Training in progress, step 180000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc6f5d0449da50e2cc178c56f0e5de3d9f88d8ba722efcdb1f6188454b553e22
+oid sha256:b8eebb295812a5e59b8cc81c26f38269a2b08ced33ac052f5cd4b925818f5ad7
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e0f44d78ff097181ae8441a089b275ece4c97622c0f5c7587605e9e7d19737
+oid sha256:2cad91391dc5d3c8f6ec4db59f2a7b1f5a82dacf011d8f90595ac52d0f99d9d8
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e61023e8d171758eb1851c2dca065b3b4d1e98a59027f5bdb640bf8eb98fa6f
+oid sha256:90eeea7f53a505f798ef8d829ace86d5cfaf983bbaaec27adfb70669887b824d
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b64255aa592b9d206efeb4577b9c6b7df5320bd933e617956ce1c675107a415
+oid sha256:661c5515c8356a401fd066b8dfe773c64b8d80125a03d5ce30709a3a7883c490
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:885fd282adb654e89ef66a92709e88aab4f0c584a17a4cbfb5ebf16374496376
+oid sha256:91d12617c44eee325f10a9bfc4a4d50be13d022c2f2b636ad533f25275cb2ce6
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfaf0569d98d355fd70668555295332869b7ffa6e14952c0ef72cfde1dbd629a
-size 14503
+oid sha256:9cf7bfc913575f8c458dbba1253c52eaa4a215c1e077041531924e651fe1b687
+size 14439

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96029aa06b1935a10dfce1bed30d34ba04f61d40b2a8befc2769e091b87f28e5
-size 14503
+oid sha256:e827d4a09db28f6f15911529cb7e65d53bf0d6e77e09abaca568307ff57a5e8d
+size 14439

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4b2741991356fdb15912c79a307dff530c6b8b5d2252839754c83a35c2164c
-size 14439
+oid sha256:3ce0c65fe2433cee8a1d4fc61a73546de1da6376b2797efc2e963c2e94a2a3d4
+size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45081d24452eda5a69c322cf4e1e913186e00e4b3904cdcafaec9818bc1f8ab5
-size 14439
+oid sha256:0f6c93cf27841b4116537c16edba24b72b1b9aa431a487c8e03a40b2f1160bf8
+size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2816e0ff915d56b8cb135a91b32566ace701bc153a7f1c90580eff5060941e1f
+oid sha256:93072fbc8e9c76b2b9e666aaadf09c064512ce4d01764f763a49ebfaf01f5177
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2861f0d820018c213fdc57cc6eebc5c8df9d5485c4072b9ac9a4ac6f902e69
+oid sha256:7a265c146087c7b525f93e19ac9e51ad44bfb6af09ebd3ea4e38ee99de52c725
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.208492907258188,
-  "global_step": 170000,
+  "epoch": 5.514874842979258,
+  "global_step": 180000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3406,11 +3406,211 @@
       "eval_samples_per_second": 1892.002,
       "eval_steps_per_second": 30.272,
       "step": 170000
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 0.0002378846657362306,
+      "loss": 0.3518,
+      "step": 170500
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 0.00023749076897000928,
+      "loss": 0.3518,
+      "step": 171000
+    },
+    {
+      "epoch": 5.24,
+      "eval_loss": 0.7876036167144775,
+      "eval_runtime": 0.5137,
+      "eval_samples_per_second": 1946.703,
+      "eval_steps_per_second": 31.147,
+      "step": 171000
+    },
+    {
+      "epoch": 5.25,
+      "learning_rate": 0.00023709597009795465,
+      "loss": 0.3517,
+      "step": 171500
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 0.000236700273437524,
+      "loss": 0.3515,
+      "step": 172000
+    },
+    {
+      "epoch": 5.27,
+      "eval_loss": 0.780876100063324,
+      "eval_runtime": 0.5145,
+      "eval_samples_per_second": 1943.544,
+      "eval_steps_per_second": 31.097,
+      "step": 172000
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 0.0002363036833159925,
+      "loss": 0.3509,
+      "step": 172500
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 0.00023590620407040633,
+      "loss": 0.351,
+      "step": 173000
