Training in progress, step 290000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685baa1115c9996a6d3f73f4d770cb44301323ea5ee9d7eb0866dbaffb748894
+oid sha256:cd4094b5cac60d73fdd6f21e7e668f3210934954f13fb86e2d4209ee938a0a5a
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:866ffe9cab4eb4a4754c64cb5d7ed4f31ed0ad83e08ecaffbb7f5035db70963f
+oid sha256:d6255fd3a6ff2bf7ca5c36d99c6e77a3008adb68677e42013dd8386bb7b970a5
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69c627f38132dd40cef0053712aa1270dae63d12ac97e7fc6aaa3050230ece5f
+oid sha256:363babfb7b54265d790fbecb2309bf42f41b102f3bf25fe89de84147b11c7dfa
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff5c53b911e025186f3d4cefd2ae203cd3c867a78b103c8c95c51e8d20b5b99
+oid sha256:510c7713e00d76055c77bffa7429d1c526fc618345e8f8ea963b237765d79340
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba38210b26270fe6dc17e8687ed18c17cb3c73130918a06af7f287737355cbb7
-size 14503
+oid sha256:1ae1f30b94d6bbe49a697a2558dea2baf48ccbdc3ae096616d495689477f1d7b
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:088007f9c38eed502aa04c5f433e4da63387bd973584b94625ca26c1cb52eacf
+oid sha256:815dd65ada93eb961b018854672e652fa0d47bdfa3d615278f6e0ee59635af1b
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2014d323a6a226b752e2eff97f028102e8f8d7d7ca11f19c3f47a58b4e4654ab
-size 14439
+oid sha256:eddefbea3505d30a2cf1bb4dae32403e020f44a6c57a201cd9d6a10a92b68999
+size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:539ae7fa3d9912913294dc2719a2dd73be6f83eb9b37e29816e50a7b5d35e566
-size 14439
+oid sha256:87c32cbcd683d4257d3e7fe41cd4c20d1f40623baf6540486e5ca371ee7890e3
+size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75cd206de91cc2704e6a99c57b9e488ddcdbbc4b410b702c69de32467cde6e75
+oid sha256:3f5b8ca27148787504a99d545fbc90a1c7466702929561717fa3c00574d165ef
 size 14439

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c28314a75be0e567739244bb3713c7239bcefe683fa1af29178e1fe22d80967d
-size 14503
+oid sha256:a00f019162fc5f8994e9b1cb654b981eebf83af07e8dead098665a0f88f9319c
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80db35d9a6af0da10cd7cebe3bf01f3932293e48fc6a8607555efe3b5591e844
+oid sha256:39bc196d8aea9810b9698ff8cd04e2aeef8774f706fbd61ae0f0055bbacd0eaf
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.578694200189958,
-  "global_step": 280000,
+  "epoch": 8.885076135911026,
+  "global_step": 290000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5606,11 +5606,211 @@
       "eval_samples_per_second": 1904.885,
       "eval_steps_per_second": 30.478,
       "step": 280000
+    },
+    {
+      "epoch": 8.59,
+      "learning_rate": 0.00013777852207079235,
+      "loss": 0.3337,
+      "step": 280500
+    },
+    {
+      "epoch": 8.61,
+      "learning_rate": 0.00013730250483349825,
+      "loss": 0.3335,
+      "step": 281000
+    },
+    {
+      "epoch": 8.61,
+      "eval_loss": 0.7787224054336548,
+      "eval_runtime": 0.5159,
+      "eval_samples_per_second": 1938.186,
+      "eval_steps_per_second": 31.011,
+      "step": 281000
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 0.00013682668113317584,
+      "loss": 0.3334,
+      "step": 281500
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 0.00013635105617335703,
+      "loss": 0.3332,
+      "step": 282000
+    },
+    {
+      "epoch": 8.64,
+      "eval_loss": 0.7804464101791382,
+      "eval_runtime": 0.5024,
+      "eval_samples_per_second": 1990.477,
+      "eval_steps_per_second": 31.848,
+      "step": 282000
+    },
+    {
+      "epoch": 8.66,
+      "learning_rate": 0.00013587563515539996,
+      "loss": 0.3335,
+      "step": 282500
+    },
+    {
+      "epoch": 8.67,
+      "learning_rate": 0.00013540042327843296,
+      "loss": 0.3332,
+      "step": 283000
+    },
