Training in progress, step 200000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c34ac780b372cb50ed12ba9fbab64719e7e6f0c18cee015d6bdb3bcb76dea71d
+oid sha256:c076bfb7efb96d5024b8a4ddaf3dce5d10dacaac14c357e2e1f987048cc997c2
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99dced181e974fd3eec8a6b81e04bd93e9d3478bda598e89eba595e55d1a22ef
+oid sha256:339fd6d90694d0866ca99f79daa02d5d9cac878b08d046df675a5dc91c855959
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e1c87bdea00ca3e6e9b20f6190563c56b2601359c213756f776a09add69b81e
+oid sha256:a3bdead3f6f5710faae22c375f543db349a175165befd270c4b65176d5d8e8d8
 size 15523

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9307e85dd6ba8a5ceae8769503e23251f8d4d2261d33516d9a1d3db2d17488d
+oid sha256:512587e6e0a7f210ac71b21a96f20cc79ec6ca8b511a1b62e00ee74e107dedd8
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de8c8841ca37efa9880cc96031ae2dad9eefb662fd05d23d903fbf6205093680
+oid sha256:a8dacaf51330a60fa39e5519f592a0627bc39ca3df9fe19b7cf9decf6b5521a0
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.925,
-  "global_step": 195000,
+  "epoch": 0.95,
+  "global_step": 200000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2658,11 +2658,79 @@
       "eval_samples_per_second": 78.69,
       "eval_steps_per_second": 1.23,
       "step": 195000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.011695311017034e-05,
+      "loss": 0.4091,
+      "step": 195500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.0092820389759403e-05,
+      "loss": 0.4099,
+      "step": 196000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.0071430695926197e-05,
+      "loss": 0.4091,
+      "step": 196500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.0052836503470134e-05,
+      "loss": 0.4093,
+      "step": 197000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.003703895936859e-05,
+      "loss": 0.4093,
+      "step": 197500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.002406224534175e-05,
+      "loss": 0.4082,
+      "step": 198000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.0013872772159007e-05,
+      "loss": 0.4105,
+      "step": 198500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.0006459132350263e-05,
+      "loss": 0.409,
+      "step": 199000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0001845001670741e-05,
+      "loss": 0.4096,
+      "step": 199500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.000003066474176e-05,
+      "loss": 0.4099,
+      "step": 200000
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 0.3822266459465027,
+      "eval_runtime": 77.6338,
+      "eval_samples_per_second": 82.438,
+      "eval_steps_per_second": 1.288,
+      "step": 200000
     }
   ],
   "max_steps": 200000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 4.592114813612851e+21,
+  "total_flos": 4.709861347295232e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99dced181e974fd3eec8a6b81e04bd93e9d3478bda598e89eba595e55d1a22ef
+oid sha256:339fd6d90694d0866ca99f79daa02d5d9cac878b08d046df675a5dc91c855959
 size 449471589