning_rate": 6.55612465231219e-05,
+      "loss": 0.2755,
+      "step": 363000
+    },
+    {
+      "epoch": 9.25,
+      "eval_loss": 0.8047894835472107,
+      "eval_runtime": 1.3007,
+      "eval_samples_per_second": 768.793,
+      "eval_steps_per_second": 12.301,
+      "step": 363000
+    },
+    {
+      "epoch": 9.26,
+      "learning_rate": 6.518431447412434e-05,
+      "loss": 0.2754,
+      "step": 363500
+    },
+    {
+      "epoch": 9.28,
+      "learning_rate": 6.480836463507392e-05,
+      "loss": 0.2753,
+      "step": 364000
+    },
+    {
+      "epoch": 9.28,
+      "eval_loss": 0.8103929758071899,
+      "eval_runtime": 1.3172,
+      "eval_samples_per_second": 759.199,
+      "eval_steps_per_second": 12.147,
+      "step": 364000
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 6.443340111729786e-05,
+      "loss": 0.2753,
+      "step": 364500
+    },
+    {
+      "epoch": 9.3,
+      "learning_rate": 6.405942802133713e-05,
+      "loss": 0.2753,
+      "step": 365000
+    },
+    {
+      "epoch": 9.3,
+      "eval_loss": 0.8095191717147827,
+      "eval_runtime": 1.3369,
+      "eval_samples_per_second": 747.972,
+      "eval_steps_per_second": 11.968,
+      "step": 365000
+    },
+    {
+      "epoch": 9.31,
+      "learning_rate": 6.36864494369016e-05,
+      "loss": 0.2754,
+      "step": 365500
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 6.331446944282534e-05,
+      "loss": 0.2753,
+      "step": 366000
+    },
+    {
+      "epoch": 9.33,
+      "eval_loss": 0.8096633553504944,
+      "eval_runtime": 1.2639,
+      "eval_samples_per_second": 791.187,
+      "eval_steps_per_second": 12.659,
+      "step": 366000
+    },
+    {
+      "epoch": 9.34,
+      "learning_rate": 6.294349210702188e-05,
+      "loss": 0.2748,
+      "step": 366500
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 6.257352148643998e-05,
+      "loss": 0.2752,
+      "step": 367000
+    },
+    {
+      "epoch": 9.35,
+      "eval_loss": 0.808983564376831,
+      "eval_runtime": 1.349,
+      "eval_samples_per_second": 741.265,
+      "eval_steps_per_second": 11.86,
+      "step": 367000
+    },
+    {
+      "epoch": 9.37,
+      "learning_rate": 6.220456162701908e-05,
+      "loss": 0.2751,
+      "step": 367500
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 6.183661656364515e-05,
+      "loss": 0.2749,
+      "step": 368000
+    },
+    {
+      "epoch": 9.38,
+      "eval_loss": 0.8059231638908386,
+      "eval_runtime": 1.3338,
+      "eval_samples_per_second": 749.736,
+      "eval_steps_per_second": 11.996,
+      "step": 368000
+    },
+    {
+      "epoch": 9.39,
+      "learning_rate": 6.146969032010631e-05,
+      "loss": 0.2747,
+      "step": 368500
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 6.110378690904928e-05,
+      "loss": 0.2749,
+      "step": 369000
+    },
+    {
+      "epoch": 9.4,
+      "eval_loss": 0.8113678097724915,
+      "eval_runtime": 1.2927,
+      "eval_samples_per_second": 773.561,
+      "eval_steps_per_second": 12.377,
+      "step": 369000
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 6.073891033193507e-05,
+      "loss": 0.2749,
+      "step": 369500
+    },
+    {
+      "epoch": 9.43,
+      "learning_rate": 6.037506457899553e-05,
+      "loss": 0.2747,
+      "step": 370000
+    },
+    {
+      "epoch": 9.43,
+      "eval_loss": 0.8089262843132019,
+      "eval_runtime": 1.3047,
+      "eval_samples_per_second": 766.44,
+      "eval_steps_per_second": 12.263,
+      "step": 370000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.1501415685664595e+22,
+  "total_flos": 1.1820902824439095e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d6df4782178506acacd0c83df02e5b041758e0dad6be6ff1fb20dae19c22b2
+oid sha256:797df8ba5787bd4a5fbf872ca4b3fe3fdb3db1dba64902a8c55adee164838ae0
 size 102501541