Training in progress, step 500000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04556cb11706d3015b54a3833cc4ab2399848632d8b3574e432d9d26ca86dd6c
+oid sha256:0b95a50ec78668fd811c005abf1bba70b859c8d764791ff84497deae1229f2c4
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00240df886e866d9b8adc06a07729b4b469a354fe39ac54cefe302442e7a0f3d
+oid sha256:70e13cbf16b6089cae157b8c12b40fad7379685997616b524de934495a681d16
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
+oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
+oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
+oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
+oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
+oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
+oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
+oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
+oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74800ce917e328df8d2e651e5da6a2b131e41e32b116f92b00e5f62a5503f854
+oid sha256:61639df917cea6bc1eea9e7a1f48d3f6c9acb9557d8752aa9847613f1b857ad8
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.4649074869232575,
-  "global_step": 490000,
+  "epoch": 5.576436211146181,
+  "global_step": 500000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9806,11 +9806,211 @@
       "eval_samples_per_second": 862.22,
       "eval_steps_per_second": 13.513,
       "step": 490000
+    },
+    {
+      "epoch": 5.47,
+      "learning_rate": 8.796894510727945e-05,
+      "loss": 0.2116,
+      "step": 490500
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 8.78539438398963e-05,
+      "loss": 0.2112,
+      "step": 491000
+    },
+    {
+      "epoch": 5.48,
+      "eval_loss": 0.20125530660152435,
+      "eval_runtime": 2.6454,
+      "eval_samples_per_second": 868.302,
+      "eval_steps_per_second": 13.609,
+      "step": 491000
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 8.773892110013058e-05,
+      "loss": 0.2116,
+      "step": 491500
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 8.762387720245008e-05,
+      "loss": 0.2114,
+      "step": 492000
+    },
+    {
+      "epoch": 5.49,
+      "eval_loss": 0.2021346092224121,
+      "eval_runtime": 2.6349,
+      "eval_samples_per_second": 871.772,
+      "eval_steps_per_second": 13.663,
+      "step": 492000
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 8.750881246138043e-05,
+      "loss": 0.2115,
+      "step": 492500
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 8.73937271915042e-05,
+      "loss": 0.2115,
+      "step": 493000
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 0.20063868165016174,
+      "eval_runtime": 2.6134,
+      "eval_samples_per_second": 878.933,
+      "eval_steps_per_second": 13.775,
+      "step": 493000
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 8.727862170746019e-05,
+      "loss": 0.2112,
+      "step": 493500
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 8.716349632394235e-05,
+      "loss": 0.2113,
+      "step": 494000
+    },
+    {
+      "epoch": 5.51,
+      "eval_loss": 0.2013174444437027,
+      "eval_runtime": 2.5993,
+      "eval_samples_per_second": 883.689,
+      "eval_steps_per_second": 13.85,
+      "step": 494000
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 8.70483513556991e-05,
+      "loss": 0.2111,
+      "step": 494500
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 8.69331871175324e-05,
+      "loss": 0.2111,
+      "step": 495000
+    },
+    {
+      "epoch": 5.52,
+      "eval_loss": 0.20253530144691467,
+      "eval_runtime": 2.655,
+      "eval_samples_per_second": 865.174,
+      "eval_steps_per_second": 13.56,
+      "step": 495000
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 8.681800392429684e-05,
+      "loss": 0.2111,
+      "step": 495500
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 8.67028020908989e-05,
+      "loss": 0.2112,
+      "step": 496000
+    },
+    {
+      "epoch": 5.53,
+      "eval_loss": 0.2021927386522293,
+      "eval_runtime": 2.5884,
+      "eval_samples_per_second": 887.415,
+      "eval_steps_per_second": 13.908,
+      "step": 496000
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 8.658758193229601e-05,
+      "loss": 0.211,
+      "step": 496500
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 8.647234376349565e-05,
+      "loss": 0.2107,
+      "step": 497000
+    },
+    {
+      "epoch": 5.54,
+      "eval_loss": 0.19982150197029114,
+      "eval_runtime": 2.5228,
+      "eval_samples_per_second": 910.512,
+      "eval_steps_per_second": 14.27,
+      "step": 497000
+    },
+    {
+      "epoch": 5.55,
+      "learning_rate": 8.635708789955458e-05,
+      "loss": 0.2108,
+      "step": 497500
+    },
+    {
+      "epoch": 5.55,
+      "learning_rate": 8.624181465557794e-05,
+      "loss": 0.2109,
+      "step": 498000
+    },
+    {
+      "epoch": 5.55,
+      "eval_loss": 0.2010236382484436,
+      "eval_runtime": 2.4638,
+      "eval_samples_per_second": 932.313,
+      "eval_steps_per_second": 14.612,
+      "step": 498000
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 8.612652434671837e-05,
+      "loss": 0.2108,
+      "step": 498500
+    },
+    {
+      "epoch": 5.57,
+      "learning_rate": 8.601121728817519e-05,
+      "loss": 0.211,
+      "step": 499000
+    },
+    {
+      "epoch": 5.57,
+      "eval_loss": 0.19817927479743958,
+      "eval_runtime": 2.5254,
+      "eval_samples_per_second": 909.547,
+      "eval_steps_per_second": 14.255,
+      "step": 499000
+    },
+    {
+      "epoch": 5.57,
+      "learning_rate": 8.589589379519346e-05,
+      "loss": 0.2109,
+      "step": 499500
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 8.578055418306327e-05,
+      "loss": 0.2107,
+      "step": 500000
+    },
+    {
+      "epoch": 5.58,
+      "eval_loss": 0.199160635471344,
+      "eval_runtime": 2.6076,
+      "eval_samples_per_second": 880.873,
+      "eval_steps_per_second": 13.806,
+      "step": 500000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 3.434885408249432e+22,
+  "total_flos": 3.504985669279779e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00240df886e866d9b8adc06a07729b4b469a354fe39ac54cefe302442e7a0f3d
+oid sha256:70e13cbf16b6089cae157b8c12b40fad7379685997616b524de934495a681d16
 size 449471589