+    },
+    {
+      "epoch": 5.3,
+      "eval_loss": 0.7936240434646606,
+      "eval_runtime": 0.5234,
+      "eval_samples_per_second": 1910.641,
+      "eval_steps_per_second": 30.57,
+      "step": 173000
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 0.00023550784004753471,
+      "loss": 0.3512,
+      "step": 173500
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 0.0002351085956038229,
+      "loss": 0.3508,
+      "step": 174000
+    },
+    {
+      "epoch": 5.33,
+      "eval_loss": 0.7791932225227356,
+      "eval_runtime": 0.5202,
+      "eval_samples_per_second": 1922.513,
+      "eval_steps_per_second": 30.76,
+      "step": 174000
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 0.00023470847510534407,
+      "loss": 0.3507,
+      "step": 174500
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 0.00023430748292775188,
+      "loss": 0.3508,
+      "step": 175000
+    },
+    {
+      "epoch": 5.36,
+      "eval_loss": 0.783431887626648,
+      "eval_runtime": 0.5231,
+      "eval_samples_per_second": 1911.723,
+      "eval_steps_per_second": 30.588,
+      "step": 175000
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 0.0002339056234562326,
+      "loss": 0.3505,
+      "step": 175500
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 0.00023350290108545694,
+      "loss": 0.3505,
+      "step": 176000
+    },
+    {
+      "epoch": 5.39,
+      "eval_loss": 0.787056028842926,
+      "eval_runtime": 0.5298,
+      "eval_samples_per_second": 1887.522,
+      "eval_steps_per_second": 30.2,
+      "step": 176000
+    },
+    {
+      "epoch": 5.41,
+      "learning_rate": 0.00023309932021953238,
+      "loss": 0.3502,
+      "step": 176500
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 0.00023269488527195446,
+      "loss": 0.3504,
+      "step": 177000
+    },
+    {
+      "epoch": 5.42,
+      "eval_loss": 0.7937799692153931,
+      "eval_runtime": 0.5254,
+      "eval_samples_per_second": 1903.32,
+      "eval_steps_per_second": 30.453,
+      "step": 177000
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 0.00023228960066555907,
+      "loss": 0.3515,
+      "step": 177500
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 0.00023188347083247365,
+      "loss": 0.3499,
+      "step": 178000
+    },
+    {
+      "epoch": 5.45,
+      "eval_loss": 0.7750864028930664,
+      "eval_runtime": 0.5058,
+      "eval_samples_per_second": 1977.117,
+      "eval_steps_per_second": 31.634,
+      "step": 178000
+    },
+    {
+      "epoch": 5.47,
+      "learning_rate": 0.00023147650021406905,
+      "loss": 0.3502,
+      "step": 178500
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 0.00023106869326091075,
+      "loss": 0.3493,
+      "step": 179000
+    },
+    {
+      "epoch": 5.48,
+      "eval_loss": 0.7836278080940247,
+      "eval_runtime": 0.5246,
+      "eval_samples_per_second": 1906.272,
+      "eval_steps_per_second": 30.5,
+      "step": 179000
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 0.00023066005443271017,
+      "loss": 0.3496,
+      "step": 179500
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 0.00023025058819827618,
+      "loss": 0.349,
+      "step": 180000
+    },
+    {
+      "epoch": 5.51,
+      "eval_loss": 0.7845665216445923,
+      "eval_runtime": 0.5357,
+      "eval_samples_per_second": 1866.879,
+      "eval_steps_per_second": 29.87,
+      "step": 180000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 5.431241419406621e+21,
+  "total_flos": 5.750728558181121e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e0f44d78ff097181ae8441a089b275ece4c97622c0f5c7587605e9e7d19737
+oid sha256:2cad91391dc5d3c8f6ec4db59f2a7b1f5a82dacf011d8f90595ac52d0f99d9d8
 size 102501541