Training in progress, step 540000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a066fdd6a5e9704ab53a362123e8e6c7c6c298bbf83b96842190cb8b4fdb5ed4
+oid sha256:b1b31bd7dde490a5110587d96c397be4c71707a6ecb631cd33ee86c661a68ad1
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e668055c06ef2a443e45480e769ec8a3c102203530012d55c2e06162fb30030
+oid sha256:cbfb5da6ba6005b792e538207aa26a055cb4e4f7a70c384ed7bc2a20c6abef6f
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757fe50faf44e9ef650e7fb5e4cefb785b6f4c9135376d00e27fcccc9fdc95b6
+oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757fe50faf44e9ef650e7fb5e4cefb785b6f4c9135376d00e27fcccc9fdc95b6
+oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757fe50faf44e9ef650e7fb5e4cefb785b6f4c9135376d00e27fcccc9fdc95b6
+oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757fe50faf44e9ef650e7fb5e4cefb785b6f4c9135376d00e27fcccc9fdc95b6
+oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757fe50faf44e9ef650e7fb5e4cefb785b6f4c9135376d00e27fcccc9fdc95b6
+oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757fe50faf44e9ef650e7fb5e4cefb785b6f4c9135376d00e27fcccc9fdc95b6
+oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757fe50faf44e9ef650e7fb5e4cefb785b6f4c9135376d00e27fcccc9fdc95b6
+oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757fe50faf44e9ef650e7fb5e4cefb785b6f4c9135376d00e27fcccc9fdc95b6
+oid sha256:46cc1d313db7599b9670e587912344e79d48684e3f61295669b546552e3d818e
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286366dc95c1888d75c773db3569adfce838dc105f2552542e8252bf7ab19ebf
+oid sha256:312a9240a59bfb6f588851dc4640a2bea628ee45c54031017e35bcac8788a581
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.911022383814951,
-  "global_step": 530000,
+  "epoch": 6.0225511080378755,
+  "global_step": 540000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10606,11 +10606,211 @@
       "eval_samples_per_second": 871.683,
       "eval_steps_per_second": 13.662,
       "step": 530000
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 7.872689843543554e-05,
+      "loss": 0.208,
+      "step": 530500
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 7.861117648512725e-05,
+      "loss": 0.2078,
+      "step": 531000
+    },
+    {
+      "epoch": 5.92,
+      "eval_loss": 0.19699302315711975,
+      "eval_runtime": 2.6704,
+      "eval_samples_per_second": 860.181,
+      "eval_steps_per_second": 13.481,
+      "step": 531000
+    },
+    {
+      "epoch": 5.93,
+      "learning_rate": 7.849545833180941e-05,
+      "loss": 0.2078,
+      "step": 531500
+    },
+    {
+      "epoch": 5.93,
+      "learning_rate": 7.837974429185103e-05,
+      "loss": 0.2084,
+      "step": 532000
+    },
+    {
+      "epoch": 5.93,
+      "eval_loss": 0.19729405641555786,
+      "eval_runtime": 2.4788,
+      "eval_samples_per_second": 926.65,
+      "eval_steps_per_second": 14.523,
+      "step": 532000
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 7.82640346816099e-05,
+      "loss": 0.2078,
+      "step": 532500
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 7.814832981743164e-05,
+      "loss": 0.2075,
+      "step": 533000
+    },
+    {
+      "epoch": 5.94,
+      "eval_loss": 0.1986730396747589,
+      "eval_runtime": 2.5108,
+      "eval_samples_per_second": 914.858,
+      "eval_steps_per_second": 14.338,
+      "step": 533000
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 7.803263001564899e-05,
+      "loss": 0.2079,
+      "step": 533500
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 7.791693559258072e-05,
+      "loss": 0.2073,
+      "step": 534000
+    },
+    {
+      "epoch": 5.96,
+      "eval_loss": 0.19755910336971283,
+      "eval_runtime": 2.4538,
+      "eval_samples_per_second": 936.101,
+      "eval_steps_per_second": 14.671,
+      "step": 534000
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 7.780124686453101e-05,
+      "loss": 0.208,
+      "step": 534500
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 7.768556414778842e-05,
+      "loss": 0.2076,
+      "step": 535000
+    },
+    {
+      "epoch": 5.97,
+      "eval_loss": 0.19874924421310425,
+      "eval_runtime": 2.4792,
+      "eval_samples_per_second": 926.525,
+      "eval_steps_per_second": 14.521,
+      "step": 535000
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 7.756988775862508e-05,
+      "loss": 0.2076,
+      "step": 535500
+    },
+    {
+      "epoch": 5.98,
+      "learning_rate": 7.74542180132958e-05,
+      "loss": 0.2076,
+      "step": 536000
+    },
+    {
+      "epoch": 5.98,
+      "eval_loss": 0.1981775462627411,
+      "eval_runtime": 2.5707,
+      "eval_samples_per_second": 893.538,
+      "eval_steps_per_second": 14.004,
+      "step": 536000
+    },
+    {
+      "epoch": 5.98,
+      "learning_rate": 7.733855522803725e-05,
+      "loss": 0.2075,
+      "step": 536500
+    },
+    {
+      "epoch": 5.99,
+      "learning_rate": 7.72228997190671e-05,
+      "loss": 0.2074,
+      "step": 537000
+    },
+    {
+      "epoch": 5.99,
+      "eval_loss": 0.19704852998256683,
+      "eval_runtime": 2.4868,
+      "eval_samples_per_second": 923.663,
+      "eval_steps_per_second": 14.476,
+      "step": 537000
+    },
+    {
+      "epoch": 5.99,
+      "learning_rate": 7.710725180258306e-05,
+      "loss": 0.2077,
+      "step": 537500
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 7.699161179476217e-05,
+      "loss": 0.2073,
+      "step": 538000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.19944582879543304,
+      "eval_runtime": 2.6063,
+      "eval_samples_per_second": 881.323,
+      "eval_steps_per_second": 13.813,
+      "step": 538000
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 7.687598001175972e-05,
+      "loss": 0.2075,
+      "step": 538500
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 7.676035676970863e-05,
+      "loss": 0.207,
+      "step": 539000
+    },
+    {
+      "epoch": 6.01,
+      "eval_loss": 0.19753174483776093,
+      "eval_runtime": 2.6631,
+      "eval_samples_per_second": 862.522,
+      "eval_steps_per_second": 13.518,
+      "step": 539000
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 7.664474238471844e-05,
+      "loss": 0.2071,
+      "step": 539500
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 7.652913717287443e-05,
+      "loss": 0.2069,
+      "step": 540000
+    },
+    {
+      "epoch": 6.02,
+      "eval_loss": 0.19679389894008636,
+      "eval_runtime": 2.5175,
+      "eval_samples_per_second": 912.43,
+      "eval_steps_per_second": 14.3,
+      "step": 540000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 3.7152864523708206e+22,
+  "total_flos": 3.785381236953652e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e668055c06ef2a443e45480e769ec8a3c102203530012d55c2e06162fb30030
+oid sha256:cbfb5da6ba6005b792e538207aa26a055cb4e4f7a70c384ed7bc2a20c6abef6f
 size 449471589