Training in progress, step 640000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017625820feef9696ace4a5cbefe218b931336a9991e2245257a1d1342a0f729
+oid sha256:570fd9971dd127676195908f1f0168c560d379e06053db1ec1c6889a24e76909
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d36d94ab11c86f651fecbc7a217529f6f250ac924b506ffb7d29aa9de0ca5bc
+oid sha256:407afab53633fc482bbe780f5224c6b1388fc7b7dd3f17aa73388222d02bc81c
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31d0ded159b5f3b1a8c1ce1b7b826e4fbdda0cc5ba59eaba62ee8809a462e8f
+oid sha256:069c7b8d28935c1bdaf707018f31232b5c5d0b17ca264ac835e0cab62f47f60b
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398f2318b4ded20f61f24fd00e4055ea625eaa86f27bce6d1e31ca0965b80a81
+oid sha256:acfb6c5ca1e2a8aae6849b592c5e4c4b839246ca00f42f46fa8da24fee6f7051
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb6422a1fad93ed77bc18b18a2c8499aa6774c77ffada9e53f436cd9d13ca0c
+oid sha256:ed15d29f5bdaa33109b0c66a9aa2dbc57339a469e3f71f40bec5ec342e0d6d49
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce446a79d89ee06223f9e2ae5f2f4290f0fb0ec1cfcfeee86b4b4ba2420ef30e
+oid sha256:962d2f5974f30660f555e22cdf0c12b334de1b8fc49a6a5192e63c3a6ee6eebe
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fbfbffabb738f483b0924b2fcbbbf4a31bdaab1f9760b5a622efffc7c59e8d2
+oid sha256:fa2e736f0ce5f395a825ebebcf342c762745706534807a9b43b2a6a713704726
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a6b1230026b3f360d114a9d0f5608343d3dbe5979744e0c2b45d14032617ff1
+oid sha256:0bff10bd0517565104b7a365f7830fc50ca6a2c535ddf94460fc2737ad38c9a7
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92afb5535b80215526b380f6cb7f75fa76f1d0853152e112df8d84246f00fed
+oid sha256:24fffbd4923bc1f675f8117f531217edf35f82264eb436b97401dab9e4eeeaa0
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5fe487d9251494c826a0bd20a1c2515c3d527bc1906f192546685af4384e7fe
+oid sha256:d716524e67d0b69cb1b5ffc99aa56ed5a73b186c4b6bfbd6ff0ef38267147113
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5538e16e2cb8a022511fa1c4ff3a30d17572708626a194d4d5db3edb9bc5de72
+oid sha256:03a35091ba68234fa026466686321e8ce53cfe05ba57973184932ffc7464e369
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2594005253499334,
-  "global_step": 630000,
+  "epoch": 1.2793910098792973,
+  "global_step": 640000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7566,11 +7566,131 @@
       "learning_rate": 5.617947778908498e-05,
       "loss": 0.3015,
       "step": 630000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.60706751197385e-05,
+      "loss": 0.3014,
+      "step": 630500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.596193787225254e-05,
+      "loss": 0.3008,
+      "step": 631000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.585326634391049e-05,
+      "loss": 0.3008,
+      "step": 631500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.574466083181624e-05,
+      "loss": 0.3014,
+      "step": 632000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.563612163289308e-05,
+      "loss": 0.3008,
+      "step": 632500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.552764904388305e-05,
+      "loss": 0.3016,
+      "step": 633000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.541924336134609e-05,
+      "loss": 0.3014,
+      "step": 633500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.5310904881659116e-05,
+      "loss": 0.301,
+      "step": 634000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.5202633901015464e-05,
+      "loss": 0.3008,
+      "step": 634500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.5094430715423835e-05,
+      "loss": 0.3017,
+      "step": 635000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.4986295620707626e-05,
+      "loss": 0.3005,
+      "step": 635500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.487822891250406e-05,
+      "loss": 0.3004,
+      "step": 636000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.477023088626334e-05,
+      "loss": 0.3008,
+      "step": 636500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.4662301837247985e-05,
+      "loss": 0.301,
+      "step": 637000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.45544420605319e-05,
+      "loss": 0.3008,
+      "step": 637500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.4446651850999604e-05,
+      "loss": 0.3012,
+      "step": 638000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.433893150334538e-05,
+      "loss": 0.3009,
+      "step": 638500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.4231281312072544e-05,
+      "loss": 0.301,
+      "step": 639000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.4123701571492636e-05,
+      "loss": 0.3009,
+      "step": 639500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.401619257572453e-05,
+      "loss": 0.3007,
+      "step": 640000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.2592477348671294e+22,
+  "total_flos": 4.326855661422541e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d36d94ab11c86f651fecbc7a217529f6f250ac924b506ffb7d29aa9de0ca5bc
+oid sha256:407afab53633fc482bbe780f5224c6b1388fc7b7dd3f17aa73388222d02bc81c
 size 449450757