Training in progress, step 340000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3af69497cd7909d18e142fdb28af685d5fd4b6d1152a10069e6f9547b752a3d5
+oid sha256:40fe0403207cad2dc3e39d3c817503e5448a77df290f57cccfb2e64288c41acd
 size 995605445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:926d62aa8c0e8eb933d167c471771b77e84d87c1ca180d71a4153e846dcaa5bc
+oid sha256:e08a500181a834c33953e56c8723ea880cc02afa481dcf62ae8634373aca3933
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac0a7c6aeb1853f8f712f2c9f2553cbe98523717c3c148ee76debf888894532
+oid sha256:2a4e01eb4a07664003103c8d71136270f0f89ab5c55108a56ff916a5b2e06d40
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.813239890141112,
-  "global_step": 330000,
+  "epoch": 8.050004735296904,
+  "global_step": 340000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4236,11 +4236,139 @@
       "eval_samples_per_second": 166.406,
       "eval_steps_per_second": 20.805,
       "step": 330000
+    },
+    {
+      "epoch": 7.83,
+      "learning_rate": 0.0,
+      "loss": 2.4532,
+      "step": 330500
+    },
+    {
+      "epoch": 7.84,
+      "learning_rate": 0.0,
+      "loss": 2.4236,
+      "step": 331000
+    },
+    {
+      "epoch": 7.85,
+      "learning_rate": 0.0,
+      "loss": 2.4411,
+      "step": 331500
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 0.0,
+      "loss": 2.4269,
+      "step": 332000
+    },
+    {
+      "epoch": 7.87,
+      "learning_rate": 0.0,
+      "loss": 2.4323,
+      "step": 332500
+    },
+    {
+      "epoch": 7.88,
+      "learning_rate": 0.0,
+      "loss": 2.4343,
+      "step": 333000
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 0.0,
+      "loss": 2.4647,
+      "step": 333500
+    },
+    {
+      "epoch": 7.91,
+      "learning_rate": 0.0,
+      "loss": 2.4331,
+      "step": 334000
+    },
+    {
+      "epoch": 7.92,
+      "learning_rate": 0.0,
+      "loss": 2.439,
+      "step": 334500
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 0.0,
+      "loss": 2.4262,
+      "step": 335000
+    },
+    {
+      "epoch": 7.94,
+      "learning_rate": 0.0,
+      "loss": 2.4369,
+      "step": 335500
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 0.0,
+      "loss": 2.4286,
+      "step": 336000
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 0.0,
+      "loss": 2.4323,
+      "step": 336500
+    },
+    {
+      "epoch": 7.98,
+      "learning_rate": 0.0,
+      "loss": 2.4318,
+      "step": 337000
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 0.0,
+      "loss": 2.4301,
+      "step": 337500
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0,
+      "loss": 2.436,
+      "step": 338000
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0,
+      "loss": 2.4323,
+      "step": 338500
+    },
+    {
+      "epoch": 8.03,
+      "learning_rate": 0.0,
+      "loss": 2.4118,
+      "step": 339000
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 0.0,
+      "loss": 2.4001,
+      "step": 339500
+    },
+    {
+      "epoch": 8.05,
+      "learning_rate": 0.0,
+      "loss": 2.4181,
+      "step": 340000
+    },
+    {
+      "epoch": 8.05,
+      "eval_loss": 3.1522228717803955,
+      "eval_runtime": 112.9345,
+      "eval_samples_per_second": 166.22,
+      "eval_steps_per_second": 20.782,
+      "step": 340000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 6.971360467392e+16,
+  "total_flos": 7.1815677126912e+16,
   "trial_name": null,
   "trial_params": null
 }