Training in progress, step 90000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7b30dd7d3cd1b36c3fa0208b9738aaffe2cc51d1a7feb434cdea790af51c1c
+oid sha256:150d8b3c57728037c4a472baaa9d8c4cdc3e29d155183e7b2a12684f9319c8cc
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2721d72b42462f692fdf3de82485b9d24d7776a465480990b2df5c24285a8e05
+oid sha256:ac7a8dbd06b2428a64e1f1bb1794f8399c9be17660f04561ced3ff300c0d49c2
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
+oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
+oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
+oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
+oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
+oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
+oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
+oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
+oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff31836ff2c96f7fb19d95df664b507273477e3a4f87dcce611b28b7e31820b
+oid sha256:5810d5d1337eca8d561357c6c9e9920258e5fc2b2f0f70ea4b52e4984949eec8
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.863976327500641,
-  "global_step": 80000,
+  "epoch": 2.096973368438221,
+  "global_step": 90000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1606,11 +1606,211 @@
       "eval_samples_per_second": 1505.956,
       "eval_steps_per_second": 23.98,
       "step": 80000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00029034050133765947,
+      "loss": 0.3111,
+      "step": 80500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00029016767524635804,
+      "loss": 0.3109,
+      "step": 81000
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 0.2935539484024048,
+      "eval_runtime": 1.3879,
+      "eval_samples_per_second": 1583.739,
+      "eval_steps_per_second": 25.219,
+      "step": 81000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00028999337098301585,
+      "loss": 0.3108,
+      "step": 81500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0002898175904537964,
+      "loss": 0.3103,
+      "step": 82000
+    },
+    {
+      "epoch": 1.91,
+      "eval_loss": 0.2912616431713104,
+      "eval_runtime": 1.3921,
+      "eval_samples_per_second": 1578.853,
+      "eval_steps_per_second": 25.141,
+      "step": 82000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0002896403355810075,
+      "loss": 0.3104,
+      "step": 82500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00028946160830307997,
+      "loss": 0.3102,
+      "step": 83000
+    },
+    {
+      "epoch": 1.93,
+      "eval_loss": 0.29547759890556335,
+      "eval_runtime": 1.4163,
+      "eval_samples_per_second": 1551.936,
+      "eval_steps_per_second": 24.712,
+      "step": 83000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00028928141057454665,
+      "loss": 0.3099,
+      "step": 83500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.0002890997443660211,
+      "loss": 0.3096,
+      "step": 84000
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 0.29173827171325684,
+      "eval_runtime": 1.3888,
+      "eval_samples_per_second": 1582.667,
+      "eval_steps_per_second": 25.202,
+      "step": 84000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00028891661166417586,
+      "loss": 0.3089,
+      "step": 84500
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00028873201447172074,
+      "loss": 0.3093,
+      "step": 85000
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 0.2930682897567749,
+      "eval_runtime": 1.4086,
+      "eval_samples_per_second": 1560.366,
+      "eval_steps_per_second": 24.847,
+      "step": 85000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0002885459548073812,
+      "loss": 0.309,
+      "step": 85500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002883584347058758,
+      "loss": 0.3084,
+      "step": 86000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.2906832695007324,
+      "eval_runtime": 1.4896,
+      "eval_samples_per_second": 1475.535,
+      "eval_steps_per_second": 23.496,
+      "step": 86000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.00028816945621789437,
+      "loss": 0.3086,
+      "step": 86500
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.0002879790214100753,
+      "loss": 0.3086,
+      "step": 87000
+    },
+    {
+      "epoch": 2.03,
+      "eval_loss": 0.2908460795879364,
+      "eval_runtime": 1.4139,
+      "eval_samples_per_second": 1554.553,
+      "eval_steps_per_second": 24.754,
+      "step": 87000
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002877871323649833,
+      "loss": 0.3078,
+      "step": 87500
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.0002875937911810861,
+      "loss": 0.3077,
+      "step": 88000
+    },
+    {
+      "epoch": 2.05,
+      "eval_loss": 0.2881493866443634,
+      "eval_runtime": 1.4042,
+      "eval_samples_per_second": 1565.313,
+      "eval_steps_per_second": 24.925,
+      "step": 88000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.000287398999972732,
+      "loss": 0.3075,
+      "step": 88500
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00028720276087012636,
+      "loss": 0.3087,
+      "step": 89000
+    },
+    {
+      "epoch": 2.07,
+      "eval_loss": 0.2877899706363678,
+      "eval_runtime": 1.3911,
+      "eval_samples_per_second": 1580.034,
+      "eval_steps_per_second": 25.16,
+      "step": 89000
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.0002870050760193086,
+      "loss": 0.3067,
+      "step": 89500
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.00028680594758212854,
+      "loss": 0.3065,
+      "step": 90000
+    },
+    {
+      "epoch": 2.1,
+      "eval_loss": 0.2883204519748688,
+      "eval_runtime": 1.3997,
+      "eval_samples_per_second": 1570.392,
+      "eval_steps_per_second": 25.006,
+      "step": 90000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 2.555894613205093e+21,
+  "total_flos": 2.8753792549886865e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2721d72b42462f692fdf3de82485b9d24d7776a465480990b2df5c24285a8e05
+oid sha256:ac7a8dbd06b2428a64e1f1bb1794f8399c9be17660f04561ced3ff300c0d49c2
 size 102501541