Training in progress, step 910000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e68aaa7f20cf2655b5ee95587161e9676e99cc34136556add0f9965734e7755
+oid sha256:833419c3e72d7f9d08d84324dff99c4df5021ccb89fb201b7ceab844fd1fe7de
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e51d656bcb12cf1d2e57afead6fbd882c17c7bfca89d40bc32ba44fc16d622
+oid sha256:178bde3b89657b90235cfe9d9ea492b4c3952edf2d20ecb0ed27ebbb80775260
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55ad6fff41d308df46b9a1b2f331c0f91fef2419029183c0886a7d45a3462024
+oid sha256:44cbeb264fb2a81130e0bac112a18c08ec1d410c1c39e23c023c635c67938a81
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40d19463da3fc8105dffb32921ceec5ee75e4844d0eca7759a43c7f4b14bbba
+oid sha256:3dbfbe0d14b5c95909c74387495649181894d175bc5bdbfa086f89dc9ba7b8e5
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd73f45d2e32308ab057499cc1554bb0a6b5dce90d1016017772831b0342b94
+oid sha256:61414351d7a2b424bf69a03902f1cdb6a014111a0704f27525f615bba9831275
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90198646614d410142ba8b69e323e9efb6043fdb55e8f55a8936dc33416f4c8d
+oid sha256:c8736baa79faca75f1de8fbb0415f2f8cedffbb08cddfa2e1e02291f66849ffd
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d370228b86aa2250b5e7dcf8be134cb35dc855b6e23853f0ea74181606aa91c
+oid sha256:43bc53bd3230780ced8543e570f3a1576c876dc5bb9da2beb20be127155a27a1
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:052919acbfa40e0f835c2850fde0f02534bb1eb7e31ee0f5a540aca7e0f25da3
+oid sha256:425858a9ea3774cea4e80f4044a1828fb43f83f6100a0fd4aa4ea1985d9d8afe
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c995fa02cdc8d504061c7c2c431119a7ac4cd2ff34fa2e7bd0545514b474d1
+oid sha256:4e99df6b45e45b719db86866dd43b0e8f476f0d4749f66d2f42f7183415384c8
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f95e8365bd03b8115e7ed1873af4534b3ec6096af843d6743d8130c920c2cc
+oid sha256:5ffd4b3aa19562ff729663fcb259b8c71f90c0398d12b236c6885ec68255bc91
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c027d2ad1a7ec1ccedf4c28ec4cf8e5a70643d6805bfcfeb4cb2085d818a7bdc
+oid sha256:aa4db73f02c4f7c376b4a473b74af0d764f1f4d822f644308482e4f6b4c6cad2
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.338804697028882,
-  "global_step": 900000,
+  "epoch": 1.3587343850894045,
+  "global_step": 910000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10806,11 +10806,131 @@
       "learning_rate": 1.3792793080955574e-05,
       "loss": 0.2852,
       "step": 900000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3755301948017599e-05,
+      "loss": 0.2853,
+      "step": 900500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3717991925554562e-05,
+      "loss": 0.285,
+      "step": 901000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.368086311557062e-05,
+      "loss": 0.2854,
+      "step": 901500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3643915619574529e-05,
+      "loss": 0.2849,
+      "step": 902000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3607149538579341e-05,
+      "loss": 0.2853,
+      "step": 902500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.35705649731021e-05,
+      "loss": 0.2849,
+      "step": 903000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3534162023163642e-05,
+      "loss": 0.2853,
+      "step": 903500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3497940788288195e-05,
+      "loss": 0.2853,
+      "step": 904000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3461901367503262e-05,
+      "loss": 0.2858,
+      "step": 904500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3426043859339253e-05,
+      "loss": 0.2854,
+      "step": 905000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3390368361829197e-05,
+      "loss": 0.2853,
+      "step": 905500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3354874972508582e-05,
+      "loss": 0.2851,
+      "step": 906000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3319563788414934e-05,
+      "loss": 0.2847,
+      "step": 906500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3284434906087695e-05,
+      "loss": 0.2846,
+      "step": 907000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3249488421567911e-05,
+      "loss": 0.2851,
+      "step": 907500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3214724430397915e-05,
+      "loss": 0.285,
+      "step": 908000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.3180143027621145e-05,
+      "loss": 0.2852,
+      "step": 908500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.314574430778182e-05,
+      "loss": 0.2844,
+      "step": 909000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.311152836492473e-05,
+      "loss": 0.2848,
+      "step": 909500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.3077495292594966e-05,
+      "loss": 0.285,
+      "step": 910000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 6.0846394803756095e+22,
+  "total_flos": 6.152247724689881e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e51d656bcb12cf1d2e57afead6fbd882c17c7bfca89d40bc32ba44fc16d622
+oid sha256:178bde3b89657b90235cfe9d9ea492b4c3952edf2d20ecb0ed27ebbb80775260
 size 449450757