Training in progress, step 220000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66ea72ff9e74c18693c50d5eb4597b71e5592e11fe45a57df3b66e628d51f20
+oid sha256:23bbc0287788b2c03b401006764ab5c51beca76144630361bf7232a38c305bb2
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b982cc265a7352e00ddc20a71748aff08f14dba0f3f3245909d1fbdbc876456
+oid sha256:536b6de0b75a81a1046eda925f6ee0d8ba9e4b19c73ef4c848e57b42c2ce63b3
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
+oid sha256:0be7ce3b05940caed2419a487b770c6b4c383452e171183ad5c457321fb063b3
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
+oid sha256:0be7ce3b05940caed2419a487b770c6b4c383452e171183ad5c457321fb063b3
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
+oid sha256:0be7ce3b05940caed2419a487b770c6b4c383452e171183ad5c457321fb063b3
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
+oid sha256:0be7ce3b05940caed2419a487b770c6b4c383452e171183ad5c457321fb063b3
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
+oid sha256:0be7ce3b05940caed2419a487b770c6b4c383452e171183ad5c457321fb063b3
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
+oid sha256:0be7ce3b05940caed2419a487b770c6b4c383452e171183ad5c457321fb063b3
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
+oid sha256:0be7ce3b05940caed2419a487b770c6b4c383452e171183ad5c457321fb063b3
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c6e64c44cdb257923265c0f09feb1a0c36283a663048d162ffa0e458017630
+oid sha256:0be7ce3b05940caed2419a487b770c6b4c383452e171183ad5c457321fb063b3
 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": 12.867647058823529,
-  "global_step": 210000,
+  "epoch": 13.480392156862745,
+  "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": 750.181,
       "eval_steps_per_second": 12.003,
       "step": 210000
+    },
+    {
+      "epoch": 12.9,
+      "learning_rate": 4.9360069932402115e-05,
+      "loss": 0.4423,
+      "step": 210500
+    },
+    {
+      "epoch": 12.93,
+      "learning_rate": 4.839198426598824e-05,
+      "loss": 0.4421,
+      "step": 211000
+    },
+    {
+      "epoch": 12.93,
+      "eval_loss": 0.8022798895835876,
+      "eval_runtime": 1.2766,
+      "eval_samples_per_second": 783.354,
+      "eval_steps_per_second": 12.534,
+      "step": 211000
+    },
+    {
+      "epoch": 12.96,
+      "learning_rate": 4.7435123465477156e-05,
+      "loss": 0.4422,
+      "step": 211500
+    },
+    {
+      "epoch": 12.99,
+      "learning_rate": 4.6489529387060306e-05,
+      "loss": 0.4421,
+      "step": 212000
+    },
+    {
+      "epoch": 12.99,
+      "eval_loss": 0.8013637661933899,
+      "eval_runtime": 1.3245,
+      "eval_samples_per_second": 754.989,
+      "eval_steps_per_second": 12.08,
+      "step": 212000
+    },
+    {
+      "epoch": 13.02,
+      "learning_rate": 4.555524339408575e-05,
+      "loss": 0.4421,
+      "step": 212500
+    },
+    {
+      "epoch": 13.05,
+      "learning_rate": 4.46323063552496e-05,
+      "loss": 0.442,
+      "step": 213000
+    },
+    {
+      "epoch": 13.05,
+      "eval_loss": 0.7998749017715454,
+      "eval_runtime": 1.3047,
+      "eval_samples_per_second": 766.488,
+      "eval_steps_per_second": 12.264,
+      "step": 213000
+    },
+    {
+      "epoch": 13.08,
+      "learning_rate": 4.3720758642807817e-05,
+      "loss": 0.4419,
+      "step": 213500
+    },
+    {
+      "epoch": 13.11,
+      "learning_rate": 4.2820640130810446e-05,
