Training in progress, step 540000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b387d4f9f04e8c9303a92c0ddb4fecebb2d329d1bad50fe16824cce0afa53f
+oid sha256:3cce3705a1c8b8d8d4264e967a6f95acb36457da2099b2e0f10708b7bc8b02f7
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1625f5e23d8f1ad41b87b90859c51a9a7e8e0c2f203d02de268a294a2c0644e2
+oid sha256:10387ca16d2be862ac39f8a7dd403935e8f63c843663bd6c250c84cc9afccb17
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f39691b2c245489425bdb803bff6f96b52586788af71785b57e3d212e063166a
+oid sha256:2d6a05599d68c81d8f28a8a18f0fba06e8b974a2ea269e8529ff0449633b1df0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7326fef653b7a70f9f155f4acb1e3ee4232444cd6d9204bc168a2d2e45c727
-size 14503
+oid sha256:fa440e15eff2f549811ca7872de21865d48dd11cb8b6542ab71253c6945d2c0d
+size 14567

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee1218ce9b7108b8255e87b249fdf7f16f07137f90939e9084af13b071ce6ffe
-size 14439
+oid sha256:24051c040fbf1ab84f4d62008b8fd2ab04d63f18b11e30fd62216b89cf665574
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c5bbfb1027111f06815f4497b89bb272c0861b51bd6d39c91af85222b32d16
-size 14567
+oid sha256:28fbe9c447e2dbc1b0d90d8fb5fa32bb60a8b179ed5bdf4dc956ff563b72c4fc
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286366dc95c1888d75c773db3569adfce838dc105f2552542e8252bf7ab19ebf
+oid sha256:312a9240a59bfb6f588851dc4640a2bea628ee45c54031017e35bcac8788a581
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.093209339258173,
-  "global_step": 530000,
+  "epoch": 8.245911402263044,
+  "global_step": 540000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3928,11 +3928,85 @@
       "eval_samples_per_second": 986.75,
       "eval_steps_per_second": 15.788,
       "step": 530000
+    },
+    {
+      "epoch": 8.11,
+      "learning_rate": 7.861117648512725e-05,
+      "loss": 0.2613,
+      "step": 531000
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 7.837974429185103e-05,
+      "loss": 0.2614,
+      "step": 532000
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 7.814832981743164e-05,
+      "loss": 0.2614,
+      "step": 533000
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 7.791693559258072e-05,
+      "loss": 0.2608,
+      "step": 534000
+    },
+    {
+      "epoch": 8.17,
+      "learning_rate": 7.768556414778842e-05,
+      "loss": 0.2606,
+      "step": 535000
+    },
+    {
+      "epoch": 8.17,
+      "eval_runtime": 1.097,
+      "eval_samples_per_second": 911.552,
+      "eval_steps_per_second": 14.585,
+      "step": 535000
+    },
+    {
+      "epoch": 8.18,
+      "learning_rate": 7.74542180132958e-05,
+      "loss": 0.2606,
+      "step": 536000
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 7.72228997190671e-05,
+      "loss": 0.2608,
+      "step": 537000
+    },
+    {
+      "epoch": 8.22,
+      "learning_rate": 7.699161179476217e-05,
+      "loss": 0.2604,
+      "step": 538000
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 7.676035676970863e-05,
+      "loss": 0.2606,
+      "step": 539000
+    },
+    {
+      "epoch": 8.25,
+      "learning_rate": 7.652913717287443e-05,
+      "loss": 0.2604,
+      "step": 540000
+    },
+    {
+      "epoch": 8.25,
+      "eval_runtime": 1.1778,
+      "eval_samples_per_second": 849.063,
+      "eval_steps_per_second": 13.585,
+      "step": 540000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.7153085780632086e+22,
+  "total_flos": 3.785408839093556e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1625f5e23d8f1ad41b87b90859c51a9a7e8e0c2f203d02de268a294a2c0644e2
+oid sha256:10387ca16d2be862ac39f8a7dd403935e8f63c843663bd6c250c84cc9afccb17
 size 449471589