Training in progress, step 190000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1b0d96f667a7b16c0c7d2f49737d4497a498e6fce49a93b982d94c8de8309c
+oid sha256:564dabf1934e46cc7ba6a8d36285b89de4adb73c031fca3ba9a7a2cd768c72d1
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:434932d378cb26c672decfb210d19f8b4a125ed1b9443d7969a7371379940fc8
+oid sha256:93645087c6aeead636db9d9e4b7cbf206d1b0f761762ede97a32712b0dcff1ba
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016c297c140d00f5c3ece68fb6697280ca6918ef74f0bee47ce148ceaa7045be
+oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016c297c140d00f5c3ece68fb6697280ca6918ef74f0bee47ce148ceaa7045be
+oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016c297c140d00f5c3ece68fb6697280ca6918ef74f0bee47ce148ceaa7045be
+oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016c297c140d00f5c3ece68fb6697280ca6918ef74f0bee47ce148ceaa7045be
+oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016c297c140d00f5c3ece68fb6697280ca6918ef74f0bee47ce148ceaa7045be
+oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016c297c140d00f5c3ece68fb6697280ca6918ef74f0bee47ce148ceaa7045be
+oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016c297c140d00f5c3ece68fb6697280ca6918ef74f0bee47ce148ceaa7045be
+oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016c297c140d00f5c3ece68fb6697280ca6918ef74f0bee47ce148ceaa7045be
+oid sha256:6434323d38390968de269207dfc4f56d03e65926668b055e0435e4eab6a847eb
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae7e48b658f6388c6c044e6d37239970a21307494d626979f7e10630dfa93207
+oid sha256:196e9b55e2db27c384076a5416088da2b3e045d13b4c3f579694349cd8bb530e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.029978586723768,
-  "global_step": 180000,
+  "epoch": 8.476088508208422,
+  "global_step": 190000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3606,11 +3606,211 @@
       "eval_samples_per_second": 987.138,
       "eval_steps_per_second": 15.471,
       "step": 180000
+    },
+    {
+      "epoch": 8.05,
+      "learning_rate": 0.00012612565995880976,
+      "loss": 0.3725,
+      "step": 180500
+    },
+    {
+      "epoch": 8.07,
+      "learning_rate": 0.00012457808290921774,
+      "loss": 0.3709,
+      "step": 181000
+    },
+    {
+      "epoch": 8.07,
+      "eval_loss": 0.3426642119884491,
+      "eval_runtime": 2.2304,
+      "eval_samples_per_second": 1029.848,
+      "eval_steps_per_second": 16.14,
+      "step": 181000
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 0.00012303839809876525,
+      "loss": 0.3705,
+      "step": 181500
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 0.00012150667287825382,
+      "loss": 0.3707,
+      "step": 182000
+    },
+    {
+      "epoch": 8.12,
+      "eval_loss": 0.3444533050060272,
+      "eval_runtime": 2.1579,
+      "eval_samples_per_second": 1064.458,
+      "eval_steps_per_second": 16.683,
+      "step": 182000
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 0.00011998297425030656,
+      "loss": 0.3705,
+      "step": 182500
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 0.00011846736886643775,
+      "loss": 0.3703,
+      "step": 183000
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": 0.34523776173591614,
+      "eval_runtime": 2.2575,
+      "eval_samples_per_second": 1017.476,
+      "eval_steps_per_second": 15.947,
+      "step": 183000
+    },
+    {
+      "epoch": 8.19,
+      "learning_rate": 0.00011695992302413651,
+      "loss": 0.3702,
+      "step": 183500
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 0.00011546070266396771,
+      "loss": 0.3701,
+      "step": 184000
+    },
+    {
+      "epoch": 8.21,
+      "eval_loss": 0.34200483560562134,
+      "eval_runtime": 2.2775,
+      "eval_samples_per_second": 1008.549,
+      "eval_steps_per_second": 15.807,
+      "step": 184000
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 0.00011396977336668645,
+      "loss": 0.3701,
+      "step": 184500
+    },
+    {
+      "epoch": 8.25,
+      "learning_rate": 0.00011248720035037021,
+      "loss": 0.3699,
+      "step": 185000
+    },
+    {
+      "epoch": 8.25,
+      "eval_loss": 0.34288346767425537,
+      "eval_runtime": 2.2113,
+      "eval_samples_per_second": 1038.766,
+      "eval_steps_per_second": 16.28,
+      "step": 185000
+    },
+    {
+      "epoch": 8.28,
+      "learning_rate": 0.00011101304846756577,
+      "loss": 0.3699,
+      "step": 185500
+    },
+    {
+      "epoch": 8.3,
+      "learning_rate": 0.00010954738220245183,
+      "loss": 0.3697,
+      "step": 186000
+    },
+    {
+      "epoch": 8.3,
+      "eval_loss": 0.3431689739227295,
+      "eval_runtime": 2.222,
+      "eval_samples_per_second": 1033.767,
+      "eval_steps_per_second": 16.202,
+      "step": 186000
+    },
+    {
+      "epoch": 8.32,
+      "learning_rate": 0.00010809026566801912,
+      "loss": 0.3695,
+      "step": 186500
+    },
+    {
+      "epoch": 8.34,
+      "learning_rate": 0.00010664176260326507,
+      "loss": 0.3696,
+      "step": 187000
+    },
+    {
+      "epoch": 8.34,
+      "eval_loss": 0.3424961268901825,
+      "eval_runtime": 2.2738,
+      "eval_samples_per_second": 1010.209,
+      "eval_steps_per_second": 15.833,
+      "step": 187000
+    },
+    {
+      "epoch": 8.36,
+      "learning_rate": 0.00010520193637040641,
+      "loss": 0.3697,
+      "step": 187500
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 0.00010377084995210682,
+      "loss": 0.3696,
+      "step": 188000
+    },
+    {
+      "epoch": 8.39,
+      "eval_loss": 0.34366557002067566,
+      "eval_runtime": 2.2531,
+      "eval_samples_per_second": 1019.467,
+      "eval_steps_per_second": 15.978,
+      "step": 188000
+    },
+    {
+      "epoch": 8.41,
+      "learning_rate": 0.00010234856594872234,
+      "loss": 0.3692,
+      "step": 188500
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 0.00010093514657556295,
+      "loss": 0.3694,
+      "step": 189000
+    },
+    {
+      "epoch": 8.43,
+      "eval_loss": 0.34253063797950745,
+      "eval_runtime": 2.2641,
+      "eval_samples_per_second": 1014.519,
+      "eval_steps_per_second": 15.9,
+      "step": 189000
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 9.953065366017073e-05,
+      "loss": 0.369,
+      "step": 189500
+    },
+    {
+      "epoch": 8.48,
+      "learning_rate": 9.813514863961586e-05,
+      "loss": 0.369,
+      "step": 190000
+    },
+    {
+      "epoch": 8.48,
+      "eval_loss": 0.34287169575691223,
+      "eval_runtime": 2.2268,
+      "eval_samples_per_second": 1031.502,
+      "eval_steps_per_second": 16.166,
+      "step": 190000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 2.882966995727085e+21,
+  "total_flos": 3.043134998592889e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:434932d378cb26c672decfb210d19f8b4a125ed1b9443d7969a7371379940fc8
+oid sha256:93645087c6aeead636db9d9e4b7cbf206d1b0f761762ede97a32712b0dcff1ba
 size 25761253