Training in progress, step 50000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b79098aba355edf15cdcc2ba65841e59d94f2195e6563e00db7a5b77d0de1b0
+oid sha256:5aab534a941de846cd5acb29f0cac50eed51613e2cbe9b058b2cef36db3ca849
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c9245179e00ecfc159536796459f1277956357c9ae2eeba259fdadb204bca4
+oid sha256:5dec19b920534a5898acdfc98e79e9b70791428c6bd7a25c13bcdf61c6645ec5
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dab27e02a841889dd406a61f3825c3bf16e995606299fd6ab9fd7db009ed4e68
-size 14503
+oid sha256:9736a584cb8ae3d7bd8ffe95a660707985f449648611e3cc9b4d825e5958e568
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783ce381375b60e783f2e4204fc7d9689e81e56991f92e086a503c69636e5046
+oid sha256:ef650477065ab5caa49e1061409f9f0faf9c6cf935e3b3d122d891a44dfd7336
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59eabe2e991b1516dd6b66887718520f904de193e569a87238bb2d8904706701
+oid sha256:b2a2ced2ef326c6276aee305dcedbdce1bdac86a7e92e323f89ded2bbda8df1d
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b999227318d7857e7c42c9ad2f2208b186825e80265bff7952618efa8d3e7e
-size 14439
+oid sha256:8434c6987c2b0551e47b946336d0f273a4237d950c380ff8d131694cde1e29a8
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b5c694b40cd5a966b5116288c30b2f19979f1058d82965ee57335ae5f1e596
+oid sha256:5b8d45ebb28c7b9f23a6abeafd90122c1ed22446a846f1cf2ac94e95c51e1adb
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6108082520194847,
-  "global_step": 40000,
+  "epoch": 0.763510315024356,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -302,11 +302,85 @@
       "eval_samples_per_second": 985.598,
       "eval_steps_per_second": 15.77,
       "step": 40000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00012299999999999998,
+      "loss": 0.5163,
+      "step": 41000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 0.5126,
+      "step": 42000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000129,
+      "loss": 0.5094,
+      "step": 43000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00013199999999999998,
+      "loss": 0.5061,
+      "step": 44000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000135,
+      "loss": 0.5036,
+      "step": 45000
+    },
+    {
+      "epoch": 0.69,
+      "eval_runtime": 1.0362,
+      "eval_samples_per_second": 965.067,
+      "eval_steps_per_second": 15.441,
+      "step": 45000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000138,
+      "loss": 0.4995,
+      "step": 46000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00014099999999999998,
+      "loss": 0.4967,
+      "step": 47000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 0.4934,
+      "step": 48000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000147,
+      "loss": 0.4898,
+      "step": 49000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00015,
+      "loss": 0.4863,
+      "step": 50000
+    },
+    {
+      "epoch": 0.76,
+      "eval_runtime": 1.0374,
+      "eval_samples_per_second": 963.96,
+      "eval_steps_per_second": 15.423,
+      "step": 50000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.804010441213886e+21,
+  "total_flos": 3.505013051517357e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c9245179e00ecfc159536796459f1277956357c9ae2eeba259fdadb204bca4
+oid sha256:5dec19b920534a5898acdfc98e79e9b70791428c6bd7a25c13bcdf61c6645ec5
 size 449471589