Training in progress, step 700000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3fbfbe90a24be671bf2fe989761e74ecd6efece427e7812964b3ea50441bc3
+oid sha256:3068e724fb5567940436e60f2384553848a9aad0263885e75f1daf1b84b38c20
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d570c8856202350b2a044aa17fe3b227f8d0ac68a7d32a12320d12e3538421d
+oid sha256:9c2cac3521920b845caebb9dc53bd10da39c532c13bda1aeb32ffbf947e78288
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd4731e74801bdba48cc8abfa936799db979f926135de7e27f7d2671d1bac66
+oid sha256:6caee68a0e054a100fac034bb9c32751e80c0254f6ec933d4ad128cba944f1dd
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd4731e74801bdba48cc8abfa936799db979f926135de7e27f7d2671d1bac66
+oid sha256:6caee68a0e054a100fac034bb9c32751e80c0254f6ec933d4ad128cba944f1dd
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd4731e74801bdba48cc8abfa936799db979f926135de7e27f7d2671d1bac66
+oid sha256:6caee68a0e054a100fac034bb9c32751e80c0254f6ec933d4ad128cba944f1dd
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd4731e74801bdba48cc8abfa936799db979f926135de7e27f7d2671d1bac66
+oid sha256:6caee68a0e054a100fac034bb9c32751e80c0254f6ec933d4ad128cba944f1dd
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd4731e74801bdba48cc8abfa936799db979f926135de7e27f7d2671d1bac66
+oid sha256:6caee68a0e054a100fac034bb9c32751e80c0254f6ec933d4ad128cba944f1dd
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd4731e74801bdba48cc8abfa936799db979f926135de7e27f7d2671d1bac66
+oid sha256:6caee68a0e054a100fac034bb9c32751e80c0254f6ec933d4ad128cba944f1dd
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd4731e74801bdba48cc8abfa936799db979f926135de7e27f7d2671d1bac66
+oid sha256:6caee68a0e054a100fac034bb9c32751e80c0254f6ec933d4ad128cba944f1dd
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd4731e74801bdba48cc8abfa936799db979f926135de7e27f7d2671d1bac66
+oid sha256:6caee68a0e054a100fac034bb9c32751e80c0254f6ec933d4ad128cba944f1dd
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4ee1c07d4ce16af70500d9164050fdd6814fe5b1c70d5ddc9dc0d403bb72893
+oid sha256:8867e21d1b6a1acf6d7736261e75716fa7b5040d081c92aba0073b066f2ada16
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.3383446906750835,
-  "global_step": 690000,
+  "epoch": 7.449873414898007,
+  "global_step": 700000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -13806,11 +13806,211 @@
       "eval_samples_per_second": 844.818,
       "eval_steps_per_second": 13.241,
       "step": 690000
+    },
+    {
+      "epoch": 7.34,
+      "learning_rate": 4.3573243363356916e-05,
+      "loss": 0.1948,
+      "step": 690500
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 4.347445648076057e-05,
+      "loss": 0.1953,
+      "step": 691000
+    },
+    {
+      "epoch": 7.35,
+      "eval_loss": 0.18430623412132263,
+      "eval_runtime": 2.6745,
+      "eval_samples_per_second": 858.843,
+      "eval_steps_per_second": 13.46,
+      "step": 691000
+    },
+    {
+      "epoch": 7.36,
+      "learning_rate": 4.337576945760554e-05,
+      "loss": 0.1949,
+      "step": 691500
+    },
+    {
+      "epoch": 7.36,
+      "learning_rate": 4.327718256369826e-05,
+      "loss": 0.1947,
+      "step": 692000
+    },
+    {
+      "epoch": 7.36,
+      "eval_loss": 0.18453127145767212,
+      "eval_runtime": 2.6094,
+      "eval_samples_per_second": 880.283,
+      "eval_steps_per_second": 13.796,
+      "step": 692000
+    },
+    {
+      "epoch": 7.37,
+      "learning_rate": 4.317869606857162e-05,
+      "loss": 0.1949,
+      "step": 692500
+    },
+    {
+      "epoch": 7.37,
+      "learning_rate": 4.3080310241483885e-05,
+      "loss": 0.1947,
+      "step": 693000
+    },
+    {
+      "epoch": 7.37,
