Training in progress, step 220000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c47fd257138231eccea9626dd76bb4ab2f6eee094f257f7969484457f4c3632
+oid sha256:3f433a536827dfe71e22cc9ae1b5c51f05bbb1bc2aaf2cf12bf5dc6dc12de9e5
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f74dd22a753cfe967920b7b8fddb7217b98b0a2e0b5df67c64a45188f75eb97d
+oid sha256:03379cedc2b74fd0a67255e5dc1c2b3e73605ea40a87df2cb44842e9ffa68b98
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab5fd582b22aec7ddbfa8fbc28c9b95ffec56fdf6ffdaedfc3579c4046380d3
+oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab5fd582b22aec7ddbfa8fbc28c9b95ffec56fdf6ffdaedfc3579c4046380d3
+oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab5fd582b22aec7ddbfa8fbc28c9b95ffec56fdf6ffdaedfc3579c4046380d3
+oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab5fd582b22aec7ddbfa8fbc28c9b95ffec56fdf6ffdaedfc3579c4046380d3
+oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab5fd582b22aec7ddbfa8fbc28c9b95ffec56fdf6ffdaedfc3579c4046380d3
+oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab5fd582b22aec7ddbfa8fbc28c9b95ffec56fdf6ffdaedfc3579c4046380d3
+oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab5fd582b22aec7ddbfa8fbc28c9b95ffec56fdf6ffdaedfc3579c4046380d3
+oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab5fd582b22aec7ddbfa8fbc28c9b95ffec56fdf6ffdaedfc3579c4046380d3
+oid sha256:314d5ecbfbb389ee2a386d01176df549ad45d90c274986b7501f19ad88f8a435
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e266918cfc5cefb1731026fc3b803b3fe8a8f730b53e3407c9a310dee0fdb3
+oid sha256:49c292ab14a993919881f01d5b74688df2db2f4ea7c017c2175d0fea64e57565
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.36830835117773,
-  "global_step": 210000,
+  "epoch": 9.814418272662383,
+  "global_step": 220000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4206,11 +4206,211 @@
       "eval_samples_per_second": 1050.236,
       "eval_steps_per_second": 16.46,
       "step": 210000
+    },
+    {
+      "epoch": 9.39,
+      "learning_rate": 4.9360069932402115e-05,
+      "loss": 0.3659,
+      "step": 210500
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 4.839198426598824e-05,
+      "loss": 0.3659,
+      "step": 211000
+    },
+    {
+      "epoch": 9.41,
+      "eval_loss": 0.3399938941001892,
+      "eval_runtime": 2.2613,
+      "eval_samples_per_second": 1015.803,
+      "eval_steps_per_second": 15.92,
+      "step": 211000
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 4.7435123465477156e-05,
+      "loss": 0.3659,
+      "step": 211500
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 4.6489529387060306e-05,
+      "loss": 0.3658,
+      "step": 212000
+    },
+    {
+      "epoch": 9.46,
+      "eval_loss": 0.34058016538619995,
+      "eval_runtime": 2.2213,
+      "eval_samples_per_second": 1034.088,
+      "eval_steps_per_second": 16.207,
+      "step": 212000
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 4.555524339408575e-05,
+      "loss": 0.3658,
+      "step": 212500
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 4.46323063552496e-05,
+      "loss": 0.3658,
+      "step": 213000
+    },
+    {
+      "epoch": 9.5,
+      "eval_loss": 0.33832791447639465,
+      "eval_runtime": 2.1746,
+      "eval_samples_per_second": 1056.275,
+      "eval_steps_per_second": 16.555,
+      "step": 213000
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 4.3720758642807817e-05,
+      "loss": 0.3655,
+      "step": 213500
+    },
+    {
+      "epoch": 9.55,
+      "learning_rate": 4.2820640130810446e-05,
+      "loss": 0.3656,
+      "step": 214000
+    },
+    {
+      "epoch": 9.55,
+      "eval_loss": 0.33994585275650024,
+      "eval_runtime": 2.2047,
+      "eval_samples_per_second": 1041.878,
+      "eval_steps_per_second": 16.329,
+      "step": 214000
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 4.193199019335709e-05,
+      "loss": 0.3654,
+      "step": 214500
+    },
+    {
+      "epoch": 9.59,
+      "learning_rate": 4.105484770287477e-05,
+      "loss": 0.3655,
+      "step": 215000
+    },
+    {
+      "epoch": 9.59,
+      "eval_loss": 0.3385065793991089,
+      "eval_runtime": 2.1784,
+      "eval_samples_per_second": 1054.433,
+      "eval_steps_per_second": 16.526,
+      "step": 215000
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 4.018925102841773e-05,
+      "loss": 0.3652,
+      "step": 215500
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 3.9335238033988484e-05,
+      "loss": 0.3653,
+      "step": 216000
+    },
+    {
+      "epoch": 9.64,
+      "eval_loss": 0.3406268358230591,
+      "eval_runtime": 2.2102,
+      "eval_samples_per_second": 1039.279,
+      "eval_steps_per_second": 16.288,
+      "step": 216000
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 3.8492846076882115e-05,
+      "loss": 0.3652,
+      "step": 216500
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 3.766211200605186e-05,
+      "loss": 0.3652,
+      "step": 217000
+    },
+    {
+      "epoch": 9.68,
+      "eval_loss": 0.33878666162490845,
+      "eval_runtime": 2.1865,
+      "eval_samples_per_second": 1050.535,
+      "eval_steps_per_second": 16.465,
+      "step": 217000
+    },
+    {
+      "epoch": 9.7,
+      "learning_rate": 3.684307216049706e-05,
+      "loss": 0.3653,
+      "step": 217500
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 3.6035762367673984e-05,
+      "loss": 0.3674,
+      "step": 218000
+    },
+    {
+      "epoch": 9.73,
+      "eval_loss": 0.33809101581573486,
+      "eval_runtime": 2.1832,
+      "eval_samples_per_second": 1052.106,
+      "eval_steps_per_second": 16.489,
+      "step": 218000
+    },
+    {
+      "epoch": 9.75,
+      "learning_rate": 3.52402179419282e-05,
+      "loss": 0.3649,
+      "step": 218500
+    },
+    {
+      "epoch": 9.77,
+      "learning_rate": 3.4456473682950194e-05,
+      "loss": 0.365,
+      "step": 219000
+    },
+    {
+      "epoch": 9.77,
+      "eval_loss": 0.33866041898727417,
+      "eval_runtime": 2.2773,
+      "eval_samples_per_second": 1008.633,
+      "eval_steps_per_second": 15.808,
+      "step": 219000
+    },
+    {
+      "epoch": 9.79,
+      "learning_rate": 3.3684563874252695e-05,
+      "loss": 0.365,
+      "step": 219500
+    },
+    {
+      "epoch": 9.81,
+      "learning_rate": 3.2924522281671496e-05,
+      "loss": 0.3648,
+      "step": 220000
+    },
+    {
+      "epoch": 9.81,
+      "eval_loss": 0.33735984563827515,
+      "eval_runtime": 2.208,
+      "eval_samples_per_second": 1040.301,
+      "eval_steps_per_second": 16.304,
+      "step": 220000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 3.3634638723423236e+21,
+  "total_flos": 3.5236318752081277e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f74dd22a753cfe967920b7b8fddb7217b98b0a2e0b5df67c64a45188f75eb97d
+oid sha256:03379cedc2b74fd0a67255e5dc1c2b3e73605ea40a87df2cb44842e9ffa68b98
 size 25761253