Training in progress, step 240000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86561053adee90a2878214be6885b067bd76d574ba4d67a50de8ddc88d4e78d
+oid sha256:86a627dfbe7c679e04ccbc3bb681acaad2eb0bc77a28387eaadb86fe5d605e1d
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd756189a715f251243356fce3a9e9698eaa1c9541391c5ada1cd1bb927f2ca
+oid sha256:9bd16572a6844d9a3d59f0a851a360e9f83b742eab8c4d285d9f60c12e35e31c
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
+oid sha256:c7965bd29c0f55a5d3c71632e761019454c0e283d2927c1b932a921a6a76d1df
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
+oid sha256:c7965bd29c0f55a5d3c71632e761019454c0e283d2927c1b932a921a6a76d1df
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
+oid sha256:c7965bd29c0f55a5d3c71632e761019454c0e283d2927c1b932a921a6a76d1df
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
+oid sha256:c7965bd29c0f55a5d3c71632e761019454c0e283d2927c1b932a921a6a76d1df
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
+oid sha256:c7965bd29c0f55a5d3c71632e761019454c0e283d2927c1b932a921a6a76d1df
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
+oid sha256:c7965bd29c0f55a5d3c71632e761019454c0e283d2927c1b932a921a6a76d1df
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
+oid sha256:c7965bd29c0f55a5d3c71632e761019454c0e283d2927c1b932a921a6a76d1df
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ae95e0a0d1a9ec67488894572c036dc35bd82e51ffb0fbd0fcc0a47e5aff06
+oid sha256:c7965bd29c0f55a5d3c71632e761019454c0e283d2927c1b932a921a6a76d1df
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde8387b01007811ac1b94d9590ed8f2f119f8e7b49d5ce42fb838c1939b856b
+oid sha256:0271bea6149ce925d63296b146082378537ccb6d117e16172c4343f0cd0f3277
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.260528194147037,
-  "global_step": 230000,
+  "epoch": 10.70663811563169,
+  "global_step": 240000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4606,11 +4606,211 @@
       "eval_samples_per_second": 1009.19,
       "eval_steps_per_second": 15.817,
       "step": 230000
+    },
+    {
+      "epoch": 10.28,
+      "learning_rate": 1.975943079434381e-05,
+      "loss": 0.3642,
+      "step": 230500
+    },
+    {
+      "epoch": 10.31,
+      "learning_rate": 1.9267967467053834e-05,
+      "loss": 0.364,
+      "step": 231000
+    },
+    {
+      "epoch": 10.31,
+      "eval_loss": 0.33804792165756226,
+      "eval_runtime": 2.1938,
+      "eval_samples_per_second": 1047.056,
+      "eval_steps_per_second": 16.41,
+      "step": 231000
+    },
+    {
+      "epoch": 10.33,
+      "learning_rate": 1.878900298451024e-05,
+      "loss": 0.3639,
+      "step": 231500
+    },
+    {
+      "epoch": 10.35,
+      "learning_rate": 1.83225582981712e-05,
+      "loss": 0.364,
+      "step": 232000
+    },
+    {
+      "epoch": 10.35,
+      "eval_loss": 0.3375454843044281,
+      "eval_runtime": 2.2078,
+      "eval_samples_per_second": 1040.381,
+      "eval_steps_per_second": 16.305,
+      "step": 232000
+    },
+    {
+      "epoch": 10.37,
+      "learning_rate": 1.7868653811838307e-05,
+      "loss": 0.3638,
+      "step": 232500
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 1.7427309380764227e-05,
+      "loss": 0.364,
+      "step": 233000
+    },
+    {
+      "epoch": 10.39,
+      "eval_loss": 0.33860087394714355,
+      "eval_runtime": 2.2,
+      "eval_samples_per_second": 1044.098,
+      "eval_steps_per_second": 16.364,
+      "step": 233000
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 1.6998544310784175e-05,
