Training in progress, step 570000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ab35ed4dfefd8dd33fb26f0ecf541378b45831852a54aeb8f775b92df21738
+oid sha256:8a767a78fa4809e168b3ccdaca8245fdd800f92f9fb131a29e7c678020a7b2e1
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5321ac05ebfcc017f8c041dae493ee5ce4f8eaceb97ac0dbd2e5b7ff1909ad9f
+oid sha256:2f451f7904b0f8403b186893bae5bf08f2c2acf369a21d50224d0be67c5692d4
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c595110edd758e9e0a71c6845041a2d22c5cf58679d14f120b5cb63abc84493
+oid sha256:28edfca80c69ce874f473f07c4b7e161b12e6d09912377717af008dd4d50a13b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:715147c7486ebd169cb8e58f73bc4aa6a8bc3129e6581c29e50cbdd2f06aae29
+oid sha256:35b65d15b0a371107c6c614a483d347936ef1bc44210919862c9b83a7094116f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da28d7b7099d5f85e00929347b66a092dbe7cfdb67ae3df05ae5bcb6ee3a235
+oid sha256:916d53efc24960a2419b0c56ff522c7980d4be4e94feb1e3f3194d2ea4a6489c
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d187c6fad30982ef7c6cac2865f72e7d2e1a26561d9ab8f74149dc0f5b946f
+oid sha256:eaddfaade81997be2461768daaef367db08e33d6fa1ca3618aadc35b99ca7474
 size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af9a25b33d29c3fd157c79676adec6abbe35f3978d907c7efc857fe0437c64ac
+oid sha256:e62e41706c3cdebd0963ceae6fb24ae079cf26e6452a67e31e4c02f3a80456e6
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.551315528272786,
-  "global_step": 560000,
+  "epoch": 8.704017591277658,
+  "global_step": 570000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4150,11 +4150,85 @@
       "eval_samples_per_second": 853.863,
       "eval_steps_per_second": 13.662,
       "step": 560000
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 7.168618306865838e-05,
+      "loss": 0.2583,
+      "step": 561000
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 7.145638164375779e-05,
+      "loss": 0.2588,
+      "step": 562000
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 7.122667365049869e-05,
+      "loss": 0.2578,
+      "step": 563000
+    },
+    {
+      "epoch": 8.61,
+      "learning_rate": 7.099706160093098e-05,
+      "loss": 0.2578,
+      "step": 564000
+    },
+    {
+      "epoch": 8.63,
+      "learning_rate": 7.076754800605516e-05,
+      "loss": 0.2579,
+      "step": 565000
+    },
+    {
+      "epoch": 8.63,
+      "eval_runtime": 1.0129,
+      "eval_samples_per_second": 987.305,
+      "eval_steps_per_second": 15.797,
+      "step": 565000
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 7.053813537579523e-05,
+      "loss": 0.2581,
+      "step": 566000
+    },
+    {
+      "epoch": 8.66,
+      "learning_rate": 7.030882621897088e-05,
+      "loss": 0.2575,
+      "step": 567000
+    },
+    {
+      "epoch": 8.67,
+      "learning_rate": 7.00796230432703e-05,
+      "loss": 0.2574,
+      "step": 568000
+    },
+    {
+      "epoch": 8.69,
+      "learning_rate": 6.985052835522279e-05,
+      "loss": 0.2572,
+      "step": 569000
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 6.962154466017105e-05,
+      "loss": 0.2572,
+      "step": 570000
+    },
+    {
+      "epoch": 8.7,
+      "eval_runtime": 1.048,
+      "eval_samples_per_second": 954.187,
+      "eval_steps_per_second": 15.267,
+      "step": 570000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.92560936115425e+22,
+  "total_flos": 3.995709622184597e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5321ac05ebfcc017f8c041dae493ee5ce4f8eaceb97ac0dbd2e5b7ff1909ad9f
+oid sha256:2f451f7904b0f8403b186893bae5bf08f2c2acf369a21d50224d0be67c5692d4
 size 449471589