Training in progress, step 510000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b95a50ec78668fd811c005abf1bba70b859c8d764791ff84497deae1229f2c4
+oid sha256:5396aadec40753879ec191ed6f1eae90ce19d71216456e008182ba20c1900e33
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e13cbf16b6089cae157b8c12b40fad7379685997616b524de934495a681d16
+oid sha256:c56b2869324d527babb9c2d9eb135d501fd6606ac9d608fd64dd0610d25503c0
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
+oid sha256:2879d0ce896bd313b65fbfcb2ce4eeab9210d4d071aa7fabb2f6d181da290650
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
+oid sha256:2879d0ce896bd313b65fbfcb2ce4eeab9210d4d071aa7fabb2f6d181da290650
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
+oid sha256:2879d0ce896bd313b65fbfcb2ce4eeab9210d4d071aa7fabb2f6d181da290650
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
+oid sha256:2879d0ce896bd313b65fbfcb2ce4eeab9210d4d071aa7fabb2f6d181da290650
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
+oid sha256:2879d0ce896bd313b65fbfcb2ce4eeab9210d4d071aa7fabb2f6d181da290650
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
+oid sha256:2879d0ce896bd313b65fbfcb2ce4eeab9210d4d071aa7fabb2f6d181da290650
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
+oid sha256:2879d0ce896bd313b65fbfcb2ce4eeab9210d4d071aa7fabb2f6d181da290650
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc9451aab89fbe5e4a74e5020bb5a2d0b3c56c76d6607e3134243128eb2c90e
+oid sha256:2879d0ce896bd313b65fbfcb2ce4eeab9210d4d071aa7fabb2f6d181da290650
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61639df917cea6bc1eea9e7a1f48d3f6c9acb9557d8752aa9847613f1b857ad8
+oid sha256:ce6a9467a251e9cbea13fa7869db249fdcb8d7f75671c56b9051c9e63a855aaa
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.576436211146181,
-  "global_step": 500000,
+  "epoch": 5.687964935369104,
+  "global_step": 510000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10006,11 +10006,211 @@
       "eval_samples_per_second": 880.873,
       "eval_steps_per_second": 13.806,
       "step": 500000
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 8.566519876711864e-05,
+      "loss": 0.2109,
+      "step": 500500
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 8.55498278627369e-05,
+      "loss": 0.2107,
+      "step": 501000
+    },
+    {
+      "epoch": 5.59,
+      "eval_loss": 0.1986326277256012,
+      "eval_runtime": 2.5229,
+      "eval_samples_per_second": 910.451,
+      "eval_steps_per_second": 14.269,
+      "step": 501000
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 8.543444178533773e-05,
+      "loss": 0.2101,
+      "step": 501500
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 8.531904085038221e-05,
+      "loss": 0.2104,
+      "step": 502000
+    },
+    {
+      "epoch": 5.6,
+      "eval_loss": 0.1985243856906891,
+      "eval_runtime": 2.533,
+      "eval_samples_per_second": 906.836,
+      "eval_steps_per_second": 14.212,
+      "step": 502000
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 8.520362537337214e-05,
+      "loss": 0.2104,
+      "step": 502500
+    },
+    {
+      "epoch": 5.61,
+      "learning_rate": 8.508819566984897e-05,
+      "loss": 0.2105,
+      "step": 503000
+    },
+    {
+      "epoch": 5.61,
+      "eval_loss": 0.19903981685638428,
+      "eval_runtime": 2.5776,
+      "eval_samples_per_second": 891.131,
+      "eval_steps_per_second": 13.966,
+      "step": 503000
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 8.497275205539314e-05,
+      "loss": 0.2103,
+      "step": 503500
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 8.485729484562307e-05,
+      "loss": 0.2104,
+      "step": 504000
+    },
+    {
+      "epoch": 5.62,
+      "eval_loss": 0.20253504812717438,
+      "eval_runtime": 2.542,
+      "eval_samples_per_second": 903.632,
+      "eval_steps_per_second": 14.162,
+      "step": 504000
+    },
+    {
+      "epoch": 5.63,
+      "learning_rate": 8.474182435619437e-05,
+      "loss": 0.21,
+      "step": 504500
+    },
+    {
+      "epoch": 5.63,
+      "learning_rate": 8.462634090279895e-05,
+      "loss": 0.2099,
+      "step": 505000
+    },
+    {
+      "epoch": 5.63,
+      "eval_loss": 0.20055775344371796,
+      "eval_runtime": 2.5318,
+      "eval_samples_per_second": 907.265,
+      "eval_steps_per_second": 14.219,
+      "step": 505000
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 8.451084480116415e-05,
+      "loss": 0.2099,
+      "step": 505500
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 8.439533636705194e-05,
+      "loss": 0.2102,
+      "step": 506000
+    },
+    {
+      "epoch": 5.64,
+      "eval_loss": 0.1988956183195114,
+      "eval_runtime": 2.5177,
+      "eval_samples_per_second": 912.354,
+      "eval_steps_per_second": 14.299,
+      "step": 506000
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 8.427981591625791e-05,
+      "loss": 0.2097,
+      "step": 506500
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 8.416428376461061e-05,
+      "loss": 0.2101,
+      "step": 507000
+    },
+    {
+      "epoch": 5.65,
+      "eval_loss": 0.20103515684604645,
+      "eval_runtime": 2.4839,
+      "eval_samples_per_second": 924.771,
+      "eval_steps_per_second": 14.494,
+      "step": 507000
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 8.404874022797049e-05,
+      "loss": 0.21,
+      "step": 507500
+    },
+    {
+      "epoch": 5.67,
+      "learning_rate": 8.393318562222916e-05,
+      "loss": 0.2102,
+      "step": 508000
+    },
+    {
+      "epoch": 5.67,
+      "eval_loss": 0.19926241040229797,
+      "eval_runtime": 2.6513,
+      "eval_samples_per_second": 866.384,
+      "eval_steps_per_second": 13.578,
+      "step": 508000
+    },
+    {
+      "epoch": 5.67,
+      "learning_rate": 8.381762026330858e-05,
+      "loss": 0.2101,
+      "step": 508500
+    },
+    {
+      "epoch": 5.68,
+      "learning_rate": 8.370204446715997e-05,
+      "loss": 0.2098,
+      "step": 509000
+    },
+    {
+      "epoch": 5.68,
+      "eval_loss": 0.2018594741821289,
+      "eval_runtime": 2.6012,
+      "eval_samples_per_second": 883.058,
+      "eval_steps_per_second": 13.84,
+      "step": 509000
+    },
+    {
+      "epoch": 5.68,
+      "learning_rate": 8.358645854976311e-05,
+      "loss": 0.2101,
+      "step": 509500
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 8.347086282712556e-05,
+      "loss": 0.2097,
+      "step": 510000
+    },
+    {
+      "epoch": 5.69,
+      "eval_loss": 0.19868962466716766,
+      "eval_runtime": 2.618,
+      "eval_samples_per_second": 877.377,
+      "eval_steps_per_second": 13.751,
+      "step": 510000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 3.504985669279779e+22,
+  "total_flos": 3.5750859303101263e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e13cbf16b6089cae157b8c12b40fad7379685997616b524de934495a681d16
+oid sha256:c56b2869324d527babb9c2d9eb135d501fd6606ac9d608fd64dd0610d25503c0
 size 449471589