+      "loss": 0.3638,
+      "step": 233500
+    },
+    {
+      "epoch": 10.44,
+      "learning_rate": 1.6582377357471285e-05,
+      "loss": 0.3639,
+      "step": 234000
+    },
+    {
+      "epoch": 10.44,
+      "eval_loss": 0.33734622597694397,
+      "eval_runtime": 2.1793,
+      "eval_samples_per_second": 1054.021,
+      "eval_steps_per_second": 16.519,
+      "step": 234000
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 1.617882672531633e-05,
+      "loss": 0.3639,
+      "step": 234500
+    },
+    {
+      "epoch": 10.48,
+      "learning_rate": 1.578791006693124e-05,
+      "loss": 0.364,
+      "step": 235000
+    },
+    {
+      "epoch": 10.48,
+      "eval_loss": 0.3377144932746887,
+      "eval_runtime": 2.2337,
+      "eval_samples_per_second": 1028.33,
+      "eval_steps_per_second": 16.117,
+      "step": 235000
+    },
+    {
+      "epoch": 10.51,
+      "learning_rate": 1.5409644482277073e-05,
+      "loss": 0.3638,
+      "step": 235500
+    },
+    {
+      "epoch": 10.53,
+      "learning_rate": 1.504404651791591e-05,
+      "loss": 0.3636,
+      "step": 236000
+    },
+    {
+      "epoch": 10.53,
+      "eval_loss": 0.3383854627609253,
+      "eval_runtime": 2.1919,
+      "eval_samples_per_second": 1047.95,
+      "eval_steps_per_second": 16.424,
+      "step": 236000
+    },
+    {
+      "epoch": 10.55,
+      "learning_rate": 1.4691132166287069e-05,
+      "loss": 0.3638,
+      "step": 236500
+    },
+    {
+      "epoch": 10.57,
+      "learning_rate": 1.4350916865007609e-05,
+      "loss": 0.3636,
+      "step": 237000
+    },
+    {
+      "epoch": 10.57,
+      "eval_loss": 0.33673885464668274,
+      "eval_runtime": 2.1228,
+      "eval_samples_per_second": 1082.067,
+      "eval_steps_per_second": 16.959,
+      "step": 237000
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 1.4023415496196915e-05,
+      "loss": 0.3635,
+      "step": 237500
+    },
+    {
+      "epoch": 10.62,
+      "learning_rate": 1.3708642385825806e-05,
+      "loss": 0.3638,
+      "step": 238000
+    },
+    {
+      "epoch": 10.62,
+      "eval_loss": 0.3373904228210449,
+      "eval_runtime": 2.309,
+      "eval_samples_per_second": 994.807,
+      "eval_steps_per_second": 15.591,
+      "step": 238000
+    },
+    {
+      "epoch": 10.64,
+      "learning_rate": 1.3406611303089918e-05,
+      "loss": 0.3639,
+      "step": 238500
+    },
+    {
+      "epoch": 10.66,
+      "learning_rate": 1.311733545980718e-05,
+      "loss": 0.3637,
+      "step": 239000
+    },
+    {
+      "epoch": 10.66,
+      "eval_loss": 0.3368372619152069,
+      "eval_runtime": 2.2218,
+      "eval_samples_per_second": 1033.83,
+      "eval_steps_per_second": 16.203,
+      "step": 239000
+    },
+    {
+      "epoch": 10.68,
+      "learning_rate": 1.284082750984018e-05,
+      "loss": 0.3635,
+      "step": 239500
+    },
+    {
+      "epoch": 10.71,
+      "learning_rate": 1.2577099548542319e-05,
+      "loss": 0.3635,
+      "step": 240000
+    },
+    {
+      "epoch": 10.71,
+      "eval_loss": 0.33518004417419434,
+      "eval_runtime": 2.1947,
+      "eval_samples_per_second": 1046.621,
+      "eval_steps_per_second": 16.403,
+      "step": 240000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 3.683792746091758e+21,
+  "total_flos": 3.8439607489575623e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd756189a715f251243356fce3a9e9698eaa1c9541391c5ada1cd1bb927f2ca
+oid sha256:9bd16572a6844d9a3d59f0a851a360e9f83b742eab8c4d285d9f60c12e35e31c
 size 25761253