Training in progress, step 620000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bbdb63dd5f35ddeda47e9dc139795456694d0aba5e0383355b4522b67e77b3
+oid sha256:c3b35f979d5fe4527b6f42c2add375e7239aec55be0317190f1a665e6ab5f35c
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b37572e353c74d53a74256f6a8b831fe7ecaed9eb997d03f96697e3f38be10fb
+oid sha256:a03035ba4bf151910d41d4c213cf2390c9903cf8cb85be4525c8f2b5574fe579
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e969b0a1f38bb709ff184bddc11e3e1b7a366f1f525d658e15c5e0e9638178b2
+oid sha256:bbb920f1348e13fdd02418f5a8bdde3a29115945de004c35412bd2480fdb9afa
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e472d706bbb24da1ae339dbf5b5e166d6a3aff07e50beb6830b013698716675c
+oid sha256:154b8f14236fa636789c866c5bab186dc1c4e26fc03e987f1aabe66a3981e8a2
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb9d01b196a085088b251b99e2302b0af5c57d846827fd2f433da2dd23ebd86a
-size 14567
+oid sha256:a933eb9e98ce78bdca0e9e206bab865aad1983b58e12a370b79e23c847c34cac
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f9539e61c7b8fd54fd055839d1a6ea3b2cd4ea6f97a1aef7d0a7c91c2429be6
-size 14503
+oid sha256:502983b98bc6a8911d0348894791667ff6481b824870d33d6fccaa23995ed7f4
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71de57969ec7a3201bd7bf6de3d6e1584c8439f398aacc61865ba691cc2653d6
+oid sha256:87df12c543e6333a1257623848db6de543e5639171e7cc03225528d064da559b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.314825843297143,
-  "global_step": 610000,
+  "epoch": 9.467527906302013,
+  "global_step": 620000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4520,11 +4520,85 @@
       "eval_samples_per_second": 972.365,
       "eval_steps_per_second": 15.558,
       "step": 610000
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 6.035950216040917e-05,
+      "loss": 0.2533,
+      "step": 611000
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 6.0137422719485145e-05,
+      "loss": 0.2531,
+      "step": 612000
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 5.991556049252401e-05,
+      "loss": 0.2532,
+      "step": 613000
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 5.969391790577551e-05,
+      "loss": 0.2532,
+      "step": 614000
+    },
+    {
+      "epoch": 9.39,
+      "learning_rate": 5.947249738308747e-05,
+      "loss": 0.2529,
+      "step": 615000
+    },
+    {
+      "epoch": 9.39,
+      "eval_runtime": 1.014,
+      "eval_samples_per_second": 986.174,
+      "eval_steps_per_second": 15.779,
+      "step": 615000
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 5.925130134587924e-05,
+      "loss": 0.2527,
+      "step": 616000
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 5.903033221311528e-05,
+      "loss": 0.2525,
+      "step": 617000
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 5.880959240127858e-05,
+      "loss": 0.2524,
+      "step": 618000
+    },
+    {
+      "epoch": 9.45,
+      "learning_rate": 5.858908432434438e-05,
+      "loss": 0.2525,
+      "step": 619000
+    },
+    {
+      "epoch": 9.47,
+      "learning_rate": 5.8368810393753684e-05,
+      "loss": 0.2524,
+      "step": 620000
+    },
+    {
+      "epoch": 9.47,
+      "eval_runtime": 1.0588,
+      "eval_samples_per_second": 944.48,
+      "eval_steps_per_second": 15.112,
+      "step": 620000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.276110009237837e+22,
+  "total_flos": 4.346210270268184e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b37572e353c74d53a74256f6a8b831fe7ecaed9eb997d03f96697e3f38be10fb
+oid sha256:a03035ba4bf151910d41d4c213cf2390c9903cf8cb85be4525c8f2b5574fe579
 size 449471589