Training in progress, step 240000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a06ef5c009b6a3d34b61b8e9435e48bd8704c1092e28f5d3a8a0669a2a565c45
+oid sha256:11144856c02c8e972a36fb5b42d4223035071c4a917ea79c06d582d2b9be6085
 size 893441530

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f9300ed2f42668d1280e1852bf99100220c183e1a5aa40fe963881c2f1f15c
+oid sha256:1ad81878847ff45e1880bc9e193537b6a982e87fb64a13bbf06eba84c2c3ee6f
 size 454197066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da60bc481c5e8dde4e51a48ffefd72b80167a866448e54613b2b81fb34be2af3
+oid sha256:20be28e08eeb080e0d87de2c1d006e31a433ae3d529b46a69dfe770492fd995c
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1786a2f6edec81fd73665bbfadc34243a09e187302f15861e7ba28d522bf54
+oid sha256:c781a803fdb01dba917962146262a56eb080213a823923503263cf460fa3ac80
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23,
-  "global_step": 230000,
+  "epoch": 0.24,
+  "global_step": 240000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1708,11 +1708,85 @@
       "eval_samples_per_second": 106.178,
       "eval_steps_per_second": 13.272,
       "step": 230000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.798940649585048e-05,
+      "loss": 0.3703,
+      "step": 231000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7981234828858012e-05,
+      "loss": 0.3696,
+      "step": 232000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7973023724659226e-05,
+      "loss": 0.3696,
+      "step": 233000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7964773273049443e-05,
+      "loss": 0.3696,
+      "step": 234000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.795648356425428e-05,
+      "loss": 0.3689,
+      "step": 235000
+    },
+    {
+      "epoch": 0.23,
+      "eval_runtime": 3392.6969,
+      "eval_samples_per_second": 100.113,
+      "eval_steps_per_second": 12.514,
+      "step": 235000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7948154688928657e-05,
+      "loss": 0.3691,
+      "step": 236000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.793978673815583e-05,
+      "loss": 0.368,
+      "step": 237000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7931379803446365e-05,
+      "loss": 0.3662,
+      "step": 238000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.792293397673715e-05,
+      "loss": 0.3634,
+      "step": 239000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.791444935039039e-05,
+      "loss": 0.365,
+      "step": 240000
+    },
+    {
+      "epoch": 0.24,
+      "eval_runtime": 3401.6269,
+      "eval_samples_per_second": 99.85,
+      "eval_steps_per_second": 12.481,
+      "step": 240000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 2.036560339843154e+21,
+  "total_flos": 2.125106441575465e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f9300ed2f42668d1280e1852bf99100220c183e1a5aa40fe963881c2f1f15c
+oid sha256:1ad81878847ff45e1880bc9e193537b6a982e87fb64a13bbf06eba84c2c3ee6f
 size 454197066