Training in progress, step 15000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dfae293f92d7ce42f799b1cfa3ff2324b449307ea5b1ffe909db5fdb43bc62e
+oid sha256:28187497dc6decd09c29c448cbe3c8f216a461b847b3dfe76c961eefcba760dd
 size 1115579397

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53993b59de6e841bf87528e770e4f0d58566f5d261e3f8b554bc4ea54782393a
+oid sha256:6cde4c8b5d264bfb9f8a06eee531d1d4753c6c5f780f672725d48cb200528c80
 size 557971229

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7350114a3b349562121e30f7b1c4e639541c40ef9b4afb3665041b3fdaa6980a
+oid sha256:21e8419e75fb4597ac6804eea271b8d8c7570e10eeb8b3dcf0e419dec78e3abc
 size 15597

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dbc5097d3af03f81acfa53fb6f73f2a12d4ea9707e4a957c56edb34d729f7f1
+oid sha256:4078cba31618fb628b6b959898b3af21da737bbca86995dd1501bc1bcdffba9e
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7118ba55ae4b4d75ed6bdb199e80512c65f03c3b9ca20e7918b6fb4ec034c32d
+oid sha256:09b501e7cbbfd105661937636cf270aadedef3375bca9faacf1296b961e54ce2
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1519631371796102,
-  "global_step": 12000,
+  "epoch": 1.4399539214745127,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,11 +189,47 @@
       "eval_samples_per_second": 7.655,
       "eval_steps_per_second": 0.383,
       "step": 12000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001400403187098013,
+      "loss": 1.8898,
+      "step": 12500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00013764039550734377,
+      "loss": 1.8321,
+      "step": 13000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00013524047230488627,
+      "loss": 1.8986,
+      "step": 13500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013284054910242874,
+      "loss": 1.8934,
+      "step": 14000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001304406258999712,
+      "loss": 1.873,
+      "step": 14500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0001280407026975137,
+      "loss": 1.8582,
+      "step": 15000
     }
   ],
   "max_steps": 41668,
   "num_train_epochs": 4,
-  "total_flos": 1.4630840437764096e+17,
+  "total_flos": 1.8288586333495296e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53993b59de6e841bf87528e770e4f0d58566f5d261e3f8b554bc4ea54782393a
+oid sha256:6cde4c8b5d264bfb9f8a06eee531d1d4753c6c5f780f672725d48cb200528c80
 size 557971229