Training in progress, step 240000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c73f6ebf98667b9d415618c592fcc151813c952d53aa83593aeea350ae20ad82
+oid sha256:e7a9d643fd165284c9d847051c171fdeb050ea172840f575f2857a0e22839d20
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f49e8c0a7fe5574e03000ae8a462d71703d3111453eca27095f6af063a3ac4e
+oid sha256:8cd72965584365f2678a23f0540f0298ff143ae7b5281c747f80901158bab7a9
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e201bd9c4e3306c102fdf93d9794a7db518406ab08c5c5b2a75cbf98841961b7
+oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e201bd9c4e3306c102fdf93d9794a7db518406ab08c5c5b2a75cbf98841961b7
+oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e201bd9c4e3306c102fdf93d9794a7db518406ab08c5c5b2a75cbf98841961b7
+oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e201bd9c4e3306c102fdf93d9794a7db518406ab08c5c5b2a75cbf98841961b7
+oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e201bd9c4e3306c102fdf93d9794a7db518406ab08c5c5b2a75cbf98841961b7
+oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e201bd9c4e3306c102fdf93d9794a7db518406ab08c5c5b2a75cbf98841961b7
+oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e201bd9c4e3306c102fdf93d9794a7db518406ab08c5c5b2a75cbf98841961b7
+oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e201bd9c4e3306c102fdf93d9794a7db518406ab08c5c5b2a75cbf98841961b7
+oid sha256:26877376a586a7e44423b2d492056222f613d04d2bdd81ac8675c24665dfa5be
 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": 14.093137254901961,
-  "global_step": 230000,
+  "epoch": 14.705882352941176,
+  "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": 737.479,
       "eval_steps_per_second": 11.8,
       "step": 230000
+    },
+    {
+      "epoch": 14.12,
+      "learning_rate": 1.975943079434381e-05,
+      "loss": 0.4406,
+      "step": 230500
+    },
+    {
+      "epoch": 14.15,
+      "learning_rate": 1.9267967467053834e-05,
+      "loss": 0.4408,
+      "step": 231000
+    },
+    {
+      "epoch": 14.15,
+      "eval_loss": 0.799385130405426,
+      "eval_runtime": 1.2054,
+      "eval_samples_per_second": 829.62,
+      "eval_steps_per_second": 13.274,
+      "step": 231000
+    },
+    {
+      "epoch": 14.19,
+      "learning_rate": 1.878900298451024e-05,
+      "loss": 0.4406,
+      "step": 231500
+    },
+    {
+      "epoch": 14.22,
+      "learning_rate": 1.83225582981712e-05,
+      "loss": 0.4406,
+      "step": 232000
+    },
+    {
+      "epoch": 14.22,
+      "eval_loss": 0.800686776638031,
+      "eval_runtime": 1.3097,
+      "eval_samples_per_second": 763.545,
+      "eval_steps_per_second": 12.217,
+      "step": 232000
+    },
+    {
+      "epoch": 14.25,
+      "learning_rate": 1.7868653811838307e-05,
+      "loss": 0.4406,
+      "step": 232500
+    },
+    {
+      "epoch": 14.28,
+      "learning_rate": 1.7427309380764227e-05,
+      "loss": 0.4404,
+      "step": 233000
+    },
+    {
+      "epoch": 14.28,
+      "eval_loss": 0.8005698323249817,
+      "eval_runtime": 1.2953,
+      "eval_samples_per_second": 772.049,
+      "eval_steps_per_second": 12.353,
+      "step": 233000
+    },
+    {
+      "epoch": 14.31,
+      "learning_rate": 1.6998544310784175e-05,
+      "loss": 0.4406,
+      "step": 233500
+    },
+    {
+      "epoch": 14.34,
+      "learning_rate": 1.6582377357471285e-05,
+      "loss": 0.4403,
+      "step": 234000
