Training in progress, step 260000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981f9cd48efb9aa651b5446906cfef65e3f5e49845175ea67dca9f635e9c1038
+oid sha256:80fb9af3e1214502ea925d3599d3b6efda5d8711659b2c90eec052ea369703f7
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22078b7cadf342376e128bb1b061228e01c38cac2488c2ab30ca05231e48ad59
+oid sha256:4ab3051ab890d6ef671960c94245505fe32b7894ead10b5d7877e9fabce99ffc
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac406c207b2f7429e3395f91a987edf514c0aeff745dd88acf0897c2d8c0d2f5
-size 14439
+oid sha256:72757db14fb233c9a7d81cef99ff1e84d48a76f7d40a8342399239cffc8c3e9f
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a150bbb8b25e860b9b4e4d20308c75cd4211d4f66e73ca0ae830a1483ae3793d
-size 14503
+oid sha256:a8fbef78331483305594b3f85c6f32ce7bab8b9f165e2fb904f362fb3239105f
+size 14567

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba99bff5574a5463122f2331dbbdbc3c75f9c55701d70a2ea0f51810fd185527
-size 14439
+oid sha256:b31003ab7fcda6d6f6ff162f700b04d49c90c118129057bd1f4ee624c393e588
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4ebfa40194a9690e4a04456095f6b6e0d44abd914d615940586748348af8ed
+oid sha256:1da43c666b0af3cbe77f19371961622ab99b1114e6beec7303d695cd496caee4
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1301777ffe2dc7d45e2808f549b6c6f37d8616c9227a415a7757312ea67a80a1
+oid sha256:04396ff3c1feb0819b380c26b60d419205385a8e624d7c59a71eaea179611c46
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.81755157512178,
-  "global_step": 250000,
+  "epoch": 3.970253638126651,
+  "global_step": 260000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1856,11 +1856,85 @@
       "eval_samples_per_second": 983.434,
       "eval_steps_per_second": 15.735,
       "step": 250000
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 0.00013509735236440766,
+      "loss": 0.3003,
+      "step": 251000
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 0.00013495426653524972,
+      "loss": 0.3,
+      "step": 252000
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 0.00013481057973503742,
+      "loss": 0.3,
+      "step": 253000
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 0.00013466629353510651,
+      "loss": 0.2997,
+      "step": 254000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 0.00013452140951334787,
+      "loss": 0.2995,
+      "step": 255000
+    },
+    {
+      "epoch": 3.89,
+      "eval_runtime": 0.8192,
+      "eval_samples_per_second": 1220.744,
+      "eval_steps_per_second": 19.532,
+      "step": 255000
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 0.00013437592925418985,
+      "loss": 0.2996,
+      "step": 256000
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 0.00013422985434858133,
+      "loss": 0.299,
+      "step": 257000
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 0.00013408318639397405,
+      "loss": 0.2987,
+      "step": 258000
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 0.00013393592699430525,
+      "loss": 0.2986,
+      "step": 259000
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 0.00013378807775998012,
+      "loss": 0.2984,
+      "step": 260000
+    },
+    {
+      "epoch": 3.97,
+      "eval_runtime": 1.0461,
+      "eval_samples_per_second": 955.963,
+      "eval_steps_per_second": 15.295,
+      "step": 260000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.7525045545542324e+22,
+  "total_flos": 1.8226048155845795e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22078b7cadf342376e128bb1b061228e01c38cac2488c2ab30ca05231e48ad59
+oid sha256:4ab3051ab890d6ef671960c94245505fe32b7894ead10b5d7877e9fabce99ffc
 size 449471589