Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b801dea4c20ae9f56153a02de048f5ae98203f41a9a2f643b5429e198a7fdc
+oid sha256:d8f3b98eec5b3330ddfd893550d0b15b1b8d3330c8cebf4f71e48ba5e53f55fb
 size 202193937

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8da0387c8445a52a92bcde48c6a02b31823dfc1997cb4f757ede3d79441e525
+oid sha256:1a3342707635b819a44d4ba00aeaa19e6d315541706f6b4722b779d3a00d1c81
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
+oid sha256:bcb55e432a6b8e9309bc4392d2b0405c96d19402563e4d0018c43fbf20f6cd3d
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
+oid sha256:bcb55e432a6b8e9309bc4392d2b0405c96d19402563e4d0018c43fbf20f6cd3d
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
+oid sha256:bcb55e432a6b8e9309bc4392d2b0405c96d19402563e4d0018c43fbf20f6cd3d
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
+oid sha256:bcb55e432a6b8e9309bc4392d2b0405c96d19402563e4d0018c43fbf20f6cd3d
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
+oid sha256:bcb55e432a6b8e9309bc4392d2b0405c96d19402563e4d0018c43fbf20f6cd3d
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
+oid sha256:bcb55e432a6b8e9309bc4392d2b0405c96d19402563e4d0018c43fbf20f6cd3d
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
+oid sha256:bcb55e432a6b8e9309bc4392d2b0405c96d19402563e4d0018c43fbf20f6cd3d
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
+oid sha256:bcb55e432a6b8e9309bc4392d2b0405c96d19402563e4d0018c43fbf20f6cd3d
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec5c60f6b831a1ad5ababd554115ca1132f641d196d63d42183ef95c8827963
+oid sha256:1afd4be721b18cec2bad25f6a60e1c3abb5c311277f62eb3e2f010bc31239df1
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1152748037116345,
-  "global_step": 50000,
+  "epoch": 1.3383297644539613,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1006,11 +1006,211 @@
       "eval_samples_per_second": 1140.566,
       "eval_steps_per_second": 17.876,
       "step": 50000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002979426829679962,
+      "loss": 0.3406,
+      "step": 50500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002978614137443183,
+      "loss": 0.3398,
+      "step": 51000
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 0.32256901264190674,
+      "eval_runtime": 1.9699,
+      "eval_samples_per_second": 1166.043,
+      "eval_steps_per_second": 18.275,
+      "step": 51000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.000297778582211108,
+      "loss": 0.3391,
+      "step": 51500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029769418927419786,
+      "loss": 0.3385,
+      "step": 52000
+    },
+    {
+      "epoch": 1.16,
+      "eval_loss": 0.3191610276699066,
+      "eval_runtime": 2.0164,
+      "eval_samples_per_second": 1139.174,
+      "eval_steps_per_second": 17.854,
+      "step": 52000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002976082358564954,
+      "loss": 0.3381,
+      "step": 52500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00029752072289797353,
+      "loss": 0.3372,
+      "step": 53000
+    },
+    {
+      "epoch": 1.18,
+      "eval_loss": 0.31954050064086914,
+      "eval_runtime": 1.913,
+      "eval_samples_per_second": 1200.727,
+      "eval_steps_per_second": 18.819,
+      "step": 53000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00029743165135565986,
+      "loss": 0.3368,
+      "step": 53500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00029734102220362654,
+      "loss": 0.3359,
+      "step": 54000
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.31627157330513,
+      "eval_runtime": 2.0014,
+      "eval_samples_per_second": 1147.684,
+      "eval_steps_per_second": 17.987,
+      "step": 54000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00029724883643297937,
+      "loss": 0.3356,
+      "step": 54500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0002971550950518473,
+      "loss": 0.3348,
+      "step": 55000
+    },
+    {
+      "epoch": 1.23,
+      "eval_loss": 0.3175150454044342,
+      "eval_runtime": 2.0666,
+      "eval_samples_per_second": 1111.49,
+      "eval_steps_per_second": 17.42,
+      "step": 55000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.000297059799085371,
+      "loss": 0.3343,
+      "step": 55500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00029696294957569196,
+      "loss": 0.3338,
+      "step": 56000
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 0.3165690302848816,
+      "eval_runtime": 2.0136,
+      "eval_samples_per_second": 1140.732,
+      "eval_steps_per_second": 17.878,
+      "step": 56000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00029686454758194076,
+      "loss": 0.3331,
+      "step": 56500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00029676459418022594,
+      "loss": 0.3327,
+      "step": 57000
+    },
+    {
+      "epoch": 1.27,
+      "eval_loss": 0.316009521484375,
+      "eval_runtime": 1.9665,
+      "eval_samples_per_second": 1168.059,
+      "eval_steps_per_second": 18.307,
+      "step": 57000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002966630904636219,
+      "loss": 0.3321,
+      "step": 57500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002965600375421569,
+      "loss": 0.3315,
+      "step": 58000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.31569892168045044,
+      "eval_runtime": 2.026,
+      "eval_samples_per_second": 1133.75,
+      "eval_steps_per_second": 17.769,
+      "step": 58000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002964554365428013,
+      "loss": 0.3313,
+      "step": 58500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00029634928860945486,
+      "loss": 0.3301,
+      "step": 59000
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.310556024312973,
+      "eval_runtime": 2.0156,
+      "eval_samples_per_second": 1139.586,
+      "eval_steps_per_second": 17.86,
+      "step": 59000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002962415949029343,
+      "loss": 0.33,
+      "step": 59500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00029613235660096084,
+      "loss": 0.3294,
+      "step": 60000
+    },
+    {
+      "epoch": 1.34,
+      "eval_loss": 0.3107939064502716,
+      "eval_runtime": 1.9893,
+      "eval_samples_per_second": 1154.672,
+      "eval_steps_per_second": 18.097,
+      "step": 60000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.5974072396110847e+21,
+  "total_flos": 1.9168943783855847e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8da0387c8445a52a92bcde48c6a02b31823dfc1997cb4f757ede3d79441e525
+oid sha256:1a3342707635b819a44d4ba00aeaa19e6d315541706f6b4722b779d3a00d1c81
 size 102501541