Training in progress, step 150000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1a663fa8a1428dfd0e1ea579f8f1884a2fe84a94e67275218c60462158fe8aa
+oid sha256:b6ca6f24dcb89d2b5b321d41377d7112797ffe1d907f15ddff7ba7e26609c862
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40275396ce53417c9c00526c28902e900eee7fe8a1176e3b167b8fa880709f1
+oid sha256:1c4cd57564a779ce9b253560bee2c5cd0e86bb9d45deec93038af06a21499a13
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6473d36a3b0d61e638f6f7adf0e3c4e3a4c90311741bef45eedc8752b4abbb
+oid sha256:fae3b17a22413cb3757589f57743e787359e0022772ac1abcd8cd137a4f47d67
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd20d5dfc80e3bb5cba79ef18d635e6b9d3fba3685d49236ba9bbfcbd245f3d
-size 14439
+oid sha256:a779f8fc855d59bcbf291b4cc6b19be7fee9321eb3062f5a2a4c0cebbb9c9578
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2963be3c0faa28379747d9429ff572f2788db89f6185c9c53832cb9290c1c849
+oid sha256:9b690234daa5d8c7710fe7be510d329d20ff0051c4744ffca45867ea3553623e
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4f1c2a017f1ba8bd941830cb07d47e6bde89cb5e80ca0663de3f779aa3e16b
-size 14439
+oid sha256:42a7533496fd3447c3098c72eeb99bc915be9c71a99c7b280c1c6731f19f5133
+size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52188af98e11936af8bc69f5366b88b44cd6c73d9b1b37682a5e46e4706f5e3f
-size 14439
+oid sha256:39883cc54bbec8fad581d8040cd06ed3b456d464ef56b30767c2b26d32316b88
+size 14567

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:299331297e38ed6c53d0026997de39e06ade131719f6e2f227655bc716b72e7d
+oid sha256:9a09d63ee9a8f047626f54ecfd465d1f3475fbfb179597785b1c98b6cb830f2d
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d145aa3067eb9b9e66af4f261f18929e80b865f364d9ea9075acacb8581bccd8
-size 14503
+oid sha256:4c16621f2d614cd323b166e84be0e313d4e55c720c949cc61553843d3fcddcc8
+size 14439

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8dc2be3757aa011e41ae06df8c828d05d218a32a27ad90767a1b48fa565a909
-size 14439
+oid sha256:2acd8d931b1baaa8c54719beb8cd5cf9a1180f13f5175d45461cfed4154f4fc9
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9522f343e5b1c37fe7e600f7b39d619e850350d8948dc240940a440582a0eb9
+oid sha256:c09454c2cc8aac6faf99c7970cf8bec57b59b683887c6bb291c3a0936d0e7d0d
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.289347100094979,
-  "global_step": 140000,
+  "epoch": 4.595729035816048,
+  "global_step": 150000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2806,11 +2806,211 @@
       "eval_samples_per_second": 1907.849,
       "eval_steps_per_second": 30.526,
       "step": 140000
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 0.0002597105316716766,
+      "loss": 0.3598,
+      "step": 140500
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 0.000259378263551047,
+      "loss": 0.3598,
+      "step": 141000
+    },
+    {
+      "epoch": 4.32,
+      "eval_loss": 0.7810735106468201,
+      "eval_runtime": 0.5319,
+      "eval_samples_per_second": 1879.976,
+      "eval_steps_per_second": 30.08,
+      "step": 141000
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 0.0002590448539664501,
+      "loss": 0.3595,
+      "step": 141500
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 0.00025871030656399966,
+      "loss": 0.3585,
+      "step": 142000
+    },
+    {
+      "epoch": 4.35,
+      "eval_loss": 0.7808945775032043,
+      "eval_runtime": 0.5345,
+      "eval_samples_per_second": 1870.803,
+      "eval_steps_per_second": 29.933,
+      "step": 142000
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 0.00025837462500225255,
+      "loss": 0.3588,
+      "step": 142500
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 0.0002580378129521685,
+      "loss": 0.3589,
+      "step": 143000
+    },
+    {
+      "epoch": 4.38,
+      "eval_loss": 0.7889230251312256,
+      "eval_runtime": 0.5368,
+      "eval_samples_per_second": 1862.837,
+      "eval_steps_per_second": 29.805,
+      "step": 143000
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 0.0002576998740970701,
+      "loss": 0.3587,
+      "step": 143500
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 0.00025736081213260253,
+      "loss": 0.3588,
+      "step": 144000
+    },
+    {
+      "epoch": 4.41,
+      "eval_loss": 0.7862944602966309,
+      "eval_runtime": 0.5148,
+      "eval_samples_per_second": 1942.516,
+      "eval_steps_per_second": 31.08,
+      "step": 144000
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 0.0002570206307666931,
+      "loss": 0.3588,
+      "step": 144500
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 0.0002566793337195108,
+      "loss": 0.3582,
+      "step": 145000
+    },
+    {
+      "epoch": 4.44,
+      "eval_loss": 0.7859060168266296,
+      "eval_runtime": 0.5347,
+      "eval_samples_per_second": 1870.153,
+      "eval_steps_per_second": 29.922,
+      "step": 145000
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 0.0002563369247234254,
+      "loss": 0.358,
+      "step": 145500
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 0.0002559934075229669,
+      "loss": 0.3577,
+      "step": 146000
+    },
+    {
+      "epoch": 4.47,
+      "eval_loss": 0.7823663353919983,
+      "eval_runtime": 0.5372,
+      "eval_samples_per_second": 1861.564,
+      "eval_steps_per_second": 29.785,
+      "step": 146000
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 0.0002556487858747843,
+      "loss": 0.3578,
+      "step": 146500
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.00025530306354760464,
+      "loss": 0.3577,
+      "step": 147000
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 0.7786086201667786,
+      "eval_runtime": 0.5231,
+      "eval_samples_per_second": 1911.791,
+      "eval_steps_per_second": 30.589,
+      "step": 147000
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 0.000254956244322192,
+      "loss": 0.3578,
+      "step": 147500
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 0.00025460833199130595,
+      "loss": 0.3575,
+      "step": 148000
+    },
+    {
+      "epoch": 4.53,
+      "eval_loss": 0.7865322232246399,
+      "eval_runtime": 0.5303,
+      "eval_samples_per_second": 1885.606,
+      "eval_steps_per_second": 30.17,
+      "step": 148000
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 0.00025425933035965983,
+      "loss": 0.3575,
+      "step": 148500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 0.00025390924324387965,
+      "loss": 0.3573,
+      "step": 149000
+    },
+    {
+      "epoch": 4.57,
+      "eval_loss": 0.787778913974762,
+      "eval_runtime": 0.5202,
+      "eval_samples_per_second": 1922.286,
+      "eval_steps_per_second": 30.757,
+      "step": 149000
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 0.0002535580744724621,
+      "loss": 0.3569,
+      "step": 149500
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 0.00025320582788573246,
+      "loss": 0.357,
+      "step": 150000
+    },
+    {
+      "epoch": 4.6,
+      "eval_loss": 0.7871734499931335,
+      "eval_runtime": 0.5167,
+      "eval_samples_per_second": 1935.344,
+      "eval_steps_per_second": 30.965,
+      "step": 150000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 4.4727879910350966e+21,
+  "total_flos": 4.792275129809597e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40275396ce53417c9c00526c28902e900eee7fe8a1176e3b167b8fa880709f1
+oid sha256:1c4cd57564a779ce9b253560bee2c5cd0e86bb9d45deec93038af06a21499a13
 size 102501541