Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc1acb58f6552f17f47c9e79c248b5766ef129b9cc7004d0289960bcfa126ad
+oid sha256:f80e3de78ec7f718a3637a451b022d00d5747c3921319eeca47a758a0e59be95
 size 68602152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2812cf244d8d46428667984a8e6ab4a612874e817adebcbd079c4d0b057e17c
+oid sha256:d57376255dcc20709e63e6fac8eb03cca00ae997ca828a45e21c3ad3d33673a5
 size 137100235

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd679242a831d4484be1b031fb6a525641a1324383532f6e1c8bb5ac52e4ce7
+oid sha256:6dc250d4299290adba53e444599baac02762c85fc6141cd19d386e734b288b94
 size 14455

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f931434598425c3d35e696dc1ef9a0302880efc75ad45f5e1fbe43cfc68f080
+oid sha256:77ced95f1c67747bc54b27b1781254392fe5947e21557e2368922a37a0b7cc5f
 size 1465

last-checkpoint/trainer_state.json

@@ -4,84 +4,161 @@
   "best_model_checkpoint": null,
   "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 10,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.1,
-      "grad_norm": 3.904756546020508,
+      "epoch": 0.005,
+      "grad_norm": 5.714346885681152,
       "learning_rate": 0.0,
-      "loss": 11.039416313171387,
+      "loss": 22.1131649017334,
       "step": 1
     },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.169634819030762,
+      "learning_rate": 0.000135,
+      "loss": 21.767859564887154,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.887928009033203,
+      "learning_rate": 0.000285,
+      "loss": 19.7130615234375,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.950296401977539,
+      "learning_rate": 0.00029815325108927063,
+      "loss": 16.41785888671875,
+      "step": 30
+    },
     {
       "epoch": 0.2,
-      "grad_norm": 2.952423572540283,
-      "learning_rate": 0.00015,
-      "loss": 11.029916763305664,
-      "step": 2
+      "grad_norm": 3.509552240371704,
+      "learning_rate": 0.00029182778633989753,
+      "loss": 13.775221252441407,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.330707550048828,
+      "learning_rate": 0.00028119295607090933,
+      "loss": 12.137359619140625,
+      "step": 50
     },
     {
       "epoch": 0.3,
-      "grad_norm": 2.548621654510498,
-      "learning_rate": 0.0003,
-      "loss": 10.987221717834473,
-      "step": 3
+      "grad_norm": 5.043827533721924,
+      "learning_rate": 0.0002665718942185456,
+      "loss": 10.122330474853516,
+      "step": 60
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 7.171847820281982,
+      "learning_rate": 0.0002484088543485761,
+      "loss": 9.294523620605469,
+      "step": 70
     },
     {
       "epoch": 0.4,
-      "grad_norm": 2.724034309387207,
-      "learning_rate": 0.000288581929876693,
-      "loss": 10.806486129760742,
-      "step": 4
+      "grad_norm": 5.002739906311035,
+      "learning_rate": 0.00022725571123650813,
+      "loss": 8.580620574951173,
+      "step": 80
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 7.2115864753723145,
+      "learning_rate": 0.000203755192431795,
+      "loss": 7.536891174316406,
+      "step": 90
     },
     {
       "epoch": 0.5,
-      "grad_norm": 2.913846731185913,
-      "learning_rate": 0.00025606601717798207,
-      "loss": 10.382536888122559,
-      "step": 5
+      "grad_norm": 6.534404277801514,
+      "learning_rate": 0.0001786213493064817,
+      "loss": 6.871263122558593,
+      "step": 100
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 7.4687371253967285,
+      "learning_rate": 0.00015261786096559254,
+      "loss": 6.103485488891602,
+      "step": 110
     },
     {
       "epoch": 0.6,
-      "grad_norm": 3.6747395992279053,
-      "learning_rate": 0.00020740251485476345,
-      "loss": 10.37621784210205,
-      "step": 6
+      "grad_norm": 7.448652744293213,
+      "learning_rate": 0.00012653483024396533,
+      "loss": 5.706993484497071,
+      "step": 120
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 8.251703262329102,
+      "learning_rate": 0.00010116477683142652,
+      "loss": 5.297743225097657,
+      "step": 130
     },
     {
       "epoch": 0.7,
-      "grad_norm": 2.790466785430908,
-      "learning_rate": 0.00015,
-      "loss": 10.06509780883789,
-      "step": 7
+      "grad_norm": 8.646885871887207,
+      "learning_rate": 7.727855696304944e-05,
+      "loss": 5.091459274291992,
+      "step": 140
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 6.968000888824463,
+      "learning_rate": 5.56019413425244e-05,
+      "loss": 5.0955852508544925,
+      "step": 150
     },
     {
       "epoch": 0.8,
-      "grad_norm": 3.1298794746398926,
-      "learning_rate": 9.259748514523653e-05,
-      "loss": 10.32823371887207,
-      "step": 8
+      "grad_norm": 7.26023530960083,
+      "learning_rate": 3.6793562966584196e-05,
+      "loss": 4.98658561706543,
+      "step": 160
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 6.96763801574707,
+      "learning_rate": 2.1424904894683165e-05,
+      "loss": 4.740906524658203,
+      "step": 170
     },
     {
       "epoch": 0.9,
-      "grad_norm": 4.239963054656982,
-      "learning_rate": 4.3933982822017876e-05,
-      "loss": 9.877490997314453,
-      "step": 9
+      "grad_norm": 5.774592399597168,
+      "learning_rate": 9.962936025419754e-06,
+      "loss": 5.162647247314453,
+      "step": 180
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 5.674193382263184,
+      "learning_rate": 2.7559224828504035e-06,
+      "loss": 4.910265731811523,
+      "step": 190
     },
     {
       "epoch": 1.0,
-      "grad_norm": 3.074774742126465,
-      "learning_rate": 1.1418070123306989e-05,
-      "loss": 9.85549545288086,
-      "step": 10
+      "grad_norm": 5.3918843269348145,
+      "learning_rate": 2.284572654130956e-08,
+      "loss": 4.620555114746094,
+      "step": 200
     }
   ],
-  "logging_steps": 1,
-  "max_steps": 10,
+  "logging_steps": 10,
+  "max_steps": 200,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
   "save_steps": 999999,
@@ -97,7 +174,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 131090350080.0,
+  "total_flos": 5243614003200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7be4b80f34efa8c6ffa736724ae3152fa29c25aa950c50b57dfee4c09cee52
+oid sha256:415469a51be6dee5831e245b12681d572265671f676d2c3884a4e71aefabe5d4
 size 5329