Training in progress, step 480000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d4808dde71eac80e04b5355e71b14ceb9b5e0ae529d95a233b51272607ab83
+oid sha256:125a953eae139b71c861d769dd5fcb3f2876cb3ba5332474ace67ff7903ad282
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7103687c38405c622f568188c0f14e1563ef023c455f4c1710827b01ab80bb17
+oid sha256:8cb09afc7f60da26cfbf13286b33ee5d8eaf949d0691655a730175e631e257c3
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4e056df33e676753147b05c71aab5efb8704dfd8ee13e008fdf53d8cdac44b2
+oid sha256:8310a18059ec0119b7d5189ac12986b598d8b8b1ef1bbfc8c8957369e8337ad7
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7049055dea9713813a526e48cc1a4819519bd8bf226d421b09446678fec8fd94
+oid sha256:c4a54b152e9b8fc53442ea8e45557e4a5adac5097977f729107da5bb580c1c20
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae399cb1dd5e413a3579163a8c5c2dc1f7fefe685aeb37d572263aef6a0f1ce1
+oid sha256:5c3be6e2beda8fd5ff4d10e6a6d31003cc62098e71db295fd431821efbbfb1a9
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0032134f185d3f5485217ef8125c850bc4af9658f5890ff772fcbabf723e2b09
+oid sha256:e1acdc1aa6e4187c8d0aa9e0711043619de98803eb54f6ce34ce5eccae47291d
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f611622a5002fa681af11a66fadbdf979555ccde290d546f60b9105024e7e63
+oid sha256:d89c33267da2eca03288d19643b70286b13de68f683e137d6b6c77f428e64db6
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.176996961228946,
-  "global_step": 470000,
+  "epoch": 7.329699024233817,
+  "global_step": 480000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3484,11 +3484,85 @@
       "eval_samples_per_second": 1116.774,
       "eval_steps_per_second": 17.868,
       "step": 470000
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 9.243390115142761e-05,
+      "loss": 0.2678,
+      "step": 471000
+    },
+    {
+      "epoch": 7.21,
+      "learning_rate": 9.220602892445661e-05,
+      "loss": 0.2678,
+      "step": 472000
+    },
+    {
+      "epoch": 7.22,
+      "learning_rate": 9.197802321430889e-05,
+      "loss": 0.2679,
+      "step": 473000
+    },
+    {
+      "epoch": 7.24,
+      "learning_rate": 9.174988651441833e-05,
+      "loss": 0.2673,
+      "step": 474000
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 9.152162131965137e-05,
+      "loss": 0.2675,
+      "step": 475000
+    },
+    {
+      "epoch": 7.25,
+      "eval_runtime": 1.0353,
+      "eval_samples_per_second": 965.922,
+      "eval_steps_per_second": 15.455,
+      "step": 475000
+    },
+    {
+      "epoch": 7.27,
+      "learning_rate": 9.129323012627956e-05,
+      "loss": 0.2693,
+      "step": 476000
+    },
+    {
+      "epoch": 7.28,
+      "learning_rate": 9.106471543195244e-05,
+      "loss": 0.2675,
+      "step": 477000
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 9.08360797356701e-05,
+      "loss": 0.2679,
+      "step": 478000
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 9.060732553775582e-05,
+      "loss": 0.2672,
+      "step": 479000
+    },
+    {
+      "epoch": 7.33,
+      "learning_rate": 9.037845533982892e-05,
+      "loss": 0.267,
+      "step": 480000
+    },
+    {
+      "epoch": 7.33,
+      "eval_runtime": 1.0347,
+      "eval_samples_per_second": 966.468,
+      "eval_steps_per_second": 15.463,
+      "step": 480000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.2947076689492745e+22,
+  "total_flos": 3.3648079299796217e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7103687c38405c622f568188c0f14e1563ef023c455f4c1710827b01ab80bb17
+oid sha256:8cb09afc7f60da26cfbf13286b33ee5d8eaf949d0691655a730175e631e257c3
 size 449471589