Training in progress, step 910000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d8bbdd8e9ea2eabe38aad0708eba010797097fc97de2bc108dfae7de70eae1
+oid sha256:286afc89953ac85c207ddee00ff74005ad2f262dcd53bfa64635a387b524e2f5
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083d2e25ea0ac8e88690f7365c08a3344ba965c5f4549f033918008711bc1651
+oid sha256:1b52f3b8fcfa70b1731fae94d573cc6b63207a962d882488f83af9b17655c7c7
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
+oid sha256:8ff175a5d87dd6b1bf5f6c9e51e5ee8b16642953afdff5a8deb87c35e540e812
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
+oid sha256:8ff175a5d87dd6b1bf5f6c9e51e5ee8b16642953afdff5a8deb87c35e540e812
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
+oid sha256:8ff175a5d87dd6b1bf5f6c9e51e5ee8b16642953afdff5a8deb87c35e540e812
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
+oid sha256:8ff175a5d87dd6b1bf5f6c9e51e5ee8b16642953afdff5a8deb87c35e540e812
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
+oid sha256:8ff175a5d87dd6b1bf5f6c9e51e5ee8b16642953afdff5a8deb87c35e540e812
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
+oid sha256:8ff175a5d87dd6b1bf5f6c9e51e5ee8b16642953afdff5a8deb87c35e540e812
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
+oid sha256:8ff175a5d87dd6b1bf5f6c9e51e5ee8b16642953afdff5a8deb87c35e540e812
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
+oid sha256:8ff175a5d87dd6b1bf5f6c9e51e5ee8b16642953afdff5a8deb87c35e540e812
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa624c96f92eaad028a188cf78acc34c38cdc88db165dfecd04176965e65555e
+oid sha256:68bd93c5df85b9ef6b8dfb004005413abc49b194d979c692716ee25211f1498f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.68044789935648,
-  "global_step": 900000,
+  "epoch": 9.791976623579403,
+  "global_step": 910000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18006,11 +18006,211 @@
       "eval_samples_per_second": 854.803,
       "eval_steps_per_second": 13.397,
       "step": 900000
+    },
+    {
+      "epoch": 9.69,
+      "learning_rate": 1.3755301948017599e-05,
+      "loss": 0.1822,
+      "step": 900500
+    },
+    {
+      "epoch": 9.69,
+      "learning_rate": 1.3717991925554562e-05,
+      "loss": 0.1821,
+      "step": 901000
+    },
+    {
+      "epoch": 9.69,
+      "eval_loss": 0.17332369089126587,
+      "eval_runtime": 2.5587,
+      "eval_samples_per_second": 897.731,
+      "eval_steps_per_second": 14.07,
+      "step": 901000
+    },
+    {
+      "epoch": 9.7,
+      "learning_rate": 1.368086311557062e-05,
+      "loss": 0.1821,
+      "step": 901500
+    },
+    {
+      "epoch": 9.7,
+      "learning_rate": 1.3643915619574529e-05,
+      "loss": 0.1821,
+      "step": 902000
+    },
+    {
+      "epoch": 9.7,
+      "eval_loss": 0.1713598072528839,
+      "eval_runtime": 2.7303,
+      "eval_samples_per_second": 841.295,
+      "eval_steps_per_second": 13.185,
+      "step": 902000
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 1.3607149538579341e-05,
+      "loss": 0.182,
+      "step": 902500
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 1.35705649731021e-05,
+      "loss": 0.1816,
+      "step": 903000
+    },
+    {
+      "epoch": 9.71,
+      "eval_loss": 0.17178992927074432,
+      "eval_runtime": 2.6316,
+      "eval_samples_per_second": 872.853,
+      "eval_steps_per_second": 13.68,
+      "step": 903000
+    },
+    {
+      "epoch": 9.72,
+      "learning_rate": 1.3534162023163642e-05,
+      "loss": 0.1821,
+      "step": 903500
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 1.3497940788288195e-05,
+      "loss": 0.182,
+      "step": 904000
+    },
+    {
+      "epoch": 9.73,
+      "eval_loss": 0.17401227355003357,
+      "eval_runtime": 2.6109,
+      "eval_samples_per_second": 879.785,
+      "eval_steps_per_second": 13.789,
+      "step": 904000
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 1.3461901367503262e-05,
+      "loss": 0.1816,
+      "step": 904500
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 1.3426043859339253e-05,
+      "loss": 0.1822,
+      "step": 905000
+    },
+    {
+      "epoch": 9.74,
+      "eval_loss": 0.16998076438903809,
+      "eval_runtime": 2.6306,
+      "eval_samples_per_second": 873.188,
+      "eval_steps_per_second": 13.685,
+      "step": 905000
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 1.3390368361829197e-05,
+      "loss": 0.1818,
+      "step": 905500
+    },
+    {
+      "epoch": 9.75,
+      "learning_rate": 1.3354874972508582e-05,
+      "loss": 0.1815,
+      "step": 906000
+    },
+    {
+      "epoch": 9.75,
+      "eval_loss": 0.17435437440872192,
+      "eval_runtime": 2.7558,
+      "eval_samples_per_second": 833.52,
+      "eval_steps_per_second": 13.063,
+      "step": 906000
+    },
+    {
+      "epoch": 9.75,
+      "learning_rate": 1.3319563788414934e-05,
+      "loss": 0.182,
+      "step": 906500
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 1.3284434906087695e-05,
+      "loss": 0.1823,
+      "step": 907000
+    },
+    {
+      "epoch": 9.76,
+      "eval_loss": 0.17397646605968475,
+      "eval_runtime": 2.6707,
+      "eval_samples_per_second": 860.067,
+      "eval_steps_per_second": 13.479,
+      "step": 907000
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 1.3249488421567911e-05,
+      "loss": 0.1818,
+      "step": 907500
+    },
+    {
+      "epoch": 9.77,
+      "learning_rate": 1.3214724430397915e-05,
+      "loss": 0.1817,
+      "step": 908000
+    },
+    {
+      "epoch": 9.77,
+      "eval_loss": 0.17298473417758942,
+      "eval_runtime": 2.659,
+      "eval_samples_per_second": 863.865,
+      "eval_steps_per_second": 13.539,
+      "step": 908000
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 1.3180143027621145e-05,
+      "loss": 0.1819,
+      "step": 908500
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 1.314574430778182e-05,
+      "loss": 0.1817,
+      "step": 909000
+    },
+    {
+      "epoch": 9.78,
+      "eval_loss": 0.17148981988430023,
+      "eval_runtime": 2.7078,
+      "eval_samples_per_second": 848.287,
+      "eval_steps_per_second": 13.295,
+      "step": 909000
+    },
+    {
+      "epoch": 9.79,
+      "learning_rate": 1.311152836492473e-05,
+      "loss": 0.1817,
+      "step": 909500
+    },
+    {
+      "epoch": 9.79,
+      "learning_rate": 1.3077495292594966e-05,
+      "loss": 0.1817,
+      "step": 910000
+    },
+    {
+      "epoch": 9.79,
+      "eval_loss": 0.17322474718093872,
+      "eval_runtime": 2.6678,
+      "eval_samples_per_second": 861.024,
+      "eval_steps_per_second": 13.495,
+      "step": 910000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 6.3089742047036024e+22,
+  "total_flos": 6.3790744657339496e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083d2e25ea0ac8e88690f7365c08a3344ba965c5f4549f033918008711bc1651
+oid sha256:1b52f3b8fcfa70b1731fae94d573cc6b63207a962d882488f83af9b17655c7c7
 size 449471589