Training in progress, step 970000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f217d4f2435c53b27b3ffb23b807fa09f40f06e34bfe7a070589d6890dd66f
+oid sha256:de1b3977166c4e20fc41f424497409f61e5dbee702d8ad14048093e7cfab3225
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5376abe825ff6d04d360831bbfd37e2e2d959d6e490763218e7e38b5c10ca1
+oid sha256:ebc5b0eb8c3bb3dd69db934b29e5beccddfae1a796cf948830a8b05766d44497
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b07a1641f2eb1fc754b2daa11b1bd54bb7066b815cea15a3f40a26c5bed3d59
+oid sha256:3a10da665c924d0a78f574c75f6e0dbcce312de7ca6adb021d1a4f147f32e318
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b07a1641f2eb1fc754b2daa11b1bd54bb7066b815cea15a3f40a26c5bed3d59
+oid sha256:3a10da665c924d0a78f574c75f6e0dbcce312de7ca6adb021d1a4f147f32e318
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b07a1641f2eb1fc754b2daa11b1bd54bb7066b815cea15a3f40a26c5bed3d59
+oid sha256:3a10da665c924d0a78f574c75f6e0dbcce312de7ca6adb021d1a4f147f32e318
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b07a1641f2eb1fc754b2daa11b1bd54bb7066b815cea15a3f40a26c5bed3d59
+oid sha256:3a10da665c924d0a78f574c75f6e0dbcce312de7ca6adb021d1a4f147f32e318
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b07a1641f2eb1fc754b2daa11b1bd54bb7066b815cea15a3f40a26c5bed3d59
+oid sha256:3a10da665c924d0a78f574c75f6e0dbcce312de7ca6adb021d1a4f147f32e318
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b07a1641f2eb1fc754b2daa11b1bd54bb7066b815cea15a3f40a26c5bed3d59
+oid sha256:3a10da665c924d0a78f574c75f6e0dbcce312de7ca6adb021d1a4f147f32e318
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b07a1641f2eb1fc754b2daa11b1bd54bb7066b815cea15a3f40a26c5bed3d59
+oid sha256:3a10da665c924d0a78f574c75f6e0dbcce312de7ca6adb021d1a4f147f32e318
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b07a1641f2eb1fc754b2daa11b1bd54bb7066b815cea15a3f40a26c5bed3d59
+oid sha256:3a10da665c924d0a78f574c75f6e0dbcce312de7ca6adb021d1a4f147f32e318
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351338e637aa543d98ac6400f2e05e86270a6a5900e20a3e790dbfa3cb26dbef
+oid sha256:9af3eb0d3db8162f6de4427ee5f19b1787f4bdb865e0ebda13f4fed6034a8890
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.349620244694021,
-  "global_step": 960000,
+  "epoch": 10.461148968916945,
+  "global_step": 970000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -19206,11 +19206,211 @@
       "eval_samples_per_second": 837.549,
       "eval_steps_per_second": 13.127,
       "step": 960000
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 1.0596344426086501e-05,
+      "loss": 0.1798,
+      "step": 960500
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 1.0581363452005424e-05,
+      "loss": 0.1805,
+      "step": 961000
+    },
+    {
+      "epoch": 10.36,
+      "eval_loss": 0.17073865234851837,
+      "eval_runtime": 2.5938,
+      "eval_samples_per_second": 885.585,
+      "eval_steps_per_second": 13.879,
+      "step": 961000
+    },
+    {
+      "epoch": 10.37,
+      "learning_rate": 1.0566572265825932e-05,
+      "loss": 0.18,
+      "step": 961500
+    },
+    {
+      "epoch": 10.37,
+      "learning_rate": 1.0551970907986557e-05,
+      "loss": 0.1801,
+      "step": 962000
+    },
+    {
+      "epoch": 10.37,
+      "eval_loss": 0.17134888470172882,
+      "eval_runtime": 2.5813,
+      "eval_samples_per_second": 889.852,
+      "eval_steps_per_second": 13.946,
+      "step": 962000
+    },
+    {
+      "epoch": 10.38,
+      "learning_rate": 1.0537559418406849e-05,
+      "loss": 0.18,
+      "step": 962500
+    },
+    {
+      "epoch": 10.38,
+      "learning_rate": 1.0523337836487271e-05,
+      "loss": 0.1799,
+      "step": 963000
+    },
+    {
+      "epoch": 10.38,
