Training in progress, step 90000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b383fa90f7293897c37b40f067f202019bba2c3453db8d1f328f6d7383cad678
+oid sha256:5f971e1495b95965474408a0b4cdd855e70f28b6c197542006f027ca89e6a9e5
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:485ed4a755afcfc6deaa5749cdb0f525c637fe083bc46abe1fbf43c5b6a8379e
+oid sha256:ae321af5d431bdb16494979ea9657b4f788a7b917f7196ff1444688e31808017
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
+oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
+oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
+oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
+oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
+oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
+oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
+oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf626f1c0627eaad3670cfc3c996a53c82f558d9ed75a3b6ecc98e209dc748f
+oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
 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": 2.038839900096845,
-  "global_step": 80000,
+  "epoch": 2.2936948876089507,
+  "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": 837.345,
       "eval_steps_per_second": 13.398,
       "step": 80000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.00029034050133765947,
+      "loss": 0.319,
+      "step": 80500
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00029016767524635804,
+      "loss": 0.3194,
+      "step": 81000
+    },
+    {
+      "epoch": 2.06,
+      "eval_loss": 0.851713240146637,
+      "eval_runtime": 1.28,
+      "eval_samples_per_second": 781.247,
+      "eval_steps_per_second": 12.5,
+      "step": 81000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.00028999337098301585,
+      "loss": 0.3187,
+      "step": 81500
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.0002898175904537964,
+      "loss": 0.3185,
+      "step": 82000
+    },
+    {
+      "epoch": 2.09,
+      "eval_loss": 0.8537120223045349,
+      "eval_runtime": 1.24,
+      "eval_samples_per_second": 806.425,
+      "eval_steps_per_second": 12.903,
+      "step": 82000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.0002896403355810075,
+      "loss": 0.3179,
+      "step": 82500
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00028946160830307997,
+      "loss": 0.3183,
+      "step": 83000
+    },
+    {
+      "epoch": 2.12,
+      "eval_loss": 0.8353117108345032,
+      "eval_runtime": 1.2534,
+      "eval_samples_per_second": 797.829,
+      "eval_steps_per_second": 12.765,
+      "step": 83000
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.00028928141057454665,
+      "loss": 0.3182,
+      "step": 83500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.0002890997443660211,
+      "loss": 0.3177,
+      "step": 84000
+    },
+    {
+      "epoch": 2.14,
+      "eval_loss": 0.845744252204895,
+      "eval_runtime": 1.2558,
+      "eval_samples_per_second": 796.305,
+      "eval_steps_per_second": 12.741,
+      "step": 84000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.00028891661166417586,
+      "loss": 0.3174,
+      "step": 84500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.00028873201447172074,
+      "loss": 0.3174,
+      "step": 85000
+    },
+    {
+      "epoch": 2.17,
+      "eval_loss": 0.8514609932899475,
+      "eval_runtime": 1.2468,
+      "eval_samples_per_second": 802.073,
+      "eval_steps_per_second": 12.833,
+      "step": 85000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.0002885459548073812,
+      "loss": 0.3173,
+      "step": 85500
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.0002883584347058758,
+      "loss": 0.3165,
+      "step": 86000
+    },
+    {
+      "epoch": 2.19,
+      "eval_loss": 0.8357125520706177,
+      "eval_runtime": 1.221,
+      "eval_samples_per_second": 818.991,
+      "eval_steps_per_second": 13.104,
+      "step": 86000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.00028816945621789437,
+      "loss": 0.3166,
+      "step": 86500
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.0002879790214100753,
+      "loss": 0.3164,
+      "step": 87000
+    },
+    {
+      "epoch": 2.22,
+      "eval_loss": 0.855523943901062,
+      "eval_runtime": 1.2726,
+      "eval_samples_per_second": 785.803,
+      "eval_steps_per_second": 12.573,
+      "step": 87000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.0002877871323649833,
+      "loss": 0.3161,
+      "step": 87500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.0002875937911810861,
+      "loss": 0.3159,
+      "step": 88000
+    },
+    {
+      "epoch": 2.24,
+      "eval_loss": 0.842631995677948,
+      "eval_runtime": 1.2074,
+      "eval_samples_per_second": 828.219,
+      "eval_steps_per_second": 13.252,
+      "step": 88000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.000287398999972732,
+      "loss": 0.3159,
+      "step": 88500
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00028720276087012636,
+      "loss": 0.3159,
+      "step": 89000
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 0.8528951406478882,
+      "eval_runtime": 1.2566,
+      "eval_samples_per_second": 795.823,
+      "eval_steps_per_second": 12.733,
+      "step": 89000
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.0002870050760193086,
+      "loss": 0.3152,
+      "step": 89500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.00028680594758212854,
+      "loss": 0.3152,
+      "step": 90000
+    },
+    {
+      "epoch": 2.29,
+      "eval_loss": 0.8297361135482788,
+      "eval_runtime": 1.2298,
+      "eval_samples_per_second": 813.129,
+      "eval_steps_per_second": 13.01,
+      "step": 90000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 2.55587015236991e+21,
+  "total_flos": 2.87535729114441e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:485ed4a755afcfc6deaa5749cdb0f525c637fe083bc46abe1fbf43c5b6a8379e
+oid sha256:ae321af5d431bdb16494979ea9657b4f788a7b917f7196ff1444688e31808017
 size 102501541