Training in progress, step 490000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4060e633dae015e5639b74a57f1603654125aa36a5a7f3f6681895bc39045ec
+oid sha256:bba175f94af3131ddc7e585c8d0c85376ebd1433f20a5a01a35d8488fc39885b
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f459617feff07cc080660c37736876af343cf74d6054e3f49e34fa66dc0e7730
+oid sha256:dc6bd31ef6b75d2ff57b791613279c5afe6c8244312a64f00fb084519b8aaac6
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
+oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
+oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
+oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
+oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
+oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
+oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
+oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
+oid sha256:90520ba7330b686999308b8bbfc39f4cdbd59c0cf0ab7c6ba32bba11cfac21a5
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbfa680b1187d22cc7371654116ef29dab3c85749ad34b845956736ad3b3612
+oid sha256:7d798ff13d72fe751bc0ea721c37eb1e98064dde5819b90f3504db53fdceee97
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.70663811563169,
-  "global_step": 480000,
+  "epoch": 10.929693076374019,
+  "global_step": 490000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9606,11 +9606,211 @@
       "eval_samples_per_second": 1170.393,
       "eval_steps_per_second": 18.343,
       "step": 480000
+    },
+    {
+      "epoch": 10.72,
+      "learning_rate": 1.1204252864868377e-05,
+      "loss": 0.2538,
+      "step": 480500
+    },
+    {
+      "epoch": 10.73,
+      "learning_rate": 1.1143368309400725e-05,
+      "loss": 0.2539,
+      "step": 481000
+    },
+    {
+      "epoch": 10.73,
+      "eval_loss": 0.23603801429271698,
+      "eval_runtime": 1.9718,
+      "eval_samples_per_second": 1164.912,
+      "eval_steps_per_second": 18.257,
+      "step": 481000
+    },
+    {
+      "epoch": 10.74,
+      "learning_rate": 1.1084056947009348e-05,
+      "loss": 0.2538,
+      "step": 481500
+    },
+    {
+      "epoch": 10.75,
+      "learning_rate": 1.1026319426313837e-05,
+      "loss": 0.2538,
+      "step": 482000
+    },
+    {
+      "epoch": 10.75,
+      "eval_loss": 0.23858527839183807,
+      "eval_runtime": 1.961,
+      "eval_samples_per_second": 1171.312,
+      "eval_steps_per_second": 18.358,
+      "step": 482000
+    },
+    {
+      "epoch": 10.76,
+      "learning_rate": 1.097015637872247e-05,
+      "loss": 0.2538,
+      "step": 482500
+    },
+    {
+      "epoch": 10.77,
+      "learning_rate": 1.0915568418425301e-05,
+      "loss": 0.2537,
+      "step": 483000
+    },
+    {
+      "epoch": 10.77,
+      "eval_loss": 0.23714858293533325,
+      "eval_runtime": 2.009,
+      "eval_samples_per_second": 1143.375,
+      "eval_steps_per_second": 17.92,
+      "step": 483000
+    },
+    {
+      "epoch": 10.78,
+      "learning_rate": 1.0862556142387571e-05,
+      "loss": 0.2539,
+      "step": 483500
+    },
+    {
+      "epoch": 10.8,
+      "learning_rate": 1.081112013034298e-05,
+      "loss": 0.2537,
+      "step": 484000
+    },
+    {
+      "epoch": 10.8,
+      "eval_loss": 0.23877692222595215,
+      "eval_runtime": 1.9856,
+      "eval_samples_per_second": 1156.824,
+      "eval_steps_per_second": 18.13,
+      "step": 484000
+    },
+    {
+      "epoch": 10.81,
+      "learning_rate": 1.0761260944787561e-05,
+      "loss": 0.2551,
+      "step": 484500
+    },
+    {
+      "epoch": 10.82,
+      "learning_rate": 1.0712979130973347e-05,
+      "loss": 0.2542,
+      "step": 485000
+    },
+    {
+      "epoch": 10.82,
+      "eval_loss": 0.23765695095062256,
+      "eval_runtime": 1.9888,
+      "eval_samples_per_second": 1154.965,
+      "eval_steps_per_second": 18.101,
+      "step": 485000
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 1.0666275216902535e-05,
+      "loss": 0.2539,
+      "step": 485500
+    },
+    {
+      "epoch": 10.84,
+      "learning_rate": 1.0621149713321656e-05,
+      "loss": 0.2539,
+      "step": 486000
+    },
+    {
+      "epoch": 10.84,
+      "eval_loss": 0.23621481657028198,
+      "eval_runtime": 1.9428,
+      "eval_samples_per_second": 1182.329,
+      "eval_steps_per_second": 18.53,
+      "step": 486000
+    },
+    {
+      "epoch": 10.85,
+      "learning_rate": 1.0577603113715964e-05,
+      "loss": 0.2539,
+      "step": 486500
+    },
+    {
+      "epoch": 10.86,
+      "learning_rate": 1.0535635894304106e-05,
+      "loss": 0.2535,
+      "step": 487000
+    },
+    {
+      "epoch": 10.86,
+      "eval_loss": 0.23733575642108917,
+      "eval_runtime": 1.9603,
+      "eval_samples_per_second": 1171.773,
+      "eval_steps_per_second": 18.365,
+      "step": 487000
+    },
+    {
+      "epoch": 10.87,
+      "learning_rate": 1.0495248514032875e-05,
+      "loss": 0.2539,
+      "step": 487500
+    },
+    {
+      "epoch": 10.89,
+      "learning_rate": 1.045644141457218e-05,
+      "loss": 0.2533,
+      "step": 488000
+    },
+    {
+      "epoch": 10.89,
+      "eval_loss": 0.23612964153289795,
+      "eval_runtime": 1.9923,
+      "eval_samples_per_second": 1152.93,
+      "eval_steps_per_second": 18.069,
+      "step": 488000
+    },
+    {
+      "epoch": 10.9,
+      "learning_rate": 1.0419215020310254e-05,
+      "loss": 0.2534,
+      "step": 488500
+    },
+    {
+      "epoch": 10.91,
+      "learning_rate": 1.0383569738348988e-05,
+      "loss": 0.2533,
+      "step": 489000
+    },
+    {
+      "epoch": 10.91,
+      "eval_loss": 0.2368190884590149,
+      "eval_runtime": 1.9507,
+      "eval_samples_per_second": 1177.524,
+      "eval_steps_per_second": 18.455,
+      "step": 489000
+    },
+    {
+      "epoch": 10.92,
+      "learning_rate": 1.0349505958499436e-05,
+      "loss": 0.2534,
+      "step": 489500
+    },
+    {
+      "epoch": 10.93,
+      "learning_rate": 1.0317024053277693e-05,
+      "loss": 0.2535,
+      "step": 490000
+    },
+    {
+      "epoch": 10.93,
+      "eval_loss": 0.23948417603969574,
+      "eval_runtime": 2.0351,
+      "eval_samples_per_second": 1128.67,
+      "eval_steps_per_second": 17.689,
+      "step": 490000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.5335098118561847e+22,
+  "total_flos": 1.5654585257336347e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f459617feff07cc080660c37736876af343cf74d6054e3f49e34fa66dc0e7730
+oid sha256:dc6bd31ef6b75d2ff57b791613279c5afe6c8244312a64f00fb084519b8aaac6
 size 102501541