Training in progress, step 360000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2412ccb8485cd06f014a9d3ba5fd1d0975b7e018d8cff9900e50d917bc1fdf5d
+oid sha256:44471d6e6546be5ac1a0d86dea95ba4d44ec44baa5148bbd72a7ea895ad69cfc
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce357ce3d6b529f718a69a4a019a30353262fc7b3a74b394a29c905d74c6bace
+oid sha256:9d3b9e249ae21e66394d1e5adda08ca3c78e35cfc386e28fe333440be7a14450
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf77bfa9438d97e6b94c6d8adb49ea05fe2793189bc403350f9c99c3df0b70f
-size 14503
+oid sha256:8cd407f01a45e91c6a9d73f9ffcc5948c50f62ac1349333301934ceecd28bde2
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4364109b281ee76bcd1190601f937d3035fb627994056b37c2278ac5b210512f
+oid sha256:10ca9bf76c7cf63afb390947106325fd549859bdbd17156e672be09fdd4b8f4d
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76fee5dcfb398dec8998f78597ffb2351be755c012a3c680797e842622a89e1a
-size 14503
+oid sha256:458dbb378f2ef2f1049b9621261d1e352171f603268c570c20cc0831e3c801af
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe21a6975cd1ab6dcf33bd2f5c91b79d5cc1adb46d481b8d3e4e4d4a9034b6a
+oid sha256:ed71a40157ab7c8a370261156f0220243926bfa7450a89c6374ca93f070e4120
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef93f126c2f64dc8d66788d8ad781c47bda9696dee0f2e314ba09dc6f0be1c9e
+oid sha256:a42c32ab3c49e09d799093ca137ee6e22777a2749e499367cd831d70ce83fb58
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.344572205170492,
-  "global_step": 350000,
+  "epoch": 5.497274268175363,
+  "global_step": 360000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2596,11 +2596,85 @@
       "eval_samples_per_second": 971.32,
       "eval_steps_per_second": 15.541,
       "step": 350000
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 0.00011809236994438816,
+      "loss": 0.2831,
+      "step": 351000
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 0.00011789795224815164,
+      "loss": 0.2827,
+      "step": 352000
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 0.00011770312010598116,
+      "loss": 0.282,
+      "step": 353000
+    },
+    {
+      "epoch": 5.41,
+      "learning_rate": 0.00011750787564852973,
+      "loss": 0.2822,
+      "step": 354000
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 0.00011731222101095955,
+      "loss": 0.2825,
+      "step": 355000
+    },
+    {
+      "epoch": 5.42,
+      "eval_runtime": 1.0697,
+      "eval_samples_per_second": 934.885,
+      "eval_steps_per_second": 14.958,
+      "step": 355000
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 0.00011711615833291833,
+      "loss": 0.2822,
+      "step": 356000
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 0.0001169196897585161,
+      "loss": 0.2824,
+      "step": 357000
+    },
+    {
+      "epoch": 5.47,
+      "learning_rate": 0.00011672281743630175,
+      "loss": 0.2818,
+      "step": 358000
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 0.0001165255435192394,
+      "loss": 0.2815,
+      "step": 359000
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 0.00011632787016468506,
+      "loss": 0.2819,
+      "step": 360000
+    },
+    {
+      "epoch": 5.5,
+      "eval_runtime": 1.1008,
+      "eval_samples_per_second": 908.433,
+      "eval_steps_per_second": 14.535,
+      "step": 360000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.4535058507214063e+22,
+  "total_flos": 2.5236061117517534e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce357ce3d6b529f718a69a4a019a30353262fc7b3a74b394a29c905d74c6bace
+oid sha256:9d3b9e249ae21e66394d1e5adda08ca3c78e35cfc386e28fe333440be7a14450
 size 449471589