Training in progress, step 140000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c7a3961722d5e2e1d58ab1ec5745ef09a520dff61782c5846ec96a38f0f0c0
+oid sha256:e173bc943b29aa0c21d3ea395d64346619684e911c9d2c5653a946ad93a080fb
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28d9f72755d5cec4196d53c4e7dbdd8ce8cdc55da23e20816db43ca099c784e
+oid sha256:718ae4d2d3142ad404624adda63a8e3a7a6979058daf4ac16e2302ca1bd70cad
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
+oid sha256:9adf2102d447f7393e18e9f9b393b7a5d5b8bba1c09f379d54252dccfd8d5615
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
+oid sha256:9adf2102d447f7393e18e9f9b393b7a5d5b8bba1c09f379d54252dccfd8d5615
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
+oid sha256:9adf2102d447f7393e18e9f9b393b7a5d5b8bba1c09f379d54252dccfd8d5615
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
+oid sha256:9adf2102d447f7393e18e9f9b393b7a5d5b8bba1c09f379d54252dccfd8d5615
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
+oid sha256:9adf2102d447f7393e18e9f9b393b7a5d5b8bba1c09f379d54252dccfd8d5615
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
+oid sha256:9adf2102d447f7393e18e9f9b393b7a5d5b8bba1c09f379d54252dccfd8d5615
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
+oid sha256:9adf2102d447f7393e18e9f9b393b7a5d5b8bba1c09f379d54252dccfd8d5615
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
+oid sha256:9adf2102d447f7393e18e9f9b393b7a5d5b8bba1c09f379d54252dccfd8d5615
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c3de3c2d66025eca4b56b8d5efacb781ba1e9b4daae40acd9c92c0f7cbe98c
+oid sha256:f9522f343e5b1c37fe7e600f7b39d619e850350d8948dc240940a440582a0eb9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8997144896502496,
-  "global_step": 130000,
+  "epoch": 3.122769450392577,
+  "global_step": 140000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2606,11 +2606,211 @@
       "eval_samples_per_second": 1154.041,
       "eval_steps_per_second": 18.087,
       "step": 130000
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 0.0002661106834948409,
+      "loss": 0.2971,
+      "step": 130500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 0.0002658019908268041,
+      "loss": 0.2968,
+      "step": 131000
+    },
+    {
+      "epoch": 2.92,
+      "eval_loss": 0.27784037590026855,
+      "eval_runtime": 1.9858,
+      "eval_samples_per_second": 1156.736,
+      "eval_steps_per_second": 18.129,
+      "step": 131000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.00026549208644594766,
+      "loss": 0.2965,
+      "step": 131500
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.00026518097374133627,
+      "loss": 0.2965,
+      "step": 132000
+    },
+    {
+      "epoch": 2.94,
+      "eval_loss": 0.27897170186042786,
+      "eval_runtime": 1.9786,
+      "eval_samples_per_second": 1160.938,
+      "eval_steps_per_second": 18.195,
+      "step": 132000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.00026486865611524853,
+      "loss": 0.2964,
+      "step": 132500
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 0.00026455513698314003,
+      "loss": 0.2968,
+      "step": 133000
+    },
+    {
+      "epoch": 2.97,
+      "eval_loss": 0.27647751569747925,
+      "eval_runtime": 1.9935,
+      "eval_samples_per_second": 1152.23,
+      "eval_steps_per_second": 18.058,
+      "step": 133000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0002642404197736058,
+      "loss": 0.2959,
+      "step": 133500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002639245079283428,
+      "loss": 0.2962,
+      "step": 134000
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 0.2772797644138336,
+      "eval_runtime": 1.997,
+      "eval_samples_per_second": 1150.213,
+      "eval_steps_per_second": 18.027,
+      "step": 134000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00026360740490211234,
+      "loss": 0.2957,
+      "step": 134500
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0002632891141627023,
+      "loss": 0.2961,
+      "step": 135000
+    },
+    {
+      "epoch": 3.01,
+      "eval_loss": 0.27765029668807983,
+      "eval_runtime": 1.9854,
+      "eval_samples_per_second": 1156.944,
+      "eval_steps_per_second": 18.132,
+      "step": 135000
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.00026296963919088923,
+      "loss": 0.2956,
+      "step": 135500
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 0.00026264898348040024,
+      "loss": 0.2955,
+      "step": 136000
+    },
+    {
+      "epoch": 3.03,
+      "eval_loss": 0.27664855122566223,
+      "eval_runtime": 1.9862,
+      "eval_samples_per_second": 1156.498,
+      "eval_steps_per_second": 18.125,
+      "step": 136000
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.0002623271505378748,
+      "loss": 0.2952,
+      "step": 136500
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 0.00026200414388282637,
+      "loss": 0.2951,
+      "step": 137000
+    },
+    {
+      "epoch": 3.06,
+      "eval_loss": 0.2762826979160309,
+      "eval_runtime": 1.9933,
+      "eval_samples_per_second": 1152.379,
+      "eval_steps_per_second": 18.061,
+      "step": 137000
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 0.00026167996704760406,
+      "loss": 0.2952,
+      "step": 137500
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 0.00026135462357735375,
+      "loss": 0.295,
+      "step": 138000
+    },
+    {
+      "epoch": 3.08,
+      "eval_loss": 0.27805039286613464,
+      "eval_runtime": 2.0209,
+      "eval_samples_per_second": 1136.598,
+      "eval_steps_per_second": 17.813,
+      "step": 138000
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 0.0002610281170299795,
+      "loss": 0.2948,
+      "step": 138500
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.00026070045097610465,
+      "loss": 0.2948,
+      "step": 139000
+    },
+    {
+      "epoch": 3.1,
+      "eval_loss": 0.27585625648498535,
+      "eval_runtime": 2.0475,
+      "eval_samples_per_second": 1121.859,
+      "eval_steps_per_second": 17.582,
+      "step": 139000
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 0.0002603716289990326,
+      "loss": 0.2944,
+      "step": 139500
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 0.00026004165469470787,
+      "loss": 0.2945,
+      "step": 140000
+    },
+    {
+      "epoch": 3.12,
+      "eval_loss": 0.28066232800483704,
+      "eval_runtime": 1.9112,
+      "eval_samples_per_second": 1201.849,
+      "eval_steps_per_second": 18.836,
+      "step": 140000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 4.1532758955456694e+21,
+  "total_flos": 4.472734580058754e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28d9f72755d5cec4196d53c4e7dbdd8ce8cdc55da23e20816db43ca099c784e
+oid sha256:718ae4d2d3142ad404624adda63a8e3a7a6979058daf4ac16e2302ca1bd70cad
 size 102501541