Training in progress, step 410000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b700ebc6fc16103b0c351577b0fe7b7a9955520a42d8ff4c426cb4c02c884230
+oid sha256:e1baf6720e03a80bba42f160ede8ecbec1168817e98171665a299ded4d992a3a
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6331caf84d401728c3e2540374852d6e489eae28c3099656d3c86fe297980cc4
+oid sha256:db26ab4777ecfb64dd27c707c9cfebcf74d431f5c02f5554c247500eee4a57f0
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418af87c326448c49979f76acb65b2fcea72841274341c16e51b4a9d24a0c8ee
+oid sha256:60abe9bac7f0fc7b8ccd2d34e905c6889ebea4f84a53f5f1e4a7b1ee92473794
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418af87c326448c49979f76acb65b2fcea72841274341c16e51b4a9d24a0c8ee
+oid sha256:60abe9bac7f0fc7b8ccd2d34e905c6889ebea4f84a53f5f1e4a7b1ee92473794
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418af87c326448c49979f76acb65b2fcea72841274341c16e51b4a9d24a0c8ee
+oid sha256:60abe9bac7f0fc7b8ccd2d34e905c6889ebea4f84a53f5f1e4a7b1ee92473794
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418af87c326448c49979f76acb65b2fcea72841274341c16e51b4a9d24a0c8ee
+oid sha256:60abe9bac7f0fc7b8ccd2d34e905c6889ebea4f84a53f5f1e4a7b1ee92473794
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418af87c326448c49979f76acb65b2fcea72841274341c16e51b4a9d24a0c8ee
+oid sha256:60abe9bac7f0fc7b8ccd2d34e905c6889ebea4f84a53f5f1e4a7b1ee92473794
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418af87c326448c49979f76acb65b2fcea72841274341c16e51b4a9d24a0c8ee
+oid sha256:60abe9bac7f0fc7b8ccd2d34e905c6889ebea4f84a53f5f1e4a7b1ee92473794
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418af87c326448c49979f76acb65b2fcea72841274341c16e51b4a9d24a0c8ee
+oid sha256:60abe9bac7f0fc7b8ccd2d34e905c6889ebea4f84a53f5f1e4a7b1ee92473794
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418af87c326448c49979f76acb65b2fcea72841274341c16e51b4a9d24a0c8ee
+oid sha256:60abe9bac7f0fc7b8ccd2d34e905c6889ebea4f84a53f5f1e4a7b1ee92473794
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ba83cbca80cb672828600b248dd69c4c050beb355cdcf7faf0b56212421edca
+oid sha256:498c95fdcab578849c69bf4a10f0532f5bf3ba8048fa37c1b416b3afd0ea5f33
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.319881637503205,
-  "global_step": 400000,
+  "epoch": 9.552878678440784,
+  "global_step": 410000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8006,11 +8006,211 @@
       "eval_samples_per_second": 1555.592,
       "eval_steps_per_second": 24.771,
       "step": 400000
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 4.0280733510303475e-05,
+      "loss": 0.2558,
+      "step": 400500
+    },
+    {
+      "epoch": 9.34,
+      "learning_rate": 3.9988095434602716e-05,
+      "loss": 0.2555,
+      "step": 401000
+    },
+    {
+      "epoch": 9.34,
+      "eval_loss": 0.2393871247768402,
+      "eval_runtime": 1.4557,
+      "eval_samples_per_second": 1509.958,
+      "eval_steps_per_second": 24.044,
+      "step": 401000
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 3.9696715110663726e-05,
+      "loss": 0.2557,
+      "step": 401500
+    },
+    {
+      "epoch": 9.37,
+      "learning_rate": 3.9406595724975116e-05,
+      "loss": 0.2553,
+      "step": 402000
+    },
+    {
+      "epoch": 9.37,
+      "eval_loss": 0.2388046830892563,
+      "eval_runtime": 1.444,
+      "eval_samples_per_second": 1522.119,
+      "eval_steps_per_second": 24.238,
+      "step": 402000
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 3.9117740450235914e-05,
+      "loss": 0.2555,
+      "step": 402500
+    },
+    {
+      "epoch": 9.39,
+      "learning_rate": 3.8830152445321163e-05,
+      "loss": 0.2553,
+      "step": 403000
+    },
+    {
+      "epoch": 9.39,
