Training in progress, step 510000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da5c66e223c9afd97a3b2031f28400ecc3ff5cf48322a645ecb5c3d4ba9e2cc8
+oid sha256:68aa498d0e3983775adcecf2a5f78debf331313630e2436769b35a9399923c5c
 size 995605445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724fe75b2891e3eb33370e185b7549e8b85ea750d0af5d509737ae3f8927f173
+oid sha256:397a701b388141e6d39ca7be9b1469b741594cf39c18781ab0d884cb484ca723
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2934ce8ee53a3f126996335cb7a1d2a9354eb222cdf717375f161332a72ce0b8
+oid sha256:fa99ca31aedd6429013044fa3d239b87534181d83f6f020dbd10161874bc75c9
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.838242257789563,
-  "global_step": 500000,
+  "epoch": 12.075007102945355,
+  "global_step": 510000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6412,11 +6412,139 @@
       "eval_samples_per_second": 166.11,
       "eval_steps_per_second": 20.768,
       "step": 500000
+    },
+    {
+      "epoch": 11.85,
+      "learning_rate": 0.0,
+      "loss": 2.4292,
+      "step": 500500
+    },
+    {
+      "epoch": 11.86,
+      "learning_rate": 0.0,
+      "loss": 2.4061,
+      "step": 501000
+    },
+    {
+      "epoch": 11.87,
+      "learning_rate": 0.0,
+      "loss": 2.4113,
+      "step": 501500
+    },
+    {
+      "epoch": 11.89,
+      "learning_rate": 0.0,
+      "loss": 2.4295,
+      "step": 502000
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 0.0,
+      "loss": 2.4258,
+      "step": 502500
+    },
+    {
+      "epoch": 11.91,
+      "learning_rate": 0.0,
+      "loss": 2.4297,
+      "step": 503000
+    },
+    {
+      "epoch": 11.92,
+      "learning_rate": 0.0,
+      "loss": 2.4361,
+      "step": 503500
+    },
+    {
+      "epoch": 11.93,
+      "learning_rate": 0.0,
+      "loss": 2.4306,
+      "step": 504000
+    },
+    {
+      "epoch": 11.94,
+      "learning_rate": 0.0,
+      "loss": 2.4255,
+      "step": 504500
+    },
+    {
+      "epoch": 11.96,
+      "learning_rate": 0.0,
+      "loss": 2.4262,
+      "step": 505000
+    },
+    {
+      "epoch": 11.97,
+      "learning_rate": 0.0,
+      "loss": 2.4273,
+      "step": 505500
+    },
+    {
+      "epoch": 11.98,
+      "learning_rate": 0.0,
+      "loss": 2.4112,
+      "step": 506000
+    },
+    {
+      "epoch": 11.99,
+      "learning_rate": 0.0,
+      "loss": 2.4283,
+      "step": 506500
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.0,
+      "loss": 2.4236,
+      "step": 507000
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.0,
+      "loss": 2.4315,
+      "step": 507500
+    },
+    {
+      "epoch": 12.03,
+      "learning_rate": 0.0,
+      "loss": 2.4321,
+      "step": 508000
+    },
+    {
+      "epoch": 12.04,
+      "learning_rate": 0.0,
+      "loss": 2.4189,
+      "step": 508500
+    },
+    {
+      "epoch": 12.05,
+      "learning_rate": 0.0,
+      "loss": 2.422,
+      "step": 509000
+    },
+    {
+      "epoch": 12.06,
+      "learning_rate": 0.0,
+      "loss": 2.4198,
+      "step": 509500
+    },
+    {
+      "epoch": 12.08,
+      "learning_rate": 0.0,
+      "loss": 2.4139,
+      "step": 510000
+    },
+    {
+      "epoch": 12.08,
+      "eval_loss": 3.1522228717803955,
+      "eval_runtime": 112.9202,
+      "eval_samples_per_second": 166.241,
+      "eval_steps_per_second": 20.785,
+      "step": 510000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 1.0549596386304e+17,
+  "total_flos": 1.07592688505088e+17,
   "trial_name": null,
   "trial_params": null
 }