Training in progress, step 30000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ee51c8aedd1331406dff270a8984611b6b49ff01591d1f971301667cfec2bb
+oid sha256:621885238091f20d2a0d641b95a90fdb9bc3444198b5397e5acf7ccaf99d5986
 size 202193937

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dbf204d94f01686d975a9600d69bdbd768ad031083dfb100f388cc4d3cc68ac
+oid sha256:fa203d33d859117c15113363e612cb47f6ca37647ffc177ded20da5dfb658c7d
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f921c9f94cfbf967d9cad8d656604b2c1e1fb876e74b18ab76eb0d839fa8e8
+oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f921c9f94cfbf967d9cad8d656604b2c1e1fb876e74b18ab76eb0d839fa8e8
+oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f921c9f94cfbf967d9cad8d656604b2c1e1fb876e74b18ab76eb0d839fa8e8
+oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f921c9f94cfbf967d9cad8d656604b2c1e1fb876e74b18ab76eb0d839fa8e8
+oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f921c9f94cfbf967d9cad8d656604b2c1e1fb876e74b18ab76eb0d839fa8e8
+oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f921c9f94cfbf967d9cad8d656604b2c1e1fb876e74b18ab76eb0d839fa8e8
+oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f921c9f94cfbf967d9cad8d656604b2c1e1fb876e74b18ab76eb0d839fa8e8
+oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f921c9f94cfbf967d9cad8d656604b2c1e1fb876e74b18ab76eb0d839fa8e8
+oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c84272d9e8a15cd78c706d16b77833d53dbfbd182e8ad79e3cd658ef6c3eaaf6
+oid sha256:ff9b79eba2b3c3487d57b5f9509b60a9305753a31bdaa8757ad442412114850e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5097099750242112,
-  "global_step": 20000,
+  "epoch": 0.7645649625363168,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -406,11 +406,211 @@
       "eval_samples_per_second": 862.885,
       "eval_steps_per_second": 13.806,
       "step": 20000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00024599999999999996,
+      "loss": 0.4437,
+      "step": 20500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00025199999999999995,
+      "loss": 0.439,
+      "step": 21000
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.8742354512214661,
+      "eval_runtime": 1.1831,
+      "eval_samples_per_second": 845.245,
+      "eval_steps_per_second": 13.524,
+      "step": 21000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.000258,
+      "loss": 0.4339,
+      "step": 21500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00026399999999999997,
+      "loss": 0.4292,
+      "step": 22000
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 0.8848758935928345,
+      "eval_runtime": 1.1886,
+      "eval_samples_per_second": 841.313,
+      "eval_steps_per_second": 13.461,
+      "step": 22000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00027,
+      "loss": 0.4251,
+      "step": 22500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000276,
+      "loss": 0.4212,
+      "step": 23000
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 0.8841528296470642,
+      "eval_runtime": 1.2211,
+      "eval_samples_per_second": 818.95,
+      "eval_steps_per_second": 13.103,
+      "step": 23000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028199999999999997,
+      "loss": 0.4175,
+      "step": 23500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028799999999999995,
+      "loss": 0.4142,
+      "step": 24000
+    },
+    {
+      "epoch": 0.61,
+      "eval_loss": 0.8811973929405212,
+      "eval_runtime": 1.275,
+      "eval_samples_per_second": 784.285,
+      "eval_steps_per_second": 12.549,
+      "step": 24000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.000294,
+      "loss": 0.4109,
+      "step": 24500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.4076,
+      "step": 25000
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.8659318089485168,
+      "eval_runtime": 1.2881,
+      "eval_samples_per_second": 776.338,
+      "eval_steps_per_second": 12.421,
+      "step": 25000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00029999920715161553,
+      "loss": 0.4045,
+      "step": 25500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002999968286151326,
+      "loss": 0.4017,
+      "step": 26000
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 0.874371349811554,
+      "eval_runtime": 1.2282,
+      "eval_samples_per_second": 814.215,
+      "eval_steps_per_second": 13.027,
+      "step": 26000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002999928644165624,
+      "loss": 0.3987,
+      "step": 26500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002999873145992569,
+      "loss": 0.3958,
+      "step": 27000
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 0.8821514844894409,
+      "eval_runtime": 1.1414,
+      "eval_samples_per_second": 876.15,
+      "eval_steps_per_second": 14.018,
+      "step": 27000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000299980179223908,
+      "loss": 0.3933,
+      "step": 27500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002999714583685469,
+      "loss": 0.3907,
+      "step": 28000
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 0.8762433528900146,
+      "eval_runtime": 1.2113,
+      "eval_samples_per_second": 825.526,
+      "eval_steps_per_second": 13.208,
+      "step": 28000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00029996115212854366,
+      "loss": 0.3886,
+      "step": 28500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00029994926061660554,
+      "loss": 0.3863,
+      "step": 29000
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 0.8757530450820923,
+      "eval_runtime": 1.1818,
+      "eval_samples_per_second": 846.134,
+      "eval_steps_per_second": 13.538,
+      "step": 29000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002999357839627762,
+      "loss": 0.3841,
+      "step": 29500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00029992072231443425,
+      "loss": 0.382,
+      "step": 30000
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.8755055069923401,
+      "eval_runtime": 1.2044,
+      "eval_samples_per_second": 830.296,
+      "eval_steps_per_second": 13.285,
+      "step": 30000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 6.38974277549e+20,
+  "total_flos": 9.584614163235e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dbf204d94f01686d975a9600d69bdbd768ad031083dfb100f388cc4d3cc68ac
+oid sha256:fa203d33d859117c15113363e612cb47f6ca37647ffc177ded20da5dfb658c7d
 size 102501541