Training in progress, step 600000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccf7cac5a21a11d7f667ccf92a06d4ca4f6e11529886f97a81cee946646a7850
+oid sha256:fa3e03e9ecd0026fc79482638e67bfbb968ad2fb2a2251138fea448958ad2549
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dfc2dd7ec4e8c1ccc6143bbc6f13f079f3e7e48a8bbfe20e040b742b8d0a1df
+oid sha256:ff751ae05b56a482e47a728b40ba33717079b6b3d77d92ae8823ddd2e524f99f
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f3d7d4e29826fad65749e3d1c71437aab80b1c0083abdcf52c0c2924f0e5e69
+oid sha256:4e165b16ec4c4b7c229152423019cf42f78fde1837556dbc7f0e0a0d03eb92f2
 size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17829d91164c4f44a41a5ead32db30cb5aee27cae3b78beefecb92d0468bafdc
-size 14503
+oid sha256:d6acb016c9e03d8943408e9c25efa54b6209d293a5e14d07d93d97c6c5df995b
+size 14567

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a63261dcff7584c8844400c561ac2e5b385953523dee796cb56c42af169cadd9
+oid sha256:a372c6638d81ac9bbd86bc3b09ec3143aa46879e63bc5f10b74bd9c0aea9c32b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41591d972d5c0406eef4b610a30a04b97cf79722da627acb09c85c762f5f46f
+oid sha256:6a1ca703723e30170efc3dee97c3c7534e4adefa45396ecce1b5c543326f570d
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf17ad9f6f8f5230f179dea9ee53bd043cf1c420455dc89092d4dbf5e8505225
+oid sha256:34904d09dca1d79fb910d11916faed0bf8107fa6c955fc65b114b5f30425510a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.0094217172874,
-  "global_step": 590000,
+  "epoch": 9.162123780292271,
+  "global_step": 600000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4372,11 +4372,85 @@
       "eval_samples_per_second": 1109.201,
       "eval_steps_per_second": 17.747,
       "step": 590000
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 6.484294934833822e-05,
+      "loss": 0.2552,
+      "step": 591000
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 6.461703860381628e-05,
+      "loss": 0.2551,
+      "step": 592000
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 6.439129608489559e-05,
+      "loss": 0.2555,
+      "step": 593000
+    },
+    {
+      "epoch": 9.07,
+      "learning_rate": 6.41657242602602e-05,
+      "loss": 0.2549,
+      "step": 594000
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 6.39403255967274e-05,
+      "loss": 0.255,
+      "step": 595000
+    },
+    {
+      "epoch": 9.09,
+      "eval_runtime": 1.1107,
+      "eval_samples_per_second": 900.319,
+      "eval_steps_per_second": 14.405,
+      "step": 595000
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 6.371510255922088e-05,
+      "loss": 0.2545,
+      "step": 596000
+    },
+    {
+      "epoch": 9.12,
+      "learning_rate": 6.349005761074372e-05,
+      "loss": 0.2547,
+      "step": 597000
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 6.326519321235139e-05,
+      "loss": 0.2546,
+      "step": 598000
+    },
+    {
+      "epoch": 9.15,
+      "learning_rate": 6.304051182312496e-05,
+      "loss": 0.2549,
+      "step": 599000
+    },
+    {
+      "epoch": 9.16,
+      "learning_rate": 6.281601590014407e-05,
+      "loss": 0.2546,
+      "step": 600000
+    },
+    {
+      "epoch": 9.16,
+      "eval_runtime": 1.0772,
+      "eval_samples_per_second": 928.316,
+      "eval_steps_per_second": 14.853,
+      "step": 600000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.135909487177143e+22,
+  "total_flos": 4.20600974820749e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dfc2dd7ec4e8c1ccc6143bbc6f13f079f3e7e48a8bbfe20e040b742b8d0a1df
+oid sha256:ff751ae05b56a482e47a728b40ba33717079b6b3d77d92ae8823ddd2e524f99f
 size 449471589