+      "loss": 0.4418,
+      "step": 214000
+    },
+    {
+      "epoch": 13.11,
+      "eval_loss": 0.8018962144851685,
+      "eval_runtime": 1.2527,
+      "eval_samples_per_second": 798.295,
+      "eval_steps_per_second": 12.773,
+      "step": 214000
+    },
+    {
+      "epoch": 13.14,
+      "learning_rate": 4.193199019335709e-05,
+      "loss": 0.4418,
+      "step": 214500
+    },
+    {
+      "epoch": 13.17,
+      "learning_rate": 4.105484770287477e-05,
+      "loss": 0.4417,
+      "step": 215000
+    },
+    {
+      "epoch": 13.17,
+      "eval_loss": 0.7995709180831909,
+      "eval_runtime": 1.3104,
+      "eval_samples_per_second": 763.154,
+      "eval_steps_per_second": 12.21,
+      "step": 215000
+    },
+    {
+      "epoch": 13.2,
+      "learning_rate": 4.018925102841773e-05,
+      "loss": 0.4416,
+      "step": 215500
+    },
+    {
+      "epoch": 13.24,
+      "learning_rate": 3.9335238033988484e-05,
+      "loss": 0.4416,
+      "step": 216000
+    },
+    {
+      "epoch": 13.24,
+      "eval_loss": 0.8006547689437866,
+      "eval_runtime": 1.3204,
+      "eval_samples_per_second": 757.326,
+      "eval_steps_per_second": 12.117,
+      "step": 216000
+    },
+    {
+      "epoch": 13.27,
+      "learning_rate": 3.8492846076882115e-05,
+      "loss": 0.4414,
+      "step": 216500
+    },
+    {
+      "epoch": 13.3,
+      "learning_rate": 3.766211200605186e-05,
+      "loss": 0.4414,
+      "step": 217000
+    },
+    {
+      "epoch": 13.3,
+      "eval_loss": 0.8029482960700989,
+      "eval_runtime": 1.3397,
+      "eval_samples_per_second": 746.459,
+      "eval_steps_per_second": 11.943,
+      "step": 217000
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 3.684307216049706e-05,
+      "loss": 0.4415,
+      "step": 217500
+    },
+    {
+      "epoch": 13.36,
+      "learning_rate": 3.6035762367673984e-05,
+      "loss": 0.4415,
+      "step": 218000
+    },
+    {
+      "epoch": 13.36,
+      "eval_loss": 0.7989561557769775,
+      "eval_runtime": 1.2937,
+      "eval_samples_per_second": 773.007,
+      "eval_steps_per_second": 12.368,
+      "step": 218000
+    },
+    {
+      "epoch": 13.39,
+      "learning_rate": 3.52402179419282e-05,
+      "loss": 0.4414,
+      "step": 218500
+    },
+    {
+      "epoch": 13.42,
+      "learning_rate": 3.4456473682950194e-05,
+      "loss": 0.4413,
+      "step": 219000
+    },
+    {
+      "epoch": 13.42,
+      "eval_loss": 0.7997331619262695,
+      "eval_runtime": 1.2967,
+      "eval_samples_per_second": 771.217,
+      "eval_steps_per_second": 12.339,
+      "step": 219000
+    },
+    {
+      "epoch": 13.45,
+      "learning_rate": 3.3684563874252695e-05,
+      "loss": 0.4412,
+      "step": 219500
+    },
+    {
+      "epoch": 13.48,
+      "learning_rate": 3.2924522281671496e-05,
+      "loss": 0.4413,
+      "step": 220000
+    },
+    {
+      "epoch": 13.48,
+      "eval_loss": 0.7997393608093262,
+      "eval_runtime": 1.3064,
+      "eval_samples_per_second": 765.469,
+      "eval_steps_per_second": 12.247,
+      "step": 220000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 16,
-  "total_flos": 3.3634079341385047e+21,
+  "total_flos": 3.5235659265006937e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b982cc265a7352e00ddc20a71748aff08f14dba0f3f3245909d1fbdbc876456
+oid sha256:536b6de0b75a81a1046eda925f6ee0d8ba9e4b19c73ef4c848e57b42c2ce63b3
 size 25761253