+      "eval_loss": 0.23731090128421783,
+      "eval_runtime": 1.5043,
+      "eval_samples_per_second": 1461.141,
+      "eval_steps_per_second": 23.267,
+      "step": 403000
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 3.854383485524724e-05,
+      "loss": 0.2553,
+      "step": 403500
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 3.8258790811137425e-05,
+      "loss": 0.2553,
+      "step": 404000
+    },
+    {
+      "epoch": 9.41,
+      "eval_loss": 0.2364571988582611,
+      "eval_runtime": 1.4662,
+      "eval_samples_per_second": 1499.102,
+      "eval_steps_per_second": 23.871,
+      "step": 404000
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 3.7975023430187676e-05,
+      "loss": 0.2552,
+      "step": 404500
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 3.7692535815632624e-05,
+      "loss": 0.2555,
+      "step": 405000
+    },
+    {
+      "epoch": 9.44,
+      "eval_loss": 0.23983800411224365,
+      "eval_runtime": 1.4385,
+      "eval_samples_per_second": 1527.964,
+      "eval_steps_per_second": 24.331,
+      "step": 405000
+    },
+    {
+      "epoch": 9.45,
+      "learning_rate": 3.741133105671159e-05,
+      "loss": 0.2554,
+      "step": 405500
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 3.713141222863474e-05,
+      "loss": 0.2553,
+      "step": 406000
+    },
+    {
+      "epoch": 9.46,
+      "eval_loss": 0.23924601078033447,
+      "eval_runtime": 1.4347,
+      "eval_samples_per_second": 1532.043,
+      "eval_steps_per_second": 24.396,
+      "step": 406000
+    },
+    {
+      "epoch": 9.47,
+      "learning_rate": 3.6852782392549584e-05,
+      "loss": 0.2556,
+      "step": 406500
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 3.657544459550729e-05,
+      "loss": 0.255,
+      "step": 407000
+    },
+    {
+      "epoch": 9.48,
+      "eval_loss": 0.23706746101379395,
+      "eval_runtime": 1.4741,
+      "eval_samples_per_second": 1491.033,
+      "eval_steps_per_second": 23.743,
+      "step": 407000
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 3.6299401870429606e-05,
+      "loss": 0.2549,
+      "step": 407500
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 3.6024657236075546e-05,
+      "loss": 0.2548,
+      "step": 408000
+    },
+    {
+      "epoch": 9.51,
+      "eval_loss": 0.23815912008285522,
+      "eval_runtime": 1.4566,
+      "eval_samples_per_second": 1508.999,
+      "eval_steps_per_second": 24.029,
+      "step": 408000
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 3.575121369700841e-05,
+      "loss": 0.2549,
+      "step": 408500
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 3.5479074243562995e-05,
+      "loss": 0.2548,
+      "step": 409000
+    },
+    {
+      "epoch": 9.53,
+      "eval_loss": 0.23738771677017212,
+      "eval_runtime": 1.4607,
+      "eval_samples_per_second": 1504.709,
+      "eval_steps_per_second": 23.96,
+      "step": 409000
+    },
+    {
+      "epoch": 9.54,
+      "learning_rate": 3.5208241851812644e-05,
+      "loss": 0.2549,
+      "step": 409500
+    },
+    {
+      "epoch": 9.55,
+      "learning_rate": 3.493871948353709e-05,
+      "loss": 0.2548,
+      "step": 410000
+    },
+    {
+      "epoch": 9.55,
+      "eval_loss": 0.23903900384902954,
+      "eval_runtime": 1.4733,
+      "eval_samples_per_second": 1491.858,
+      "eval_steps_per_second": 23.756,
+      "step": 410000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.277946307806184e+22,
+  "total_flos": 1.309895021683634e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6331caf84d401728c3e2540374852d6e489eae28c3099656d3c86fe297980cc4
+oid sha256:db26ab4777ecfb64dd27c707c9cfebcf74d431f5c02f5554c247500eee4a57f0
 size 102501541