Training in progress, step 250000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21c21b20fb8c80d8819d148082ca4735a2ddcf51c6d5bd15312d293ac83a63c8
+oid sha256:981f9cd48efb9aa651b5446906cfef65e3f5e49845175ea67dca9f635e9c1038
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398ac2faeaf62d164de8b0d15d7dce648669506924aad7a65bb21212c9dd95dd
+oid sha256:22078b7cadf342376e128bb1b061228e01c38cac2488c2ab30ca05231e48ad59
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675c1da6a29e5de200fb272be2a868637018c999addc56c161958a25c0a5349b
-size 14503
+oid sha256:ac406c207b2f7429e3395f91a987edf514c0aeff745dd88acf0897c2d8c0d2f5
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3612d2c4e947f05578cbcbc2e6074dbe6180f6b3ff976664366be3670d8b1d56
+oid sha256:a150bbb8b25e860b9b4e4d20308c75cd4211d4f66e73ca0ae830a1483ae3793d
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d433144714402feaf6a20e1bebd60563ad86ca2c8b3c2397a63d836b6b3aee95
+oid sha256:ba99bff5574a5463122f2331dbbdbc3c75f9c55701d70a2ea0f51810fd185527
 size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24627e975d8a309c60a5796ee3829db81bd4fe576d49e1ab91aa7f4b4645e7d4
+oid sha256:4b4ebfa40194a9690e4a04456095f6b6e0d44abd914d615940586748348af8ed
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59cfcefded7a2b207187159c019180f873df3dbebd125628eee7537065bae35
+oid sha256:1301777ffe2dc7d45e2808f549b6c6f37d8616c9227a415a7757312ea67a80a1
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.6648495121169087,
-  "global_step": 240000,
+  "epoch": 3.81755157512178,
+  "global_step": 250000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1782,11 +1782,85 @@
       "eval_samples_per_second": 990.396,
       "eval_steps_per_second": 15.846,
       "step": 240000
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.00013649481627508181,
+      "loss": 0.3031,
+      "step": 241000
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 0.0001363578251256578,
+      "loss": 0.3023,
+      "step": 242000
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 0.00013622021765608754,
+      "loss": 0.3022,
+      "step": 243000
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.00013608199537122425,
+      "loss": 0.3017,
+      "step": 244000
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 0.0001359431597826447,
+      "loss": 0.3019,
+      "step": 245000
+    },
+    {
+      "epoch": 3.74,
+      "eval_runtime": 1.0744,
+      "eval_samples_per_second": 930.717,
+      "eval_steps_per_second": 14.891,
+      "step": 245000
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 0.0001358037124086327,
+      "loss": 0.3015,
+      "step": 246000
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 0.00013566365477416233,
+      "loss": 0.3018,
+      "step": 247000
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 0.00013552298841088144,
+      "loss": 0.3013,
+      "step": 248000
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 0.00013538171485709486,
+      "loss": 0.3006,
+      "step": 249000
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 0.00013523983565774753,
+      "loss": 0.3008,
+      "step": 250000
+    },
+    {
+      "epoch": 3.82,
+      "eval_runtime": 1.0168,
+      "eval_samples_per_second": 983.434,
+      "eval_steps_per_second": 15.735,
+      "step": 250000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.6824042935238852e+22,
+  "total_flos": 1.7525045545542324e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398ac2faeaf62d164de8b0d15d7dce648669506924aad7a65bb21212c9dd95dd
+oid sha256:22078b7cadf342376e128bb1b061228e01c38cac2488c2ab30ca05231e48ad59
 size 449471589