Training in progress, step 90000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:777cbc08cf00d2034da503c2311badc12f52c886a74e063f2bdcca4a39f3860a
+oid sha256:8708ec97bce87427113cb3bf6905b9f810ab82b123d12fcc544222cdb26d7419
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32adc1e9533dfb979bd9b242f566145bd80a023bab65cedd4ce88ac7bfc33308
+oid sha256:7c23665c6fffdc38b76419cd527f6c3457b01f06daed5d2205a211e3813eb63a
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9543caaad5def051a5eb368861a91fecf7f5eb37053f95ab1319e7b8e7847f9d
+oid sha256:64aad1e6af6d427ce850c7d412d4cc63c4e57d6cd729c08dece84a7254b2ab10
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9543caaad5def051a5eb368861a91fecf7f5eb37053f95ab1319e7b8e7847f9d
+oid sha256:64aad1e6af6d427ce850c7d412d4cc63c4e57d6cd729c08dece84a7254b2ab10
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9543caaad5def051a5eb368861a91fecf7f5eb37053f95ab1319e7b8e7847f9d
+oid sha256:64aad1e6af6d427ce850c7d412d4cc63c4e57d6cd729c08dece84a7254b2ab10
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9543caaad5def051a5eb368861a91fecf7f5eb37053f95ab1319e7b8e7847f9d
+oid sha256:64aad1e6af6d427ce850c7d412d4cc63c4e57d6cd729c08dece84a7254b2ab10
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9543caaad5def051a5eb368861a91fecf7f5eb37053f95ab1319e7b8e7847f9d
+oid sha256:64aad1e6af6d427ce850c7d412d4cc63c4e57d6cd729c08dece84a7254b2ab10
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9543caaad5def051a5eb368861a91fecf7f5eb37053f95ab1319e7b8e7847f9d
+oid sha256:64aad1e6af6d427ce850c7d412d4cc63c4e57d6cd729c08dece84a7254b2ab10
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9543caaad5def051a5eb368861a91fecf7f5eb37053f95ab1319e7b8e7847f9d
+oid sha256:64aad1e6af6d427ce850c7d412d4cc63c4e57d6cd729c08dece84a7254b2ab10
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9543caaad5def051a5eb368861a91fecf7f5eb37053f95ab1319e7b8e7847f9d
+oid sha256:64aad1e6af6d427ce850c7d412d4cc63c4e57d6cd729c08dece84a7254b2ab10
 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": 1.7844396859386151,
-  "global_step": 80000,
+  "epoch": 2.007494646680942,
+  "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": 1185.314,
       "eval_steps_per_second": 18.577,
       "step": 80000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00029034050133765947,
+      "loss": 0.3149,
+      "step": 80500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00029016767524635804,
+      "loss": 0.3145,
+      "step": 81000
+    },
+    {
+      "epoch": 1.81,
+      "eval_loss": 0.2963857054710388,
+      "eval_runtime": 1.9198,
+      "eval_samples_per_second": 1196.488,
+      "eval_steps_per_second": 18.752,
+      "step": 81000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00028999337098301585,
+      "loss": 0.3144,
+      "step": 81500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.0002898175904537964,
+      "loss": 0.314,
+      "step": 82000
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 0.295415997505188,
+      "eval_runtime": 1.9531,
+      "eval_samples_per_second": 1176.079,
+      "eval_steps_per_second": 18.432,
+      "step": 82000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.0002896403355810075,
+      "loss": 0.3135,
+      "step": 82500
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00028946160830307997,
+      "loss": 0.3135,
+      "step": 83000
+    },
+    {
+      "epoch": 1.85,
+      "eval_loss": 0.2971150577068329,
+      "eval_runtime": 2.0357,
+      "eval_samples_per_second": 1128.362,
+      "eval_steps_per_second": 17.684,
+      "step": 83000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00028928141057454665,
+      "loss": 0.3136,
+      "step": 83500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002890997443660211,
+      "loss": 0.3127,
+      "step": 84000
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 0.2954028248786926,
+      "eval_runtime": 2.0203,
+      "eval_samples_per_second": 1136.969,
+      "eval_steps_per_second": 17.819,
+      "step": 84000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00028891661166417586,
+      "loss": 0.3126,
+      "step": 84500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00028873201447172074,
+      "loss": 0.3125,
+      "step": 85000
+    },
+    {
+      "epoch": 1.9,
+      "eval_loss": 0.2963060438632965,
+      "eval_runtime": 1.9991,
+      "eval_samples_per_second": 1149.017,
+      "eval_steps_per_second": 18.008,
+      "step": 85000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0002885459548073812,
+      "loss": 0.3124,
+      "step": 85500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0002883584347058758,
+      "loss": 0.3122,
+      "step": 86000
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.2932322025299072,
+      "eval_runtime": 1.9426,
+      "eval_samples_per_second": 1182.434,
+      "eval_steps_per_second": 18.532,
+      "step": 86000
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00028816945621789437,
+      "loss": 0.3121,
+      "step": 86500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.0002879790214100753,
+      "loss": 0.3119,
+      "step": 87000
+    },
+    {
+      "epoch": 1.94,
+      "eval_loss": 0.29384109377861023,
+      "eval_runtime": 1.9978,
+      "eval_samples_per_second": 1149.741,
+      "eval_steps_per_second": 18.019,
+      "step": 87000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0002877871323649833,
+      "loss": 0.3115,
+      "step": 87500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.0002875937911810861,
+      "loss": 0.3111,
+      "step": 88000
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 0.29092082381248474,
+      "eval_runtime": 1.9165,
+      "eval_samples_per_second": 1198.512,
+      "eval_steps_per_second": 18.784,
+      "step": 88000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.000287398999972732,
+      "loss": 0.3107,
+      "step": 88500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00028720276087012636,
+      "loss": 0.3107,
+      "step": 89000
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 0.2925170063972473,
+      "eval_runtime": 1.9863,
+      "eval_samples_per_second": 1156.436,
+      "eval_steps_per_second": 18.124,
+      "step": 89000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002870050760193086,
+      "loss": 0.3103,
+      "step": 89500
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.00028680594758212854,
+      "loss": 0.3105,
+      "step": 90000
+    },
+    {
+      "epoch": 2.01,
+      "eval_loss": 0.2921919524669647,
+      "eval_runtime": 2.0098,
+      "eval_samples_per_second": 1142.913,
+      "eval_steps_per_second": 17.912,
+      "step": 90000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 2.5558686559345847e+21,
+  "total_flos": 2.8753273404476694e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32adc1e9533dfb979bd9b242f566145bd80a023bab65cedd4ce88ac7bfc33308
+oid sha256:7c23665c6fffdc38b76419cd527f6c3457b01f06daed5d2205a211e3813eb63a
 size 102501541