Training in progress, step 630000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a097619eaa9ef720984e4ddd9dde8f3b697ba4e3a54ad0e09caff9a338f70f3
+oid sha256:017625820feef9696ace4a5cbefe218b931336a9991e2245257a1d1342a0f729
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6297a4aa090b90aa3635b3517c4b127894ad2c42e14fd6d228c6743ce17aee7d
+oid sha256:2d36d94ab11c86f651fecbc7a217529f6f250ac924b506ffb7d29aa9de0ca5bc
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef2eb325ca73aeb9167731426720e192b4dc476427d6c01affc7b3b2a3e583b
+oid sha256:d31d0ded159b5f3b1a8c1ce1b7b826e4fbdda0cc5ba59eaba62ee8809a462e8f
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ef8f093c13597a9033ad0961b449077de3ab17c6b5e598e7ffe900737a37b62
+oid sha256:398f2318b4ded20f61f24fd00e4055ea625eaa86f27bce6d1e31ca0965b80a81
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20445f0abf4410bec575adab612ba675a2a9e22a555ffb2b2fb85961556a332
+oid sha256:cbb6422a1fad93ed77bc18b18a2c8499aa6774c77ffada9e53f436cd9d13ca0c
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20bb77018a33c479ea4b69c28339611c22b8e8641554d8590d8198df56a8bc21
+oid sha256:ce446a79d89ee06223f9e2ae5f2f4290f0fb0ec1cfcfeee86b4b4ba2420ef30e
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34450b80230704bfaa6dfc6f8672078f09277102e090e32e505412e8b0a06323
+oid sha256:5fbfbffabb738f483b0924b2fcbbbf4a31bdaab1f9760b5a622efffc7c59e8d2
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f073590871f68cf52e503ea996a2b041d76f54fc155c63b39985473c3a2c6e9
+oid sha256:6a6b1230026b3f360d114a9d0f5608343d3dbe5979744e0c2b45d14032617ff1
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb10ba8d357eb68fad272ff5bc8fb10ce9e5818ee9a6bd185f2331209c9c5eee
+oid sha256:c92afb5535b80215526b380f6cb7f75fa76f1d0853152e112df8d84246f00fed
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bdc5c8f1d9880eb7b2e1404af5eeae63b870215c24de51ca47db7d2d9d87809
+oid sha256:c5fe487d9251494c826a0bd20a1c2515c3d527bc1906f192546685af4384e7fe
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0be0a1dddd0483c31953c97f497ac534ef42fa519c13cb1ceaab964eeaafea
+oid sha256:5538e16e2cb8a022511fa1c4ff3a30d17572708626a194d4d5db3edb9bc5de72
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2394100408205695,
-  "global_step": 620000,
+  "epoch": 1.2594005253499334,
+  "global_step": 630000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7446,11 +7446,131 @@
       "learning_rate": 5.8368810393753684e-05,
       "loss": 0.3021,
       "step": 620000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5.8258761986213015e-05,
+      "loss": 0.3027,
+      "step": 620500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5.814877301838688e-05,
+      "loss": 0.3021,
+      "step": 621000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5.803884379098094e-05,
+      "loss": 0.3022,
+      "step": 621500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5.7928974604537494e-05,
+      "loss": 0.3022,
+      "step": 622000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5.781916575943469e-05,
+      "loss": 0.3022,
+      "step": 622500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.770941755588573e-05,
+      "loss": 0.3023,
+      "step": 623000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.7599730293938e-05,
+      "loss": 0.302,
+      "step": 623500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.749010427347233e-05,
+      "loss": 0.3021,
+      "step": 624000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.738053979420199e-05,
+      "loss": 0.3019,
+      "step": 624500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.7271037155672156e-05,
+      "loss": 0.3015,
+      "step": 625000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.716159665725883e-05,
+      "loss": 0.3016,
+      "step": 625500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.7052218598168154e-05,
+      "loss": 0.3017,
+      "step": 626000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.69429032774356e-05,
+      "loss": 0.3021,
+      "step": 626500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.6833650993925016e-05,
+      "loss": 0.3015,
+      "step": 627000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.6724462046328025e-05,
+      "loss": 0.3021,
+      "step": 627500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.661533673316303e-05,
+      "loss": 0.3026,
+      "step": 628000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.6506275352774447e-05,
+      "loss": 0.3009,
+      "step": 628500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.639727820333198e-05,
+      "loss": 0.3017,
+      "step": 629000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.62883455828296e-05,
+      "loss": 0.3016,
+      "step": 629500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.617947778908498e-05,
+      "loss": 0.3015,
+      "step": 630000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.191638959928546e+22,
+  "total_flos": 4.2592477348671294e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6297a4aa090b90aa3635b3517c4b127894ad2c42e14fd6d228c6743ce17aee7d
+oid sha256:2d36d94ab11c86f651fecbc7a217529f6f250ac924b506ffb7d29aa9de0ca5bc
 size 449450757