Training in progress, step 980000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51baa4ddc0d5650abf5371aac2f77196b05031ccca7029b3d99ba99af85e57f
+oid sha256:a37ff0bb2125ba916e184875051de31c0a53ab6d8764d350d94b8f895cf97825
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf04012905f76240c2902acedd8866c3a784e83992a5f4e0dc380bf807380dc
+oid sha256:29e72a077e735dda0d42d87bba36bdd29e6f03ff47e8d9d7c8531209111d469e
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a45db7e85e08c084e49c40cab0c2c6092d92f81b5fa24290a645085ef74f75b
+oid sha256:22c34d3305b209ee825f5aed33939719436301cfaf9de55d7b3b5639a3350e80
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d647c17f4fed38d972bfade7f44a26e438ac9b6b775a7bbc225c5be1e112bd
+oid sha256:b6315416921462fe0ecc7a0c3f368f4b3c932064b761ab22ca7678bb4befc6c5
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9cbd943c7dcfb1555090abbcd45a86173e47d10be2fa2e7308539ca596dff0
+oid sha256:5a76def7122ba11f5e0b58c3da4b2e90151c2789ca35782d50ddc98428cb6201
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5917abb04845a366f52356ca50f06ea044267bd039a587ed19cc120ed161e748
+oid sha256:8dd7ce8763729f28d8acde8cd6b3dfea779e9b4dbaa1cc534d994758c7e6d95d
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:582d77403f5af050452c09ec279770dab4724f234e767ab55c84c502beea2905
+oid sha256:3093dd66e653e1347d48de0c3738e9baef47fa7023af660daaa6d276c2516c1c
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c6bb99cfe9f0c710fe2cc6cec0d5d888a917b4fa016be56cafcfbbd47bac76
+oid sha256:8c71863cae64230816d8f7da13edddd177d84ad915ea936c18a2d7e479676590
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f81952f7451d63a6ff6bf67269698e7e674adab210fce43113020157f4cf03d
+oid sha256:1106c2b8026b5aad28464b0bd2b8b204a664cd4c27abf0a87c50c85c6899ce87
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee4f92b2c66061ec16f42f6ff8db5a75108eff8cc62884e9d5c3c7875be42d2c
+oid sha256:4abf64edbda9080a72948f7486c0ac7635f48e74d5752a1a9ab0d947e838bf23
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf98a74aa6df8eeab9552258d949bc73dcd837ff3b88682e5ebe82858a949936
+oid sha256:5f6a86f148673573f563d78ae30ad4429d07d6c9eca28255a514457fc218ec48
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4783125134525394,
-  "global_step": 970000,
+  "epoch": 1.4982422015130619,
+  "global_step": 980000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11646,11 +11646,131 @@
       "learning_rate": 1.0344196821849202e-05,
       "loss": 0.2821,
       "step": 970000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0332828229586692e-05,
+      "loss": 0.2831,
+      "step": 970500
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.032165010471157e-05,
+      "loss": 0.2835,
+      "step": 971000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0310662477784401e-05,
+      "loss": 0.2824,
+      "step": 971500
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0299865378844936e-05,
+      "loss": 0.2828,
+      "step": 972000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.028925883741203e-05,
+      "loss": 0.2832,
+      "step": 972500
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0278842882483569e-05,
+      "loss": 0.2836,
+      "step": 973000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.026861754253637e-05,
+      "loss": 0.2837,
+      "step": 973500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.025858284552612e-05,
+      "loss": 0.2829,
+      "step": 974000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0248738818887307e-05,
+      "loss": 0.2829,
+      "step": 974500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.023908548953311e-05,
+      "loss": 0.2832,
+      "step": 975000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0229622883855378e-05,
+      "loss": 0.2837,
+      "step": 975500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.02203510277245e-05,
+      "loss": 0.2832,
+      "step": 976000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.021126994648939e-05,
+      "loss": 0.2828,
+      "step": 976500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0202379664977364e-05,
+      "loss": 0.2838,
+      "step": 977000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.019368020749412e-05,
+      "loss": 0.2828,
+      "step": 977500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.018517159782365e-05,
+      "loss": 0.2826,
+      "step": 978000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0176853859228149e-05,
+      "loss": 0.2829,
+      "step": 978500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0168727014448004e-05,
+      "loss": 0.2836,
+      "step": 979000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0160791085701714e-05,
+      "loss": 0.2834,
+      "step": 979500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0153046094685783e-05,
+      "loss": 0.2831,
+      "step": 980000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 6.557885636027719e+22,
+  "total_flos": 6.625495046923828e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf04012905f76240c2902acedd8866c3a784e83992a5f4e0dc380bf807380dc
+oid sha256:29e72a077e735dda0d42d87bba36bdd29e6f03ff47e8d9d7c8531209111d469e
 size 449450757