Training in progress, step 500000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005db65eb58f9237e48ebb211a3461d36a8a5572524730ba998bc2393e3a0b49
+oid sha256:da5c66e223c9afd97a3b2031f28400ecc3ff5cf48322a645ecb5c3d4ba9e2cc8
 size 995605445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76e0744d6f0f537056ad5103f02a6d5f5eb5eb960f943e779627f94d0de15e0
+oid sha256:724fe75b2891e3eb33370e185b7549e8b85ea750d0af5d509737ae3f8927f173
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28300f1d8f6ee8059c5bd58bb510fd233bccfaebc75fff86f7a87e9ea5e4924e
+oid sha256:2934ce8ee53a3f126996335cb7a1d2a9354eb222cdf717375f161332a72ce0b8
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.601477412633772,
-  "global_step": 490000,
+  "epoch": 11.838242257789563,
+  "global_step": 500000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6284,11 +6284,139 @@
       "eval_samples_per_second": 166.429,
       "eval_steps_per_second": 20.808,
       "step": 490000
+    },
+    {
+      "epoch": 11.61,
+      "learning_rate": 0.0,
+      "loss": 2.4271,
+      "step": 490500
+    },
+    {
+      "epoch": 11.63,
+      "learning_rate": 0.0,
+      "loss": 2.4343,
+      "step": 491000
+    },
+    {
+      "epoch": 11.64,
+      "learning_rate": 0.0,
+      "loss": 2.4414,
+      "step": 491500
+    },
+    {
+      "epoch": 11.65,
+      "learning_rate": 0.0,
+      "loss": 2.4335,
+      "step": 492000
+    },
+    {
+      "epoch": 11.66,
+      "learning_rate": 0.0,
+      "loss": 2.4353,
+      "step": 492500
+    },
+    {
+      "epoch": 11.67,
+      "learning_rate": 0.0,
+      "loss": 2.4308,
+      "step": 493000
+    },
+    {
+      "epoch": 11.68,
+      "learning_rate": 0.0,
+      "loss": 2.4395,
+      "step": 493500
+    },
+    {
+      "epoch": 11.7,
+      "learning_rate": 0.0,
+      "loss": 2.4239,
+      "step": 494000
+    },
+    {
+      "epoch": 11.71,
+      "learning_rate": 0.0,
+      "loss": 2.4247,
+      "step": 494500
+    },
+    {
+      "epoch": 11.72,
+      "learning_rate": 0.0,
+      "loss": 2.4229,
+      "step": 495000
+    },
+    {
+      "epoch": 11.73,
+      "learning_rate": 0.0,
+      "loss": 2.4253,
+      "step": 495500
+    },
+    {
+      "epoch": 11.74,
+      "learning_rate": 0.0,
+      "loss": 2.4108,
+      "step": 496000
+    },
+    {
+      "epoch": 11.76,
+      "learning_rate": 0.0,
+      "loss": 2.4133,
+      "step": 496500
+    },
+    {
+      "epoch": 11.77,
+      "learning_rate": 0.0,
+      "loss": 2.4318,
+      "step": 497000
+    },
+    {
+      "epoch": 11.78,
+      "learning_rate": 0.0,
+      "loss": 2.4255,
+      "step": 497500
+    },
+    {
+      "epoch": 11.79,
+      "learning_rate": 0.0,
+      "loss": 2.4123,
+      "step": 498000
+    },
+    {
+      "epoch": 11.8,
+      "learning_rate": 0.0,
+      "loss": 2.4323,
+      "step": 498500
+    },
+    {
+      "epoch": 11.81,
+      "learning_rate": 0.0,
+      "loss": 2.4014,
+      "step": 499000
+    },
+    {
+      "epoch": 11.83,
+      "learning_rate": 0.0,
+      "loss": 2.4377,
+      "step": 499500
+    },
+    {
+      "epoch": 11.84,
+      "learning_rate": 0.0,
+      "loss": 2.4497,
+      "step": 500000
+    },
+    {
+      "epoch": 11.84,
+      "eval_loss": 3.1522228717803955,
+      "eval_runtime": 113.0091,
+      "eval_samples_per_second": 166.11,
+      "eval_steps_per_second": 20.768,
+      "step": 500000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 1.0338847011072e+17,
+  "total_flos": 1.0549596386304e+17,
   "trial_name": null,
   "trial_params": null
 }