Training in progress, step 410000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4fff2aeefd83972c56998a5a03a364dee23e67947e66df33d2bd966ca11368c
+oid sha256:c55164556dd25d6a582fef22bc2c651808a168730ec26b5c6008062fd0f7cc5d
 size 995605445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c80caa7b1c7797261d4006e75832b7028b5806951118ab498cf6b90ae0034d29
+oid sha256:d13f3b70adc2f936ec547de1ec36f77495ca229446b2ed5ee40a8227e58a819b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92db83fcf7b59e32e0dc1343bd429b913ab1514aa1de584e30dfd9208d927736
+oid sha256:bc51395fb5526d062f2906017676468fbf5f119fecfd463d76e3f9fc8a940a31
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.470593806231651,
-  "global_step": 400000,
+  "epoch": 9.707358651387443,
+  "global_step": 410000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5132,11 +5132,139 @@
       "eval_samples_per_second": 166.431,
       "eval_steps_per_second": 20.808,
       "step": 400000
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 0.0,
+      "loss": 2.413,
+      "step": 400500
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 0.0,
+      "loss": 2.4149,
+      "step": 401000
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 0.0,
+      "loss": 2.4278,
+      "step": 401500
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 0.0,
+      "loss": 2.4337,
+      "step": 402000
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 0.0,
+      "loss": 2.4553,
+      "step": 402500
+    },
+    {
+      "epoch": 9.54,
+      "learning_rate": 0.0,
+      "loss": 2.4216,
+      "step": 403000
+    },
+    {
+      "epoch": 9.55,
+      "learning_rate": 0.0,
+      "loss": 2.4092,
+      "step": 403500
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 0.0,
+      "loss": 2.4274,
+      "step": 404000
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 0.0,
+      "loss": 2.426,
+      "step": 404500
+    },
+    {
+      "epoch": 9.59,
+      "learning_rate": 0.0,
+      "loss": 2.4348,
+      "step": 405000
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 0.0,
+      "loss": 2.4308,
+      "step": 405500
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 0.0,
+      "loss": 2.4369,
+      "step": 406000
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 0.0,
+      "loss": 2.4375,
+      "step": 406500
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 0.0,
+      "loss": 2.4243,
+      "step": 407000
+    },
+    {
+      "epoch": 9.65,
+      "learning_rate": 0.0,
+      "loss": 2.4209,
+      "step": 407500
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 0.0,
+      "loss": 2.4399,
+      "step": 408000
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 0.0,
+      "loss": 2.4302,
+      "step": 408500
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 0.0,
+      "loss": 2.4611,
+      "step": 409000
+    },
+    {
+      "epoch": 9.7,
+      "learning_rate": 0.0,
+      "loss": 2.4166,
+      "step": 409500
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 0.0,
+      "loss": 2.4281,
+      "step": 410000
+    },
+    {
+      "epoch": 9.71,
+      "eval_loss": 3.1522228717803955,
+      "eval_runtime": 112.8711,
+      "eval_samples_per_second": 166.314,
+      "eval_steps_per_second": 20.794,
+      "step": 410000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 8.444449158912e+16,
+  "total_flos": 8.6548090457088e+16,
   "trial_name": null,
   "trial_params": null
 }