Training in progress, step 970000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82bf941331b6147f0c38426d0407fa25ba10c0bd3b73ef74a1673cd375f5dea3
+oid sha256:e51baa4ddc0d5650abf5371aac2f77196b05031ccca7029b3d99ba99af85e57f
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e039cd872f61b73cdde9f431db14aa3e4f6ae315b0cdef8e97e75cdb6be6fa4
+oid sha256:acf04012905f76240c2902acedd8866c3a784e83992a5f4e0dc380bf807380dc
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73634de375042b3baa7b5c117beb24655dd2f7f5f57009b1eef654c82b3b44b5
+oid sha256:7a45db7e85e08c084e49c40cab0c2c6092d92f81b5fa24290a645085ef74f75b
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb4c489f0f7eeedc1b3b1654e89c9a4aafbf4af00e935321e2351196b10ff6c
+oid sha256:56d647c17f4fed38d972bfade7f44a26e438ac9b6b775a7bbc225c5be1e112bd
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060c7b3ac0997105e228b3a17b751784076ba7d3219bd9bc28aad1940ff45553
+oid sha256:0e9cbd943c7dcfb1555090abbcd45a86173e47d10be2fa2e7308539ca596dff0
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612d68332bbb7f66da9a1c4eee686f9c7adc9fb542398fcfd0c492b56e914c02
+oid sha256:5917abb04845a366f52356ca50f06ea044267bd039a587ed19cc120ed161e748
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70baf209a4631065e5f1d839e29da7241e0065c3f0cd0e2e1c6f4c4e169d312e
+oid sha256:582d77403f5af050452c09ec279770dab4724f234e767ab55c84c502beea2905
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc2e296643bbf328fc4ab16e724c938d6325131f9cb567ebc676b5d1a649c3a
+oid sha256:94c6bb99cfe9f0c710fe2cc6cec0d5d888a917b4fa016be56cafcfbbd47bac76
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc74f55e3f6e86286f729f34589914d40a1b187feaf939dd73f214761d85e9c
+oid sha256:6f81952f7451d63a6ff6bf67269698e7e674adab210fce43113020157f4cf03d
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a192d4f815ba365d126dfc7fc40698d69e696351b09b7c12fff827e40276ec96
+oid sha256:ee4f92b2c66061ec16f42f6ff8db5a75108eff8cc62884e9d5c3c7875be42d2c
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6eea93722769fd2cdfccc4deac474dd6ab3e6b96299bf9d74b4a0082fc65937
+oid sha256:bf98a74aa6df8eeab9552258d949bc73dcd837ff3b88682e5ebe82858a949936
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.458382825392017,
-  "global_step": 960000,
+  "epoch": 1.4783125134525394,
+  "global_step": 970000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11526,11 +11526,131 @@
       "learning_rate": 1.0611515147111736e-05,
       "loss": 0.2832,
       "step": 960000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0596344426086501e-05,
+      "loss": 0.2831,
+      "step": 960500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0581363452005424e-05,
+      "loss": 0.2836,
+      "step": 961000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0566572265825932e-05,
+      "loss": 0.2835,
+      "step": 961500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0551970907986557e-05,
+      "loss": 0.2835,
+      "step": 962000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0537559418406849e-05,
+      "loss": 0.2838,
+      "step": 962500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0523337836487271e-05,
+      "loss": 0.2829,
+      "step": 963000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0509306201109092e-05,
+      "loss": 0.2835,
+      "step": 963500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0495464550634267e-05,
+      "loss": 0.284,
+      "step": 964000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0481812922905339e-05,
+      "loss": 0.2837,
+      "step": 964500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.046835135524533e-05,
+      "loss": 0.2834,
+      "step": 965000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0455079884457653e-05,
+      "loss": 0.2832,
+      "step": 965500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.044199854682601e-05,
+      "loss": 0.2837,
+      "step": 966000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0429107378114277e-05,
+      "loss": 0.2834,
+      "step": 966500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0416406413566414e-05,
+      "loss": 0.2833,
+      "step": 967000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0403895687906366e-05,
+      "loss": 0.2839,
+      "step": 967500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0391575235337991e-05,
+      "loss": 0.2828,
+      "step": 968000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0379445089544929e-05,
+      "loss": 0.2837,
+      "step": 968500
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0367505283690547e-05,
+      "loss": 0.2832,
+      "step": 969000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0355755850417803e-05,
+      "loss": 0.283,
+      "step": 969500
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0344196821849202e-05,
+      "loss": 0.2821,
+      "step": 970000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 6.4902759073727495e+22,
+  "total_flos": 6.557885636027719e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e039cd872f61b73cdde9f431db14aa3e4f6ae315b0cdef8e97e75cdb6be6fa4
+oid sha256:acf04012905f76240c2902acedd8866c3a784e83992a5f4e0dc380bf807380dc
 size 449450757