Training in progress, step 400000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea287e9b4ef69b399ab26f5a72f16419f78692f80f4478f9dc9fde54c01b3139
+oid sha256:1d612139c711185e81ead4721c4ade182b8281e1479ae688f56802b6c4e9ba79
 size 893441530

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0754eb41ff5a1456b603e8b2753adb511ac0a9ee839b9d73f658f3c72064f5ce
+oid sha256:4fa7a23bc8b764ecbc33e951ce5db5a8164946993424ddee93b25c094c7c5323
 size 454197066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea76d909d3c482cb352315f678531422d38691040b817f22cbe42d6a4283267d
+oid sha256:5d031f87a51288ac205183f504513071ae4228fb022abef477b54b6727749f44
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb7667759b15c886ebe5f226629aa0745d8db84769a12c7b2d7c8d4d08bd35a
+oid sha256:3802b6d325bea1bd6ad9279691926311340a3a4209ab5b2d2bcf1374ce2a9b10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.39,
-  "global_step": 390000,
+  "epoch": 0.4,
+  "global_step": 400000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2892,11 +2892,85 @@
       "eval_samples_per_second": 105.762,
       "eval_steps_per_second": 13.22,
       "step": 390000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.625086510311916e-05,
+      "loss": 0.3443,
+      "step": 391000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.623778440059719e-05,
+      "loss": 0.3439,
+      "step": 392000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.622468332696346e-05,
+      "loss": 0.3444,
+      "step": 393000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.6211562025489212e-05,
+      "loss": 0.3426,
+      "step": 394000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.6198420639666893e-05,
+      "loss": 0.3395,
+      "step": 395000
+    },
+    {
+      "epoch": 0.4,
+      "eval_runtime": 3116.6643,
+      "eval_samples_per_second": 108.979,
+      "eval_steps_per_second": 13.623,
+      "step": 395000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.61852593132086e-05,
+      "loss": 0.3363,
+      "step": 396000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.6172078190044487e-05,
+      "loss": 0.3362,
+      "step": 397000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.61588774143212e-05,
+      "loss": 0.3414,
+      "step": 398000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.614565713040032e-05,
+      "loss": 0.3447,
+      "step": 399000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.613241748285674e-05,
+      "loss": 0.3438,
+      "step": 400000
+    },
+    {
+      "epoch": 0.4,
+      "eval_runtime": 3111.8012,
+      "eval_samples_per_second": 109.15,
+      "eval_steps_per_second": 13.644,
+      "step": 400000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 3.4532979675601306e+21,
+  "total_flos": 3.5418440692924416e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0754eb41ff5a1456b603e8b2753adb511ac0a9ee839b9d73f658f3c72064f5ce
+oid sha256:4fa7a23bc8b764ecbc33e951ce5db5a8164946993424ddee93b25c094c7c5323
 size 454197066