Training in progress, step 40000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5028e680b90d0d5deb58c782fcd2654d9815241c8789819c0ef4b4a5d0227dd1
+oid sha256:cfd90268a183d4a4023e5612c8fb0216ae28336b775995df418dab01a0f952f3
 size 202193937

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ec0fa394e10e50451293d1035a84eba2d3d01f6d72f6c0c1bd4739fe3ee776
+oid sha256:1cfa522f93b8ede7d3066bcbe6d05c94f3a226c317ea2a1bebd0b5057965b5b7
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43991d7af84e9540d8f27d2f0d1e420a0cf71dfe1da000898814055b8f62473
+oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43991d7af84e9540d8f27d2f0d1e420a0cf71dfe1da000898814055b8f62473
+oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43991d7af84e9540d8f27d2f0d1e420a0cf71dfe1da000898814055b8f62473
+oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43991d7af84e9540d8f27d2f0d1e420a0cf71dfe1da000898814055b8f62473
+oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43991d7af84e9540d8f27d2f0d1e420a0cf71dfe1da000898814055b8f62473
+oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43991d7af84e9540d8f27d2f0d1e420a0cf71dfe1da000898814055b8f62473
+oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43991d7af84e9540d8f27d2f0d1e420a0cf71dfe1da000898814055b8f62473
+oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43991d7af84e9540d8f27d2f0d1e420a0cf71dfe1da000898814055b8f62473
+oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff9b79eba2b3c3487d57b5f9509b60a9305753a31bdaa8757ad442412114850e
+oid sha256:a74054da3729955ad5eacae83f875e2df84ec7d4ca3ed3437d6f2cf84557171f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6989911228127402,
-  "global_step": 30000,
+  "epoch": 0.9319881637503203,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -606,11 +606,211 @@
       "eval_samples_per_second": 1736.053,
       "eval_steps_per_second": 27.644,
       "step": 30000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002999040758362914,
+      "loss": 0.3731,
+      "step": 30500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00029988584471039094,
+      "loss": 0.3713,
+      "step": 31000
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.35287660360336304,
+      "eval_runtime": 1.3423,
+      "eval_samples_per_second": 1637.545,
+      "eval_steps_per_second": 26.076,
+      "step": 31000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002998660291361054,
+      "loss": 0.3699,
+      "step": 31500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002998446293301349,
+      "loss": 0.3681,
+      "step": 32000
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.35174888372421265,
+      "eval_runtime": 1.3006,
+      "eval_samples_per_second": 1690.029,
+      "eval_steps_per_second": 26.911,
+      "step": 32000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002998216455265042,
+      "loss": 0.3667,
+      "step": 32500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00029979707797656046,
+      "loss": 0.3656,
+      "step": 33000
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.34766125679016113,
+      "eval_runtime": 1.3363,
+      "eval_samples_per_second": 1644.872,
+      "eval_steps_per_second": 26.192,
+      "step": 33000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00029977092694897053,
+      "loss": 0.3641,
+      "step": 33500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002997431927297178,
+      "loss": 0.3626,
+      "step": 34000
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.3423311412334442,
+      "eval_runtime": 1.3208,
+      "eval_samples_per_second": 1664.116,
+      "eval_steps_per_second": 26.499,
+      "step": 34000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00029971387562209936,
+      "loss": 0.3616,
+      "step": 34500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00029968297594672226,
+      "loss": 0.3601,
+      "step": 35000
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 0.34427037835121155,
+      "eval_runtime": 1.2929,
+      "eval_samples_per_second": 1700.099,
+      "eval_steps_per_second": 27.072,
+      "step": 35000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002996504940415005,
+      "loss": 0.3589,
+      "step": 35500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00029961643026165096,
+      "loss": 0.3577,
+      "step": 36000
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.34002143144607544,
+      "eval_runtime": 1.2974,
+      "eval_samples_per_second": 1694.186,
+      "eval_steps_per_second": 26.977,
+      "step": 36000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00029958078497968973,
+      "loss": 0.3568,
+      "step": 36500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002995435585854278,
+      "loss": 0.3555,
+      "step": 37000
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.3368704915046692,
+      "eval_runtime": 1.3166,
+      "eval_samples_per_second": 1669.417,
+      "eval_steps_per_second": 26.583,
+      "step": 37000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002995047514859671,
+      "loss": 0.3542,
+      "step": 37500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002994643641056959,
+      "loss": 0.3532,
+      "step": 38000
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 0.3357352018356323,
+      "eval_runtime": 1.2847,
+      "eval_samples_per_second": 1710.953,
+      "eval_steps_per_second": 27.244,
+      "step": 38000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.000299422396886284,
+      "loss": 0.3523,
+      "step": 38500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002993788502866783,
+      "loss": 0.3514,
+      "step": 39000
+    },
+    {
+      "epoch": 0.91,
+      "eval_loss": 0.33294928073883057,
+      "eval_runtime": 1.272,
+      "eval_samples_per_second": 1728.032,
+      "eval_steps_per_second": 27.516,
+      "step": 39000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00029933372478309746,
+      "loss": 0.3503,
+      "step": 39500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00029928702086902664,
+      "loss": 0.3493,
+      "step": 40000
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 0.332314670085907,
+      "eval_runtime": 1.318,
+      "eval_samples_per_second": 1667.699,
+      "eval_steps_per_second": 26.556,
+      "step": 40000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 9.584614163235e+20,
+  "total_flos": 1.277948555098e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ec0fa394e10e50451293d1035a84eba2d3d01f6d72f6c0c1bd4739fe3ee776
+oid sha256:1cfa522f93b8ede7d3066bcbe6d05c94f3a226c317ea2a1bebd0b5057965b5b7
 size 102501541