+    {
+      "epoch": 8.67,
+      "eval_loss": 0.7820075750350952,
+      "eval_runtime": 0.5246,
+      "eval_samples_per_second": 1906.19,
+      "eval_steps_per_second": 30.499,
+      "step": 283000
+    },
+    {
+      "epoch": 8.69,
+      "learning_rate": 0.00013492542573929678,
+      "loss": 0.3364,
+      "step": 283500
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 0.00013445064773248846,
+      "loss": 0.3349,
+      "step": 284000
+    },
+    {
+      "epoch": 8.7,
+      "eval_loss": 0.7795833349227905,
+      "eval_runtime": 0.5328,
+      "eval_samples_per_second": 1877.003,
+      "eval_steps_per_second": 30.032,
+      "step": 284000
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 0.00013397609445010432,
+      "loss": 0.3324,
+      "step": 284500
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 0.00013350177108178288,
+      "loss": 0.3322,
+      "step": 285000
+    },
+    {
+      "epoch": 8.73,
+      "eval_loss": 0.778048574924469,
+      "eval_runtime": 0.5458,
+      "eval_samples_per_second": 1832.202,
+      "eval_steps_per_second": 29.315,
+      "step": 285000
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 0.00013302768281464863,
+      "loss": 0.3325,
+      "step": 285500
+    },
+    {
+      "epoch": 8.76,
+      "learning_rate": 0.0001325538348332548,
+      "loss": 0.3328,
+      "step": 286000
+    },
+    {
+      "epoch": 8.76,
+      "eval_loss": 0.7764204144477844,
+      "eval_runtime": 0.5373,
+      "eval_samples_per_second": 1861.329,
+      "eval_steps_per_second": 29.781,
+      "step": 286000
+    },
+    {
+      "epoch": 8.78,
+      "learning_rate": 0.00013208023231952706,
+      "loss": 0.3322,
+      "step": 286500
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 0.0001316068804527066,
+      "loss": 0.3323,
+      "step": 287000
+    },
+    {
+      "epoch": 8.79,
+      "eval_loss": 0.7780716419219971,
+      "eval_runtime": 0.5287,
+      "eval_samples_per_second": 1891.289,
+      "eval_steps_per_second": 30.261,
+      "step": 287000
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 0.00013113378440929353,
+      "loss": 0.3322,
+      "step": 287500
+    },
+    {
+      "epoch": 8.82,
+      "learning_rate": 0.00013066094936299056,
+      "loss": 0.332,
+      "step": 288000
+    },
+    {
+      "epoch": 8.82,
+      "eval_loss": 0.7822167873382568,
+      "eval_runtime": 0.5284,
+      "eval_samples_per_second": 1892.53,
+      "eval_steps_per_second": 30.28,
+      "step": 288000
+    },
+    {
+      "epoch": 8.84,
+      "learning_rate": 0.00013018838048464582,
+      "loss": 0.332,
+      "step": 288500
+    },
+    {
+      "epoch": 8.85,
+      "learning_rate": 0.00012971608294219702,
+      "loss": 0.332,
+      "step": 289000
+    },
+    {
+      "epoch": 8.85,
+      "eval_loss": 0.7825139760971069,
+      "eval_runtime": 0.5164,
+      "eval_samples_per_second": 1936.526,
+      "eval_steps_per_second": 30.984,
+      "step": 289000
+    },
+    {
+      "epoch": 8.87,
+      "learning_rate": 0.00012924406190061423,
+      "loss": 0.332,
+      "step": 289500
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 0.0001287723225218441,
+      "loss": 0.3323,
+      "step": 290000
+    },
+    {
+      "epoch": 8.89,
+      "eval_loss": 0.7750741839408875,
+      "eval_runtime": 0.5106,
+      "eval_samples_per_second": 1958.426,
+      "eval_steps_per_second": 31.335,
+      "step": 290000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 8.945575982070193e+21,
+  "total_flos": 9.265063120844693e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:866ffe9cab4eb4a4754c64cb5d7ed4f31ed0ad83e08ecaffbb7f5035db70963f
+oid sha256:d6255fd3a6ff2bf7ca5c36d99c6e77a3008adb68677e42013dd8386bb7b970a5
 size 102501541