Training in progress, step 810000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ec057c0ea307d9f51e3009e95cfba4d493f3e514026b596f1c721e347110a2
+oid sha256:937c7c0f70a279ee503aacdb71e2ed944ca0935d892236cbc194ebb0a487078d
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c985c5c271524f27a0a6ac2cedd7bd56467790c039bcfe7ae085c019b80866ff
+oid sha256:b11d3700c444e5be7a81b810567d1ec12594038b95620633a1bd2bdea5720a82
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0493bee6992b67d925775f2df83491a04dff10cd3cfaddd00934784185d10d2e
+oid sha256:ae78156aa426e9b178cf6fee9de070cdf8f42ae880d982b2d7744b9aef0151e2
 size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04d30c889b2c1188805f0e0743f415f3e88c779ab0ac6888677c659a1fcc6f0f
+oid sha256:21facfb39767781c851d9e48c4797705b198dc5e6b8cbf69054469662fef7a97
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5feee3a51b2120b65724867d176679fa33e4ec4b388d10b3340281bee5153e6a
+oid sha256:4e6cb051a738441d99712588916bc3687b4f28c951201e05ef9935c6498e2add
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34638a46c5b98d6fa60d632175553537f127fe65e252717a514cd2f205e50dee
+oid sha256:9386b24abfba6bc92416379b1f9ea9f1d4b9d09be1e413347b26a358344ede31
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57cc3662a36c24e948440a9c5383a944373362c15a98a0fb5317ec1e024dd4c4
+oid sha256:80ff99717fc66d7e2670093ac4b787c0d4e68c8bb6b50d5d8a0a59479daaf2a3
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.216165040389695,
-  "global_step": 800000,
+  "epoch": 12.368867103394567,
+  "global_step": 810000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5926,11 +5926,85 @@
       "eval_samples_per_second": 1349.61,
       "eval_steps_per_second": 21.594,
       "step": 800000
+    },
+    {
+      "epoch": 12.23,
+      "learning_rate": 2.461828514290513e-05,
+      "loss": 0.2364,
+      "step": 801000
+    },
+    {
+      "epoch": 12.25,
+      "learning_rate": 2.447701158911855e-05,
+      "loss": 0.2373,
+      "step": 802000
+    },
+    {
+      "epoch": 12.26,
+      "learning_rate": 2.4336345225837658e-05,
+      "loss": 0.2369,
+      "step": 803000
+    },
+    {
+      "epoch": 12.28,
+      "learning_rate": 2.4196287591367296e-05,
+      "loss": 0.2363,
+      "step": 804000
+    },
+    {
+      "epoch": 12.29,
+      "learning_rate": 2.405684021735527e-05,
+      "loss": 0.2366,
+      "step": 805000
+    },
+    {
+      "epoch": 12.29,
+      "eval_runtime": 0.7797,
+      "eval_samples_per_second": 1282.575,
+      "eval_steps_per_second": 20.521,
+      "step": 805000
+    },
+    {
+      "epoch": 12.31,
+      "learning_rate": 2.3918004628775736e-05,
+      "loss": 0.2366,
+      "step": 806000
+    },
+    {
+      "epoch": 12.32,
+      "learning_rate": 2.3779782343912463e-05,
+      "loss": 0.2367,
+      "step": 807000
+    },
+    {
+      "epoch": 12.34,
+      "learning_rate": 2.364217487434221e-05,
+      "loss": 0.24,
+      "step": 808000
+    },
+    {
+      "epoch": 12.35,
+      "learning_rate": 2.3505183724918196e-05,
+      "loss": 0.2369,
+      "step": 809000
+    },
+    {
+      "epoch": 12.37,
+      "learning_rate": 2.3368810393753687e-05,
+      "loss": 0.2365,
+      "step": 810000
+    },
+    {
+      "epoch": 12.37,
+      "eval_runtime": 0.7457,
+      "eval_samples_per_second": 1341.078,
+      "eval_steps_per_second": 21.457,
+      "step": 810000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.6080129976099865e+22,
+  "total_flos": 5.678113258640334e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c985c5c271524f27a0a6ac2cedd7bd56467790c039bcfe7ae085c019b80866ff
+oid sha256:b11d3700c444e5be7a81b810567d1ec12594038b95620633a1bd2bdea5720a82
 size 449471589