Training in progress, step 820000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:937c7c0f70a279ee503aacdb71e2ed944ca0935d892236cbc194ebb0a487078d
+oid sha256:ece7b379c7a5a58ecf06bad11ca4cf9bd52de11683f133c698a0cd46d58e7f3f
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b11d3700c444e5be7a81b810567d1ec12594038b95620633a1bd2bdea5720a82
+oid sha256:83c02b97525bdc0170d693b11906b5064b3417228255adea84f3fccd20f429d1
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae78156aa426e9b178cf6fee9de070cdf8f42ae880d982b2d7744b9aef0151e2
-size 14439
+oid sha256:471be9073ca16931b802d54b255e23b3102b1be6c0e243832ecda5d9de213243
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21facfb39767781c851d9e48c4797705b198dc5e6b8cbf69054469662fef7a97
-size 14503
+oid sha256:c26d9707c692819517328265ab4fd028c1ec91f8e531a3899c963382192856e1
+size 14567

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e6cb051a738441d99712588916bc3687b4f28c951201e05ef9935c6498e2add
-size 14503
+oid sha256:2f7ef808d3e0c55b070bb63a51ac31108dc6594c932f2329575c64f0ec5d34a6
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9386b24abfba6bc92416379b1f9ea9f1d4b9d09be1e413347b26a358344ede31
+oid sha256:3915824192442b74d4af5e3ad4160d4a09adeeec3fcac9fa02d181a6969e8279
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ff99717fc66d7e2670093ac4b787c0d4e68c8bb6b50d5d8a0a59479daaf2a3
+oid sha256:c63a65d51252613e1cd5f3ab255f2a8e56d55631776ee22be37789c5802ebbf2
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.368867103394567,
-  "global_step": 810000,
+  "epoch": 12.521569166399438,
+  "global_step": 820000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6000,11 +6000,85 @@
       "eval_samples_per_second": 1341.078,
       "eval_steps_per_second": 21.457,
       "step": 810000
+    },
+    {
+      "epoch": 12.38,
+      "learning_rate": 2.32330563722056e-05,
+      "loss": 0.2357,
+      "step": 811000
+    },
+    {
+      "epoch": 12.4,
+      "learning_rate": 2.309792314485815e-05,
+      "loss": 0.2356,
+      "step": 812000
+    },
+    {
+      "epoch": 12.41,
+      "learning_rate": 2.2963412189506695e-05,
+      "loss": 0.2358,
+      "step": 813000
+    },
+    {
+      "epoch": 12.43,
+      "learning_rate": 2.282952497714145e-05,
+      "loss": 0.2356,
+      "step": 814000
+    },
+    {
+      "epoch": 12.45,
+      "learning_rate": 2.2696262971931538e-05,
+      "loss": 0.2357,
+      "step": 815000
+    },
+    {
+      "epoch": 12.45,
+      "eval_runtime": 0.7163,
+      "eval_samples_per_second": 1396.105,
+      "eval_steps_per_second": 22.338,
+      "step": 815000
+    },
+    {
+      "epoch": 12.46,
+      "learning_rate": 2.2563627631208887e-05,
+      "loss": 0.2355,
+      "step": 816000
+    },
+    {
+      "epoch": 12.48,
+      "learning_rate": 2.2431620405452336e-05,
+      "loss": 0.2351,
+      "step": 817000
+    },
+    {
+      "epoch": 12.49,
+      "learning_rate": 2.230024273827179e-05,
+      "loss": 0.2357,
+      "step": 818000
+    },
+    {
+      "epoch": 12.51,
+      "learning_rate": 2.216949606639231e-05,
+      "loss": 0.2353,
+      "step": 819000
+    },
+    {
+      "epoch": 12.52,
+      "learning_rate": 2.2039381819638596e-05,
+      "loss": 0.2351,
+      "step": 820000
+    },
+    {
+      "epoch": 12.52,
+      "eval_runtime": 0.6211,
+      "eval_samples_per_second": 1609.99,
+      "eval_steps_per_second": 25.76,
+      "step": 820000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.678113258640334e+22,
+  "total_flos": 5.748213519670681e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b11d3700c444e5be7a81b810567d1ec12594038b95620633a1bd2bdea5720a82
+oid sha256:83c02b97525bdc0170d693b11906b5064b3417228255adea84f3fccd20f429d1
 size 449471589