Training in progress, step 170000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bfe26318a498d7159440a97f6aa88e178fd8cfca07f0e3c0f2baa3c80edd1cc
+oid sha256:fc237dbddbbf9460161ce6eb75bbbd2e7ecdff21b202e0e7a13cc25fb9c09b56
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30edd70a79d1324bf23d2b4cd2aadc6dcc51387b691e7868236c4f9d83750ba9
+oid sha256:3cfb247d98c5022356a7b59a271aff04531b844ba1be46c0e78cb0cfe119fbac
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
+oid sha256:5acce959199fb05e4e1101efd27f7a7ab8e3aea0ddea43b3703666db4d3d6f88
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
+oid sha256:5acce959199fb05e4e1101efd27f7a7ab8e3aea0ddea43b3703666db4d3d6f88
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
+oid sha256:5acce959199fb05e4e1101efd27f7a7ab8e3aea0ddea43b3703666db4d3d6f88
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
+oid sha256:5acce959199fb05e4e1101efd27f7a7ab8e3aea0ddea43b3703666db4d3d6f88
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
+oid sha256:5acce959199fb05e4e1101efd27f7a7ab8e3aea0ddea43b3703666db4d3d6f88
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
+oid sha256:5acce959199fb05e4e1101efd27f7a7ab8e3aea0ddea43b3703666db4d3d6f88
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
+oid sha256:5acce959199fb05e4e1101efd27f7a7ab8e3aea0ddea43b3703666db4d3d6f88
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
+oid sha256:5acce959199fb05e4e1101efd27f7a7ab8e3aea0ddea43b3703666db4d3d6f88
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc0c53c979a7805930dacd44e26c88894a437860c12a8b9fd2b0695ce7c583e
+oid sha256:fd2861f0d820018c213fdc57cc6eebc5c8df9d5485c4072b9ac9a4ac6f902e69
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.7279526550012814,
-  "global_step": 160000,
+  "epoch": 3.9609496959388615,
+  "global_step": 170000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3206,11 +3206,211 @@
       "eval_samples_per_second": 1521.168,
       "eval_steps_per_second": 24.222,
       "step": 160000
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 0.0002455665988827021,
+      "loss": 0.2869,
+      "step": 160500
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.0002451916353649261,
+      "loss": 0.287,
+      "step": 161000
+    },
+    {
+      "epoch": 3.75,
+      "eval_loss": 0.27171802520751953,
+      "eval_runtime": 1.4254,
+      "eval_samples_per_second": 1542.077,
+      "eval_steps_per_second": 24.555,
+      "step": 161000
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 0.00024481568552587566,
+      "loss": 0.2871,
+      "step": 161500
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 0.0002444387534768781,
+      "loss": 0.2868,
+      "step": 162000
+    },
+    {
+      "epoch": 3.77,
+      "eval_loss": 0.26901960372924805,
+      "eval_runtime": 1.4243,
+      "eval_samples_per_second": 1543.244,
+      "eval_steps_per_second": 24.574,
+      "step": 162000
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 0.0002440608433400018,
+      "loss": 0.2869,
+      "step": 162500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 0.00024368195924801158,
+      "loss": 0.2869,
+      "step": 163000
+    },
+    {
+      "epoch": 3.8,
+      "eval_loss": 0.26863837242126465,
+      "eval_runtime": 1.4601,
+      "eval_samples_per_second": 1505.401,
+      "eval_steps_per_second": 23.971,
+      "step": 163000
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.00024330210534432314,
+      "loss": 0.2862,
+      "step": 163500
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 0.0002429212857829579,
+      "loss": 0.286,
+      "step": 164000
+    },
+    {
+      "epoch": 3.82,
+      "eval_loss": 0.26618143916130066,
+      "eval_runtime": 1.4166,
+      "eval_samples_per_second": 1551.57,
+      "eval_steps_per_second": 24.707,
+      "step": 164000
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 0.00024253950472849758,
+      "loss": 0.2863,
+      "step": 164500
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 0.0002421567663560386,
+      "loss": 0.286,
+      "step": 165000
+    },
+    {
+      "epoch": 3.84,
+      "eval_loss": 0.26967230439186096,
+      "eval_runtime": 1.4363,
+      "eval_samples_per_second": 1530.302,
+      "eval_steps_per_second": 24.368,
+      "step": 165000
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 0.00024177307485114653,
+      "loss": 0.2864,
+      "step": 165500
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 0.0002413884344098101,
+      "loss": 0.2859,
+      "step": 166000
+    },
+    {
+      "epoch": 3.87,
+      "eval_loss": 0.270435631275177,
+      "eval_runtime": 1.4339,
+      "eval_samples_per_second": 1532.847,
+      "eval_steps_per_second": 24.408,
+      "step": 166000
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 0.00024100284923839568,
+      "loss": 0.2855,
+      "step": 166500
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 0.0002406163235536008,
+      "loss": 0.2858,
+      "step": 167000
+    },
+    {
+      "epoch": 3.89,
+      "eval_loss": 0.26777446269989014,
+      "eval_runtime": 1.4287,
+      "eval_samples_per_second": 1538.493,
+      "eval_steps_per_second": 24.498,
+      "step": 167000
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.00024022886158240857,
+      "loss": 0.2856,
+      "step": 167500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 0.0002398404675620409,
+      "loss": 0.2854,
+      "step": 168000
+    },
+    {
+      "epoch": 3.91,
+      "eval_loss": 0.2669973075389862,
+      "eval_runtime": 1.4303,
+      "eval_samples_per_second": 1536.724,
+      "eval_steps_per_second": 24.47,
+      "step": 168000
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 0.0002394511457399126,
+      "loss": 0.2858,
+      "step": 168500
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 0.00023906090037358478,
+      "loss": 0.2853,
+      "step": 169000
+    },
+    {
+      "epoch": 3.94,
+      "eval_loss": 0.2690945863723755,
+      "eval_runtime": 1.4107,
+      "eval_samples_per_second": 1558.141,
+      "eval_steps_per_second": 24.811,
+      "step": 169000
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 0.0002386697357307182,
+      "loss": 0.285,
+      "step": 169500
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 0.00023827765608902676,
+      "loss": 0.2849,
+      "step": 170000
+    },
+    {
+      "epoch": 3.96,
+      "eval_loss": 0.2683064937591553,
+      "eval_runtime": 1.4268,
+      "eval_samples_per_second": 1540.527,
+      "eval_steps_per_second": 24.531,
+      "step": 170000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 5.11178672941928e+21,
+  "total_flos": 5.43127386819378e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30edd70a79d1324bf23d2b4cd2aadc6dcc51387b691e7868236c4f9d83750ba9
+oid sha256:3cfb247d98c5022356a7b59a271aff04531b844ba1be46c0e78cb0cfe119fbac
 size 102501541