Training in progress, step 420000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c55164556dd25d6a582fef22bc2c651808a168730ec26b5c6008062fd0f7cc5d
+oid sha256:a8d8ec6028dead3d065f5e19f39c225d85816b62dfc54fdff7b0a67b5e1553ac
 size 995605445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d13f3b70adc2f936ec547de1ec36f77495ca229446b2ed5ee40a8227e58a819b
+oid sha256:177da09f25973ce374c55c97d3fcb0a54d0e03455809b93e6dc65d55606d23b1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc51395fb5526d062f2906017676468fbf5f119fecfd463d76e3f9fc8a940a31
+oid sha256:d0a0d52267e40d2e8071377ef892e2dec84343c6b0d715ab78d160ed1be31b19
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.707358651387443,
-  "global_step": 410000,
+  "epoch": 9.944123496543233,
+  "global_step": 420000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5260,11 +5260,139 @@
       "eval_samples_per_second": 166.314,
       "eval_steps_per_second": 20.794,
       "step": 410000
+    },
+    {
+      "epoch": 9.72,
+      "learning_rate": 0.0,
+      "loss": 2.4291,
+      "step": 410500
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 0.0,
+      "loss": 2.4174,
+      "step": 411000
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 0.0,
+      "loss": 2.4336,
+      "step": 411500
+    },
+    {
+      "epoch": 9.75,
+      "learning_rate": 0.0,
+      "loss": 2.4315,
+      "step": 412000
+    },
+    {
+      "epoch": 9.77,
+      "learning_rate": 0.0,
+      "loss": 2.4305,
+      "step": 412500
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 0.0,
+      "loss": 2.4303,
+      "step": 413000
+    },
+    {
+      "epoch": 9.79,
+      "learning_rate": 0.0,
+      "loss": 2.4342,
+      "step": 413500
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 0.0,
+      "loss": 2.4348,
+      "step": 414000
+    },
+    {
+      "epoch": 9.81,
+      "learning_rate": 0.0,
+      "loss": 2.4026,
+      "step": 414500
+    },
+    {
+      "epoch": 9.83,
+      "learning_rate": 0.0,
+      "loss": 2.4215,
+      "step": 415000
+    },
+    {
+      "epoch": 9.84,
+      "learning_rate": 0.0,
+      "loss": 2.4197,
+      "step": 415500
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 0.0,
+      "loss": 2.4167,
+      "step": 416000
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 0.0,
+      "loss": 2.4285,
+      "step": 416500
+    },
+    {
+      "epoch": 9.87,
+      "learning_rate": 0.0,
+      "loss": 2.4292,
+      "step": 417000
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 0.0,
+      "loss": 2.4294,
+      "step": 417500
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 0.0,
+      "loss": 2.418,
+      "step": 418000
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 0.0,
+      "loss": 2.437,
+      "step": 418500
+    },
+    {
+      "epoch": 9.92,
+      "learning_rate": 0.0,
+      "loss": 2.4259,
+      "step": 419000
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 0.0,
+      "loss": 2.4406,
+      "step": 419500
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 0.0,
+      "loss": 2.4385,
+      "step": 420000
+    },
+    {
+      "epoch": 9.94,
+      "eval_loss": 3.1522228717803955,
+      "eval_runtime": 112.8353,
+      "eval_samples_per_second": 166.366,
+      "eval_steps_per_second": 20.8,
+      "step": 420000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 8.6548090457088e+16,
+  "total_flos": 8.8658966716416e+16,
   "trial_name": null,
   "trial_params": null
 }