+    },
+    {
+      "epoch": 14.34,
+      "eval_loss": 0.7986977696418762,
+      "eval_runtime": 1.3526,
+      "eval_samples_per_second": 739.295,
+      "eval_steps_per_second": 11.829,
+      "step": 234000
+    },
+    {
+      "epoch": 14.37,
+      "learning_rate": 1.617882672531633e-05,
+      "loss": 0.4405,
+      "step": 234500
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 1.578791006693124e-05,
+      "loss": 0.4405,
+      "step": 235000
+    },
+    {
+      "epoch": 14.4,
+      "eval_loss": 0.8009754419326782,
+      "eval_runtime": 1.2995,
+      "eval_samples_per_second": 769.543,
+      "eval_steps_per_second": 12.313,
+      "step": 235000
+    },
+    {
+      "epoch": 14.43,
+      "learning_rate": 1.5409644482277073e-05,
+      "loss": 0.4403,
+      "step": 235500
+    },
+    {
+      "epoch": 14.46,
+      "learning_rate": 1.504404651791591e-05,
+      "loss": 0.4404,
+      "step": 236000
+    },
+    {
+      "epoch": 14.46,
+      "eval_loss": 0.798170268535614,
+      "eval_runtime": 1.2848,
+      "eval_samples_per_second": 778.322,
+      "eval_steps_per_second": 12.453,
+      "step": 236000
+    },
+    {
+      "epoch": 14.49,
+      "learning_rate": 1.4691132166287069e-05,
+      "loss": 0.4403,
+      "step": 236500
+    },
+    {
+      "epoch": 14.52,
+      "learning_rate": 1.4350916865007609e-05,
+      "loss": 0.4404,
+      "step": 237000
+    },
+    {
+      "epoch": 14.52,
+      "eval_loss": 0.7984534502029419,
+      "eval_runtime": 1.2843,
+      "eval_samples_per_second": 778.661,
+      "eval_steps_per_second": 12.459,
+      "step": 237000
+    },
+    {
+      "epoch": 14.55,
+      "learning_rate": 1.4023415496196915e-05,
+      "loss": 0.4402,
+      "step": 237500
+    },
+    {
+      "epoch": 14.58,
+      "learning_rate": 1.3708642385825806e-05,
+      "loss": 0.4403,
+      "step": 238000
+    },
+    {
+      "epoch": 14.58,
+      "eval_loss": 0.8015879392623901,
+      "eval_runtime": 1.3525,
+      "eval_samples_per_second": 739.353,
+      "eval_steps_per_second": 11.83,
+      "step": 238000
+    },
+    {
+      "epoch": 14.61,
+      "learning_rate": 1.3406611303089918e-05,
+      "loss": 0.4404,
+      "step": 238500
+    },
+    {
+      "epoch": 14.64,
+      "learning_rate": 1.311733545980718e-05,
+      "loss": 0.4402,
+      "step": 239000
+    },
+    {
+      "epoch": 14.64,
+      "eval_loss": 0.8024547696113586,
+      "eval_runtime": 1.3287,
+      "eval_samples_per_second": 752.597,
+      "eval_steps_per_second": 12.042,
+      "step": 239000
+    },
+    {
+      "epoch": 14.68,
+      "learning_rate": 1.284082750984018e-05,
+      "loss": 0.4401,
+      "step": 239500
+    },
+    {
+      "epoch": 14.71,
+      "learning_rate": 1.2577099548542319e-05,
+      "loss": 0.4402,
+      "step": 240000
+    },
+    {
+      "epoch": 14.71,
+      "eval_loss": 0.8019887804985046,
+      "eval_runtime": 1.3351,
+      "eval_samples_per_second": 748.984,
+      "eval_steps_per_second": 11.984,
+      "step": 240000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 16,
-  "total_flos": 3.6837239188628827e+21,
+  "total_flos": 3.843891921728687e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f49e8c0a7fe5574e03000ae8a462d71703d3111453eca27095f6af063a3ac4e
+oid sha256:8cd72965584365f2678a23f0540f0298ff143ae7b5281c747f80901158bab7a9
 size 25761253