Training in progress, step 530000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dff40157bf3742c8b21f53f2322e73342fc065e8772423f3999033957d5a66bd
+oid sha256:00b387d4f9f04e8c9303a92c0ddb4fecebb2d329d1bad50fe16824cce0afa53f
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e0e94c5a6037200ef903f8fe73caf33854246cdca4d17f5dd1d03ffcdcb4f5
+oid sha256:1625f5e23d8f1ad41b87b90859c51a9a7e8e0c2f203d02de268a294a2c0644e2
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:384aea0e5f6d022d8f660cfde96c61a9f493d19909a7af22387885e66de278b6
+oid sha256:f39691b2c245489425bdb803bff6f96b52586788af71785b57e3d212e063166a
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc0739a046c0e6446f60e8683c8b90305e2fea169b76b64f56106f66b6420d0
+oid sha256:af7326fef653b7a70f9f155f4acb1e3ee4232444cd6d9204bc168a2d2e45c727
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e44d4ec16875ec90faf97785738c3779aee1f020966316b5892073b0622b56d
-size 14503
+oid sha256:ee1218ce9b7108b8255e87b249fdf7f16f07137f90939e9084af13b071ce6ffe
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09aadf2a5ab4eb2176572147df0f7002cbd6c8df6b1aea2c4ed7fd23277b83ba
-size 14503
+oid sha256:f9c5bbfb1027111f06815f4497b89bb272c0861b51bd6d39c91af85222b32d16
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd06a603e7f0cb9a198767e099f70695383faf72e0162b6befb3712823cfe27e
+oid sha256:286366dc95c1888d75c773db3569adfce838dc105f2552542e8252bf7ab19ebf
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.940507276253302,
-  "global_step": 520000,
+  "epoch": 8.093209339258173,
+  "global_step": 530000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3854,11 +3854,85 @@
       "eval_samples_per_second": 952.036,
       "eval_steps_per_second": 15.233,
       "step": 520000
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 8.092591609553747e-05,
+      "loss": 0.2623,
+      "step": 521000
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 8.069444593175975e-05,
+      "loss": 0.2622,
+      "step": 522000
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 8.046296817363259e-05,
+      "loss": 0.262,
+      "step": 523000
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 8.023148535255965e-05,
+      "loss": 0.2619,
+      "step": 524000
+    },
+    {
+      "epoch": 8.02,
+      "learning_rate": 7.999999999999999e-05,
+      "loss": 0.262,
+      "step": 525000
+    },
+    {
+      "epoch": 8.02,
+      "eval_runtime": 1.1375,
+      "eval_samples_per_second": 879.131,
+      "eval_steps_per_second": 14.066,
+      "step": 525000
+    },
+    {
+      "epoch": 8.03,
+      "learning_rate": 7.976851464744033e-05,
+      "loss": 0.2616,
+      "step": 526000
+    },
+    {
+      "epoch": 8.05,
+      "learning_rate": 7.953703182636741e-05,
+      "loss": 0.2616,
+      "step": 527000
+    },
+    {
+      "epoch": 8.06,
+      "learning_rate": 7.930555406824026e-05,
+      "loss": 0.2617,
+      "step": 528000
+    },
+    {
+      "epoch": 8.08,
+      "learning_rate": 7.907408390446254e-05,
+      "loss": 0.2614,
+      "step": 529000
+    },
+    {
+      "epoch": 8.09,
+      "learning_rate": 7.884262386635489e-05,
+      "loss": 0.2607,
+      "step": 530000
+    },
+    {
+      "epoch": 8.09,
+      "eval_runtime": 1.0134,
+      "eval_samples_per_second": 986.75,
+      "eval_steps_per_second": 15.788,
+      "step": 530000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.6452089741010102e+22,
+  "total_flos": 3.7153085780632086e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e0e94c5a6037200ef903f8fe73caf33854246cdca4d17f5dd1d03ffcdcb4f5
+oid sha256:1625f5e23d8f1ad41b87b90859c51a9a7e8e0c2f203d02de268a294a2c0644e2
 size 449471589