Training in progress, step 10000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426565ae7e122986bcb61feb0824a20d697e6e1d0d7ee61605f81249ac607053
+oid sha256:73489cdb01a4bb6cfe5252edc42886df8eebea1bb75734e470347a6522c023a1
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5975d5c14cb653070063ab664a542345e1d7b31d1f7f2691782cc33745d9b2b9
+oid sha256:5920908de9e54da20823768f6ef8cc7bc5d55494a5080bb14683341420ff389e
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b802e5910fd078d7354b6fbe97850b2f1ec26c0f43e7f9e349a96b25ed8f557
+oid sha256:9b44d07e2d139a22d271aa72093cf081d67bc950fe387651d7d6d2f2dba45fb6
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6775d0c71cbc2254c9932c38f18b38899f4e38dc0dfc75f710acd45f734e62b
+oid sha256:351b48ff70cf2e76c396612d9003a4396dc5f5b7c719dcf507ee09719e12672a
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ebe9ed2aebd8d40826f0d7b248340ae7726517e3fb98bf26aa87be67a5fb7a
+oid sha256:2d524b4cb1391ef7e50966a3eef7ac714ecb6ed976eedf165d99a07d29c73b99
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4353125544140693,
-  "global_step": 5000,
+  "epoch": 0.8706251088281386,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,11 +74,79 @@
       "eval_samples_per_second": 202.871,
       "eval_steps_per_second": 3.205,
       "step": 5000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010010559815435491,
+      "loss": 0.4647,
+      "step": 5500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.997779155931062e-05,
+      "loss": 0.4633,
+      "step": 6000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.983873864536092e-05,
+      "loss": 0.4633,
+      "step": 6500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.968871882446063e-05,
+      "loss": 0.4599,
+      "step": 7000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.952776911175577e-05,
+      "loss": 0.4583,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.935592921917959e-05,
+      "loss": 0.459,
+      "step": 8000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.91732415456543e-05,
+      "loss": 0.4574,
+      "step": 8500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.897975116662973e-05,
+      "loss": 0.4571,
+      "step": 9000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.877550582296162e-05,
+      "loss": 0.456,
+      "step": 9500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.856099645730841e-05,
+      "loss": 0.4546,
+      "step": 10000
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 0.43266522884368896,
+      "eval_runtime": 17.119,
+      "eval_samples_per_second": 292.073,
+      "eval_steps_per_second": 4.615,
+      "step": 10000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 2.354930673647616e+20,
+  "total_flos": 4.709861347295232e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5975d5c14cb653070063ab664a542345e1d7b31d1f7f2691782cc33745d9b2b9
+oid sha256:5920908de9e54da20823768f6ef8cc7bc5d55494a5080bb14683341420ff389e
 size 449471589