+      "eval_loss": 0.17050015926361084,
+      "eval_runtime": 2.6391,
+      "eval_samples_per_second": 870.378,
+      "eval_steps_per_second": 13.641,
+      "step": 963000
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 1.0509306201109092e-05,
+      "loss": 0.1801,
+      "step": 963500
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 1.0495464550634267e-05,
+      "loss": 0.18,
+      "step": 964000
+    },
+    {
+      "epoch": 10.39,
+      "eval_loss": 0.17047521471977234,
+      "eval_runtime": 2.6548,
+      "eval_samples_per_second": 865.215,
+      "eval_steps_per_second": 13.56,
+      "step": 964000
+    },
+    {
+      "epoch": 10.4,
+      "learning_rate": 1.0481812922905339e-05,
+      "loss": 0.1805,
+      "step": 964500
+    },
+    {
+      "epoch": 10.41,
+      "learning_rate": 1.046835135524533e-05,
+      "loss": 0.1798,
+      "step": 965000
+    },
+    {
+      "epoch": 10.41,
+      "eval_loss": 0.17172271013259888,
+      "eval_runtime": 2.5812,
+      "eval_samples_per_second": 889.895,
+      "eval_steps_per_second": 13.947,
+      "step": 965000
+    },
+    {
+      "epoch": 10.41,
+      "learning_rate": 1.0455079884457653e-05,
+      "loss": 0.1801,
+      "step": 965500
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 1.044199854682601e-05,
+      "loss": 0.1797,
+      "step": 966000
+    },
+    {
+      "epoch": 10.42,
+      "eval_loss": 0.16956347227096558,
+      "eval_runtime": 2.6699,
+      "eval_samples_per_second": 860.34,
+      "eval_steps_per_second": 13.484,
+      "step": 966000
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 1.0429107378114277e-05,
+      "loss": 0.1802,
+      "step": 966500
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 1.0416406413566414e-05,
+      "loss": 0.1802,
+      "step": 967000
+    },
+    {
+      "epoch": 10.43,
+      "eval_loss": 0.17151953279972076,
+      "eval_runtime": 2.5629,
+      "eval_samples_per_second": 896.252,
+      "eval_steps_per_second": 14.047,
+      "step": 967000
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 1.0403895687906366e-05,
+      "loss": 0.1803,
+      "step": 967500
+    },
+    {
+      "epoch": 10.44,
+      "learning_rate": 1.0391575235337991e-05,
+      "loss": 0.1798,
+      "step": 968000
+    },
+    {
+      "epoch": 10.44,
+      "eval_loss": 0.17273712158203125,
+      "eval_runtime": 2.6967,
+      "eval_samples_per_second": 851.792,
+      "eval_steps_per_second": 13.35,
+      "step": 968000
+    },
+    {
+      "epoch": 10.44,
+      "learning_rate": 1.0379445089544929e-05,
+      "loss": 0.1799,
+      "step": 968500
+    },
+    {
+      "epoch": 10.45,
+      "learning_rate": 1.0367505283690547e-05,
+      "loss": 0.1797,
+      "step": 969000
+    },
+    {
+      "epoch": 10.45,
+      "eval_loss": 0.17085492610931396,
+      "eval_runtime": 2.6519,
+      "eval_samples_per_second": 866.18,
+      "eval_steps_per_second": 13.575,
+      "step": 969000
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 1.0355755850417803e-05,
+      "loss": 0.1797,
+      "step": 969500
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 1.0344196821849202e-05,
+      "loss": 0.1799,
+      "step": 970000
+    },
+    {
+      "epoch": 10.46,
+      "eval_loss": 0.1711302548646927,
+      "eval_runtime": 2.5979,
+      "eval_samples_per_second": 884.178,
+      "eval_steps_per_second": 13.857,
+      "step": 970000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 6.72957029443817e+22,
+  "total_flos": 6.799670555468517e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5376abe825ff6d04d360831bbfd37e2e2d959d6e490763218e7e38b5c10ca1
+oid sha256:ebc5b0eb8c3bb3dd69db934b29e5beccddfae1a796cf948830a8b05766d44497
 size 449471589