Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aab534a941de846cd5acb29f0cac50eed51613e2cbe9b058b2cef36db3ca849
+oid sha256:6a827260146648964e1c0473647fdd276801d3a7209c7df3eb87d73e4518f74c
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dec19b920534a5898acdfc98e79e9b70791428c6bd7a25c13bcdf61c6645ec5
+oid sha256:5671fc2a233d9d155c62d2c9fb67023f69b7d1fe8428c704d638f8bca4866498
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9736a584cb8ae3d7bd8ffe95a660707985f449648611e3cc9b4d825e5958e568
-size 14439
+oid sha256:ad14af5dd7abce3c61cc5e578461c309f69e60de21b0c054a8f3f4c7bba9e4e6
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef650477065ab5caa49e1061409f9f0faf9c6cf935e3b3d122d891a44dfd7336
+oid sha256:e8388ca66f8f9c6c8c8157a81f6bde550f1b25a31aa2aa22e4704b5ef4e971ee
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2a2ced2ef326c6276aee305dcedbdce1bdac86a7e92e323f89ded2bbda8df1d
-size 14503
+oid sha256:782279cba623055efc3193875769c57ec4b067421ccba6e615fbf1b5214e724b
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8434c6987c2b0551e47b946336d0f273a4237d950c380ff8d131694cde1e29a8
+oid sha256:749c503bc6cade081df3a923d8ae2be2ccf707f9f3b893640379c785aa6facd4
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8d45ebb28c7b9f23a6abeafd90122c1ed22446a846f1cf2ac94e95c51e1adb
+oid sha256:90ff94ce099b109f6c343c1450c170171a247badda4343ab1850180869cf03e2
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.763510315024356,
-  "global_step": 50000,
+  "epoch": 0.9162123780292272,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -376,11 +376,85 @@
       "eval_samples_per_second": 963.96,
       "eval_steps_per_second": 15.423,
       "step": 50000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001499996172456075,
+      "loss": 0.4824,
+      "step": 51000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014999846898661572,
+      "loss": 0.4778,
+      "step": 52000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00014999655523558183,
+      "loss": 0.474,
+      "step": 53000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00014999387601343436,
+      "loss": 0.4694,
+      "step": 54000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00014999043134947282,
+      "loss": 0.4651,
+      "step": 55000
+    },
+    {
+      "epoch": 0.84,
+      "eval_runtime": 1.0465,
+      "eval_samples_per_second": 955.566,
+      "eval_steps_per_second": 15.289,
+      "step": 55000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00014998622128136748,
+      "loss": 0.4608,
+      "step": 56000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.000149981245855159,
+      "loss": 0.4566,
+      "step": 57000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00014997550512525784,
+      "loss": 0.4523,
+      "step": 58000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0001499689991544437,
+      "loss": 0.4483,
+      "step": 59000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00014996172801386482,
+      "loss": 0.4447,
+      "step": 60000
+    },
+    {
+      "epoch": 0.92,
+      "eval_runtime": 1.2288,
+      "eval_samples_per_second": 813.826,
+      "eval_steps_per_second": 13.021,
+      "step": 60000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.505013051517357e+21,
+  "total_flos": 4.2060156618208287e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dec19b920534a5898acdfc98e79e9b70791428c6bd7a25c13bcdf61c6645ec5
+oid sha256:5671fc2a233d9d155c62d2c9fb67023f69b7d1fe8428c704d638f8bca4866498
 size 449471589