Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44519022516715e3b4aa9fbebd26a8f16d69cc1037c43939223444845c039b2a
+oid sha256:11cf0c7d6b061f7dad52edce9e5088c7de01b0d50fde085c881cac1ce38869f0
 size 50044241

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31ddb9e289da6dc236cf93f3881df915ba1b345fb3bc4108ca78271c87c7807
+oid sha256:32de19aae4938ccc6ceff2fe466b7bb7987521081cfbb1f7e1384e10682c2045
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95236c288314cf7e95c084d5233e1be1e022395a42503d56c52a71f4cff32b4
+oid sha256:fe81dd181a7243c753033870695d21544789f2b7d0e68df1f7bb5c7aa16b0ba0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95236c288314cf7e95c084d5233e1be1e022395a42503d56c52a71f4cff32b4
+oid sha256:fe81dd181a7243c753033870695d21544789f2b7d0e68df1f7bb5c7aa16b0ba0
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95236c288314cf7e95c084d5233e1be1e022395a42503d56c52a71f4cff32b4
+oid sha256:fe81dd181a7243c753033870695d21544789f2b7d0e68df1f7bb5c7aa16b0ba0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95236c288314cf7e95c084d5233e1be1e022395a42503d56c52a71f4cff32b4
+oid sha256:fe81dd181a7243c753033870695d21544789f2b7d0e68df1f7bb5c7aa16b0ba0
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95236c288314cf7e95c084d5233e1be1e022395a42503d56c52a71f4cff32b4
+oid sha256:fe81dd181a7243c753033870695d21544789f2b7d0e68df1f7bb5c7aa16b0ba0
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95236c288314cf7e95c084d5233e1be1e022395a42503d56c52a71f4cff32b4
+oid sha256:fe81dd181a7243c753033870695d21544789f2b7d0e68df1f7bb5c7aa16b0ba0
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95236c288314cf7e95c084d5233e1be1e022395a42503d56c52a71f4cff32b4
+oid sha256:fe81dd181a7243c753033870695d21544789f2b7d0e68df1f7bb5c7aa16b0ba0
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95236c288314cf7e95c084d5233e1be1e022395a42503d56c52a71f4cff32b4
+oid sha256:fe81dd181a7243c753033870695d21544789f2b7d0e68df1f7bb5c7aa16b0ba0
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9511edec0a698219a4fec94630f2bf1ec60055a31bda0393e6aadb5a36db13d
+oid sha256:6a14cae2e3d67695f0ffa4604dbaaa3f7147d70607921bb89c9afa09d57c87a5
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.230549607423269,
-  "global_step": 50000,
+  "epoch": 2.6766595289079227,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1006,11 +1006,211 @@
       "eval_samples_per_second": 1041.459,
       "eval_steps_per_second": 16.322,
       "step": 50000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.0005635104706129397,
+      "loss": 0.5958,
+      "step": 50500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.0005625648765345228,
+      "loss": 0.5924,
+      "step": 51000
+    },
+    {
+      "epoch": 2.28,
+      "eval_loss": 0.5799189209938049,
+      "eval_runtime": 2.2525,
+      "eval_samples_per_second": 1019.737,
+      "eval_steps_per_second": 15.982,
+      "step": 51000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.0005616080157340118,
+      "loss": 0.5872,
+      "step": 51500
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.0005606399300675978,
+      "loss": 0.5817,
+      "step": 52000
+    },
+    {
+      "epoch": 2.32,
+      "eval_loss": 0.5670354962348938,
+      "eval_runtime": 2.3437,
+      "eval_samples_per_second": 980.093,
+      "eval_steps_per_second": 15.361,
+      "step": 52000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.0005596606618824843,
+      "loss": 0.5766,
+      "step": 52500
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.0005586702540150338,
+      "loss": 0.5719,
+      "step": 53000
+    },
+    {
+      "epoch": 2.36,
+      "eval_loss": 0.5556795597076416,
+      "eval_runtime": 2.1734,
+      "eval_samples_per_second": 1056.846,
+      "eval_steps_per_second": 16.564,
+      "step": 53000
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 0.000557668749788895,
+      "loss": 0.5681,
+      "step": 53500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.0005566561930131072,
+      "loss": 0.5651,
+      "step": 54000
+    },
+    {
+      "epoch": 2.41,
+      "eval_loss": 0.5476705431938171,
+      "eval_runtime": 2.2374,
+      "eval_samples_per_second": 1026.619,
+      "eval_steps_per_second": 16.09,
+      "step": 54000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 0.000555632627980184,
+      "loss": 0.562,
+      "step": 54500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 0.0005545980994641758,
+      "loss": 0.5592,
+      "step": 55000
+    },
+    {
+      "epoch": 2.45,
+      "eval_loss": 0.5407888889312744,
+      "eval_runtime": 2.2932,
+      "eval_samples_per_second": 1001.641,
+      "eval_steps_per_second": 15.698,
+      "step": 55000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0005535526527187115,
+      "loss": 0.5563,
+      "step": 55500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.0005524963334750183,
+      "loss": 0.5534,
+      "step": 56000
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.536229133605957,
+      "eval_runtime": 2.1818,
+      "eval_samples_per_second": 1052.81,
+      "eval_steps_per_second": 16.5,
+      "step": 56000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 0.0005514291879399219,
+      "loss": 0.5496,
+      "step": 56500
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.000550351262793825,
+      "loss": 0.5446,
+      "step": 57000
+    },
+    {
+      "epoch": 2.54,
+      "eval_loss": 0.5251114964485168,
+      "eval_runtime": 2.298,
+      "eval_samples_per_second": 999.556,
+      "eval_steps_per_second": 15.666,
+      "step": 57000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 0.0005492626051886659,
+      "loss": 0.5392,
+      "step": 57500
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 0.0005481632627458546,
+      "loss": 0.5342,
+      "step": 58000
+    },
+    {
+      "epoch": 2.59,
+      "eval_loss": 0.5129896402359009,
+      "eval_runtime": 2.2194,
+      "eval_samples_per_second": 1034.968,
+      "eval_steps_per_second": 16.221,
+      "step": 58000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 0.0005470532835541911,
+      "loss": 0.529,
+      "step": 58500
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 0.000545932716167761,
+      "loss": 0.5239,
+      "step": 59000
+    },
+    {
+      "epoch": 2.63,
+      "eval_loss": 0.5024312734603882,
+      "eval_runtime": 2.205,
+      "eval_samples_per_second": 1041.743,
+      "eval_steps_per_second": 16.327,
+      "step": 59000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 0.000544801609603812,
+      "loss": 0.5193,
+      "step": 59500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 0.0005436600133406095,
+      "loss": 0.5147,
+      "step": 60000
+    },
+    {
+      "epoch": 2.68,
+      "eval_loss": 0.49465516209602356,
+      "eval_runtime": 2.2427,
+      "eval_samples_per_second": 1024.23,
+      "eval_steps_per_second": 16.052,
+      "step": 60000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 8.008257503646733e+20,
+  "total_flos": 9.609937532304774e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31ddb9e289da6dc236cf93f3881df915ba1b345fb3bc4108ca78271c87c7807
+oid sha256:32de19aae4938ccc6ceff2fe466b7bb7987521081cfbb1f7e1384e10682c2045
 size 25761253