Training in progress, step 44, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeba0945f4546b78eaf4823ea1f7e8774bebfd4b7b8df946e5dcf8fe3d36de96
+oid sha256:c50b6924c0bae87fa8e5869ef55c6409080cc8ac233f10e7e00c9dc6d398b868
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289ed26394e07a9948bb758d765c61c6a14c5a507f0037ca9bbfded95dba5d69
+oid sha256:955541acfa538474394bfae75d0261c5c7d5f6d66f9f363ce06879f4346cbc35
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea72a3c7c3f5fbd943777ee7aad2c271e2b4d0e636726ec2c150d59c58996742
+oid sha256:1557612bdfe011a5f03dc7a0a178f11184e1f05a1c711a44277f76958cbd51f6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1c67d139246c842a4b79e6b8bd3f522f027ea0779697679ed43d2158816955
+oid sha256:d42c3974ad11284d4f50a33b67765f6599a1b5d76329126c6a94122ab70bef91
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7d714eedfd2719e7864ae12b235da25bd945c66246239893634604dbfb1cb6
+oid sha256:7b0611057f14ec35f9fbab9fc2ae3bf51241e604ad6d3af38adfe532a456b52d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c5cd8b76b68cfffd874939abaa6a334ea28dfa9e17d85e1863c43383b13d365
+oid sha256:681ae736f9b6865e85081bdd80b2d3d5e4bbb5fa4b577c4c7ad40e9d10f25ead
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c90b2d8623eacbca7de7c3a4e7890d40417c2144f0746860a87974700b51740c
+oid sha256:74384ee4f4d516692f488cd2897f31d93127b8f052b6b6c3deb94eb2492306b3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.830071449279785,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7489177489177488,
+  "epoch": 3.0995670995670994,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 44,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,139 @@
       "eval_samples_per_second": 285.216,
       "eval_steps_per_second": 38.225,
       "step": 25
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 11.699345588684082,
+      "learning_rate": 3.887395330218429e-05,
+      "loss": 173.6496,
+      "step": 26
+    },
+    {
+      "epoch": 1.8874458874458875,
+      "grad_norm": 12.151203155517578,
+      "learning_rate": 3.5262241279454785e-05,
+      "loss": 173.2626,
+      "step": 27
+    },
+    {
+      "epoch": 1.9567099567099566,
+      "grad_norm": 13.101295471191406,
+      "learning_rate": 3.173294878168025e-05,
+      "loss": 172.6745,
+      "step": 28
+    },
+    {
+      "epoch": 2.0432900432900434,
+      "grad_norm": 11.549407005310059,
+      "learning_rate": 2.8305813044122097e-05,
+      "loss": 173.3999,
+      "step": 29
+    },
+    {
+      "epoch": 2.1125541125541125,
+      "grad_norm": 11.566390037536621,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 173.2819,
+      "step": 30
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 12.355212211608887,
+      "learning_rate": 2.1833997096818898e-05,
+      "loss": 172.7516,
+      "step": 31
+    },
+    {
+      "epoch": 2.2510822510822512,
+      "grad_norm": 12.678069114685059,
+      "learning_rate": 1.8825509907063327e-05,
+      "loss": 172.5498,
+      "step": 32
+    },
+    {
+      "epoch": 2.3203463203463204,
+      "grad_norm": 11.534626007080078,
+      "learning_rate": 1.599136311145402e-05,
+      "loss": 173.2147,
+      "step": 33
+    },
+    {
+      "epoch": 2.3896103896103895,
+      "grad_norm": 11.905769348144531,
+      "learning_rate": 1.3347406408508695e-05,
+      "loss": 172.7978,
+      "step": 34
+    },
+    {
+      "epoch": 2.458874458874459,
+      "grad_norm": 12.531118392944336,
+      "learning_rate": 1.090842587659851e-05,
+      "loss": 172.408,
+      "step": 35
+    },
+    {
+      "epoch": 2.5281385281385282,
+      "grad_norm": 11.69418716430664,
+      "learning_rate": 8.688061284200266e-06,
+      "loss": 172.8473,
+      "step": 36
+    },
+    {
+      "epoch": 2.5974025974025974,
+      "grad_norm": 11.74834156036377,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 172.91,
+      "step": 37
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 12.282010078430176,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 172.4874,
+      "step": 38
+    },
+    {
+      "epoch": 2.7359307359307357,
+      "grad_norm": 12.744579315185547,
+      "learning_rate": 3.4563125677897932e-06,
+      "loss": 172.1435,
+      "step": 39
+    },
+    {
+      "epoch": 2.8051948051948052,
+      "grad_norm": 11.38916015625,
+      "learning_rate": 2.221359710692961e-06,
+      "loss": 173.1085,
+      "step": 40
+    },
+    {
+      "epoch": 2.8744588744588744,
+      "grad_norm": 11.664361000061035,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 172.7579,
+      "step": 41
+    },
+    {
+      "epoch": 2.9437229437229435,
+      "grad_norm": 12.311667442321777,
+      "learning_rate": 5.584586887435739e-07,
+      "loss": 172.3491,
+      "step": 42
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "grad_norm": 11.661219596862793,
+      "learning_rate": 1.3981014094099353e-07,
+      "loss": 172.7641,
+      "step": 43
+    },
+    {
+      "epoch": 3.0995670995670994,
+      "grad_norm": 11.562482833862305,
+      "learning_rate": 0.0,
+      "loss": 172.8927,
+      "step": 44
     }
   ],
   "logging_steps": 1,
@@ -221,12 +354,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 19055561932800.0,
+  "total_flos": 33537789001728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null