+      "eval_loss": 0.18398995697498322,
+      "eval_runtime": 2.7028,
+      "eval_samples_per_second": 849.851,
+      "eval_steps_per_second": 13.319,
+      "step": 693000
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 4.298202535141818e-05,
+      "loss": 0.1944,
+      "step": 693500
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 4.2883841667081675e-05,
+      "loss": 0.1945,
+      "step": 694000
+    },
+    {
+      "epoch": 7.38,
+      "eval_loss": 0.1815757304430008,
+      "eval_runtime": 2.6223,
+      "eval_samples_per_second": 875.945,
+      "eval_steps_per_second": 13.728,
+      "step": 694000
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 4.2785759456904745e-05,
+      "loss": 0.1943,
+      "step": 694500
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 4.268777898904044e-05,
+      "loss": 0.1945,
+      "step": 695000
+    },
+    {
+      "epoch": 7.39,
+      "eval_loss": 0.1843911111354828,
+      "eval_runtime": 2.6472,
+      "eval_samples_per_second": 867.72,
+      "eval_steps_per_second": 13.599,
+      "step": 695000
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 4.2589900531363606e-05,
+      "loss": 0.1947,
+      "step": 695500
+    },
+    {
+      "epoch": 7.41,
+      "learning_rate": 4.2492124351470214e-05,
+      "loss": 0.1946,
+      "step": 696000
+    },
+    {
+      "epoch": 7.41,
+      "eval_loss": 0.18493103981018066,
+      "eval_runtime": 2.6337,
+      "eval_samples_per_second": 872.173,
+      "eval_steps_per_second": 13.669,
+      "step": 696000
+    },
+    {
+      "epoch": 7.41,
+      "learning_rate": 4.239445071667666e-05,
+      "loss": 0.1946,
+      "step": 696500
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 4.2296879894018835e-05,
+      "loss": 0.1944,
+      "step": 697000
+    },
+    {
+      "epoch": 7.42,
+      "eval_loss": 0.18418000638484955,
+      "eval_runtime": 2.5716,
+      "eval_samples_per_second": 893.203,
+      "eval_steps_per_second": 13.999,
+      "step": 697000
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 4.219941215025171e-05,
+      "loss": 0.1943,
+      "step": 697500
+    },
+    {
+      "epoch": 7.43,
+      "learning_rate": 4.210204775184834e-05,
+      "loss": 0.1948,
+      "step": 698000
+    },
+    {
+      "epoch": 7.43,
+      "eval_loss": 0.18401235342025757,
+      "eval_runtime": 2.6433,
+      "eval_samples_per_second": 868.996,
+      "eval_steps_per_second": 13.619,
+      "step": 698000
+    },
+    {
+      "epoch": 7.43,
+      "learning_rate": 4.2004786964999304e-05,
+      "loss": 0.1944,
+      "step": 698500
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 4.190763005561186e-05,
+      "loss": 0.1943,
+      "step": 699000
+    },
+    {
+      "epoch": 7.44,
+      "eval_loss": 0.1846538931131363,
+      "eval_runtime": 2.6279,
+      "eval_samples_per_second": 874.077,
+      "eval_steps_per_second": 13.699,
+      "step": 699000
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 4.1810577289309266e-05,
+      "loss": 0.1941,
+      "step": 699500
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 4.171362893143013e-05,
+      "loss": 0.1944,
+      "step": 700000
+    },
+    {
+      "epoch": 7.45,
+      "eval_loss": 0.1839645951986313,
+      "eval_runtime": 2.6536,
+      "eval_samples_per_second": 865.616,
+      "eval_steps_per_second": 13.566,
+      "step": 700000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 4.836879675961344e+22,
+  "total_flos": 4.906979936991691e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d570c8856202350b2a044aa17fe3b227f8d0ac68a7d32a12320d12e3538421d
+oid sha256:9c2cac3521920b845caebb9dc53bd10da39c532c13bda1aeb32ffbf947e78288
 size 449471589