Training in progress, step 170000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7fa6f67a02b92595e2aff826fe56cab9b750c0aa9eed74a0c077457f9526a38
+oid sha256:dc6f5d0449da50e2cc178c56f0e5de3d9f88d8ba722efcdb1f6188454b553e22
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377f17dd91bef1f8d76bf027ee815cc42fde00afa68776f28a01f3707681243e
+oid sha256:72e0f44d78ff097181ae8441a089b275ece4c97622c0f5c7587605e9e7d19737
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9987290a679306f1b084feec0755691092b1d64ddfc7e54de33d1d15f38b37c5
+oid sha256:6e61023e8d171758eb1851c2dca065b3b4d1e98a59027f5bdb640bf8eb98fa6f
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3930873c7aebc048e1e6b5707a188d1d16da050c73fd5a40451efe67b05447a
+oid sha256:4b64255aa592b9d206efeb4577b9c6b7df5320bd933e617956ce1c675107a415
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e66b144627191cd9907774cddaa716b9a3469498c3635098f787cc03994045a
+oid sha256:885fd282adb654e89ef66a92709e88aab4f0c584a17a4cbfb5ebf16374496376
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:467cacbc42e6b7a1aca96dfbbc644355c389f0ee7689457651e4e2a25df79552
+oid sha256:dfaf0569d98d355fd70668555295332869b7ffa6e14952c0ef72cfde1dbd629a
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62dfde7cdd3982ed20c005df1890f27c27f2ad9af1961cd883bd47b05ccd4020
-size 14439
+oid sha256:96029aa06b1935a10dfce1bed30d34ba04f61d40b2a8befc2769e091b87f28e5
+size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcbb58a56a3d2cf5b2ed3ab5c08c634b6d8951e1d9246f641494be97ef58199d
-size 14503
+oid sha256:8f4b2741991356fdb15912c79a307dff530c6b8b5d2252839754c83a35c2164c
+size 14439

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ae31e4239cb266a5df3399c9d9ccb8e2372ff9d2c418e64e941930de1c56237
-size 14503
+oid sha256:45081d24452eda5a69c322cf4e1e913186e00e4b3904cdcafaec9818bc1f8ab5
+size 14439

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c129c447b52f4655050576e211e6a16cffe6c0990663b13474ab0efd7745497f
+oid sha256:2816e0ff915d56b8cb135a91b32566ace701bc153a7f1c90580eff5060941e1f
 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": 4.902110971537118,
-  "global_step": 160000,
+  "epoch": 5.208492907258188,
+  "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": 1926.096,
       "eval_steps_per_second": 30.818,
       "step": 160000
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 0.0002455665988827021,
+      "loss": 0.3542,
+      "step": 160500
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 0.0002451916353649261,
+      "loss": 0.3538,
+      "step": 161000
+    },
+    {
+      "epoch": 4.93,
+      "eval_loss": 0.7811290621757507,
+      "eval_runtime": 0.5184,
+      "eval_samples_per_second": 1929.028,
+      "eval_steps_per_second": 30.864,
+      "step": 161000
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 0.00024481568552587566,
+      "loss": 0.3539,
+      "step": 161500
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 0.0002444387534768781,
+      "loss": 0.3544,
+      "step": 162000
+    },
+    {
+      "epoch": 4.96,
+      "eval_loss": 0.7849481105804443,
+      "eval_runtime": 0.5349,
+      "eval_samples_per_second": 1869.494,
+      "eval_steps_per_second": 29.912,
+      "step": 162000
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 0.0002440608433400018,
+      "loss": 0.354,
+      "step": 162500
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 0.00024368195924801158,
+      "loss": 0.3537,
+      "step": 163000
+    },
+    {
+      "epoch": 4.99,
+      "eval_loss": 0.7821019887924194,
+      "eval_runtime": 0.5319,
+      "eval_samples_per_second": 1880.027,
+      "eval_steps_per_second": 30.08,
+      "step": 163000
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.00024330210534432314,
+      "loss": 0.3544,
+      "step": 163500
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.0002429212857829579,
+      "loss": 0.3535,
+      "step": 164000
+    },
+    {
+      "epoch": 5.02,
+      "eval_loss": 0.7799093127250671,
+      "eval_runtime": 0.5175,
+      "eval_samples_per_second": 1932.464,
+      "eval_steps_per_second": 30.919,
+      "step": 164000
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 0.00024253950472849758,
+      "loss": 0.3529,
+      "step": 164500
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 0.0002421567663560386,
+      "loss": 0.353,
+      "step": 165000
+    },
+    {
+      "epoch": 5.06,
+      "eval_loss": 0.787077784538269,
+      "eval_runtime": 0.5165,
+      "eval_samples_per_second": 1936.126,
+      "eval_steps_per_second": 30.978,
+      "step": 165000
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 0.00024177307485114653,
+      "loss": 0.3535,
+      "step": 165500
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 0.0002413884344098101,
+      "loss": 0.3528,
+      "step": 166000
+    },
+    {
+      "epoch": 5.09,
+      "eval_loss": 0.7880011200904846,
+      "eval_runtime": 0.5056,
+      "eval_samples_per_second": 1977.97,
+      "eval_steps_per_second": 31.648,
+      "step": 166000
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 0.00024100284923839568,
+      "loss": 0.3529,
+      "step": 166500
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 0.0002406163235536008,
+      "loss": 0.3528,
+      "step": 167000
+    },
+    {
+      "epoch": 5.12,
+      "eval_loss": 0.7795886397361755,
+      "eval_runtime": 0.5086,
+      "eval_samples_per_second": 1966.255,
+      "eval_steps_per_second": 31.46,
+      "step": 167000
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 0.00024022886158240857,
+      "loss": 0.3526,
+      "step": 167500
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 0.0002398404675620409,
+      "loss": 0.353,
+      "step": 168000
+    },
+    {
+      "epoch": 5.15,
+      "eval_loss": 0.7831447124481201,
+      "eval_runtime": 0.5186,
+      "eval_samples_per_second": 1928.417,
+      "eval_steps_per_second": 30.855,
+      "step": 168000
+    },
+    {
+      "epoch": 5.16,
+      "learning_rate": 0.0002394511457399126,
+      "loss": 0.3524,
+      "step": 168500
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 0.00023906090037358478,
+      "loss": 0.3519,
+      "step": 169000
+    },
+    {
+      "epoch": 5.18,
+      "eval_loss": 0.7807596325874329,
+      "eval_runtime": 0.5293,
+      "eval_samples_per_second": 1889.214,
+      "eval_steps_per_second": 30.227,
+      "step": 169000
+    },
+    {
+      "epoch": 5.19,
+      "learning_rate": 0.0002386697357307182,
+      "loss": 0.3519,
+      "step": 169500
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 0.00023827765608902676,
+      "loss": 0.3517,
+      "step": 170000
+    },
+    {
+      "epoch": 5.21,
+      "eval_loss": 0.7891790866851807,
+      "eval_runtime": 0.5285,
+      "eval_samples_per_second": 1892.002,
+      "eval_steps_per_second": 30.272,
+      "step": 170000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 5.111762268584097e+21,
+  "total_flos": 5.431241419406621e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377f17dd91bef1f8d76bf027ee815cc42fde00afa68776f28a01f3707681243e
+oid sha256:72e0f44d78ff097181ae8441a089b275ece4c97622c0f5c7587605e9e7d19737
 size 102501541