Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b262f3940750b190d96db404d8b7be748afd37e7722c173c295ae970e72d408f
+oid sha256:dcbb71ee6902820938fb7191246d8d93bb293cabd8d7e19570813e3bd71858fb
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41267e907c3c64a9eab9a9be9e42135251f0170acce84b7512dcf74b73603d6
+oid sha256:813c3bc201a3d6b8c1f9f27a12e5ae8d332dd8fa1dd981f77aaed37dd2821d1b
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff383314706f04a5be47f7718a16317dcbc2e34ef67666665654cf6c6ee365b
+oid sha256:fda46c45207c477583d8570015b878d6c2d34bc9f248ab28ce54748ea88ac403
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45a60ece43c7f2b86d8fa5a261371b3d68475d4bd4f09601e0100b9c7dc8846c
+oid sha256:b567b22b755ea350861d319b375faafd7e69841d532b0cb359c63888848bb7a2
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec42c25eb7478ac84d4d9417b6c2bb3174731b719c2aa0a659b71f10e98687e
+oid sha256:621aa918e7d94e76e980dd52e6d602b019ed8ae919fe1ca65a5ac903747bec67
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.788438098554762,
-  "global_step": 55000,
+  "epoch": 5.223750652968832,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -754,11 +754,79 @@
       "eval_samples_per_second": 286.186,
       "eval_steps_per_second": 4.522,
       "step": 55000
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 4.7616157225640255e-05,
+      "loss": 0.4173,
+      "step": 55500
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 4.6914687204096124e-05,
+      "loss": 0.4152,
+      "step": 56000
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 4.621530849337495e-05,
+      "loss": 0.4153,
+      "step": 56500
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 4.5518193654708575e-05,
+      "loss": 0.4156,
+      "step": 57000
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 4.48235146907523e-05,
+      "loss": 0.4149,
+      "step": 57500
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 4.413282443085026e-05,
+      "loss": 0.4138,
+      "step": 58000
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 4.344352505188909e-05,
+      "loss": 0.4138,
+      "step": 58500
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 4.2757173441071825e-05,
+      "loss": 0.4129,
+      "step": 59000
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 4.2073938945388334e-05,
+      "loss": 0.4128,
+      "step": 59500
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 4.1393990142726966e-05,
+      "loss": 0.4133,
+      "step": 60000
+    },
+    {
+      "epoch": 5.22,
+      "eval_loss": 0.3932584524154663,
+      "eval_runtime": 17.6982,
+      "eval_samples_per_second": 282.515,
+      "eval_steps_per_second": 4.464,
+      "step": 60000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 2.590349259484095e+21,
+  "total_flos": 2.8258237064667857e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41267e907c3c64a9eab9a9be9e42135251f0170acce84b7512dcf74b73603d6
+oid sha256:813c3bc201a3d6b8c1f9f27a12e5ae8d332dd8fa1dd981f77aaed37dd2821d1b
 size 449471589