Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9568737ee3b1912717256324d7af78d3e5423caaecf325747821670ea49f11d7
+oid sha256:cdea657463b389a3a325b33524baf72112d6092576b2ee88c5b39a9679817f11
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd94bbeeced8c1d22913ff15eae36c6f7bd57fbbdca2e78189957b10546b26ca
+oid sha256:2702d06c242f54a529a43a3eb283403c2498794325969967dbf4c4238bbe1b5e
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac0bf5a078333eaa8c23dbe13e54983d1473a9524435bf56835064342e38bffd
+oid sha256:0c049f6d294d77c889a3f6283eedad32a564ee7fe10320f131918d45d22966f9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e35baca7ff704e0cb86e3ba8b9d338d99a38343d60e096e7d4f7f4266018ffcf
+oid sha256:fae73c7ee510820b87ad1220cf9918dac46ff163d436a8e30696c737aa0a5bd8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60814aa9a0b879d145fe73d8baeeeeccf54f9cccd348c70cd086800bc58d1e29
+oid sha256:35fbb2363821ebd2a19456bce09e5d6e677661a2deddb5cc50ecc37c3d3199e9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:447b7636edef2ae67b46a9a4452370ceb449c1e87a363e51b667652ad3bd7164
+oid sha256:89057d83a1c0e5973fc8203478aa9d0efacecdd531969b425bc0957efed3adea
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.39730966091156,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9237875288683602,
+  "best_metric": 1.3839502334594727,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.8475750577367207,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 32.638,
       "eval_steps_per_second": 4.125,
       "step": 25
+    },
+    {
+      "epoch": 0.9607390300230947,
+      "grad_norm": 0.3993252217769623,
+      "learning_rate": 5e-05,
+      "loss": 1.3449,
+      "step": 26
+    },
+    {
+      "epoch": 0.9976905311778291,
+      "grad_norm": 0.4546384811401367,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1338,
+      "step": 27
+    },
+    {
+      "epoch": 1.0346420323325636,
+      "grad_norm": 1.0680946111679077,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.1549,
+      "step": 28
+    },
+    {
+      "epoch": 1.071593533487298,
+      "grad_norm": 0.5346181392669678,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.531,
+      "step": 29
+    },
+    {
+      "epoch": 1.1085450346420322,
+      "grad_norm": 0.5427453517913818,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.4747,
+      "step": 30
+    },
+    {
+      "epoch": 1.1454965357967668,
+      "grad_norm": 0.558639407157898,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.393,
+      "step": 31
+    },
+    {
+      "epoch": 1.1824480369515011,
+      "grad_norm": 0.585619330406189,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3481,
+      "step": 32
+    },
+    {
+      "epoch": 1.2193995381062355,
+      "grad_norm": 0.6847278475761414,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3739,
+      "step": 33
+    },
+    {
+      "epoch": 1.25635103926097,
+      "grad_norm": 0.5396642088890076,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0703,
+      "step": 34
+    },
+    {
+      "epoch": 1.2933025404157044,
+      "grad_norm": 0.5222858190536499,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6278,
+      "step": 35
+    },
+    {
+      "epoch": 1.3302540415704387,
+      "grad_norm": 0.540937066078186,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4927,
+      "step": 36
+    },
+    {
+      "epoch": 1.3672055427251733,
+      "grad_norm": 0.55878084897995,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4581,
+      "step": 37
+    },
+    {
+      "epoch": 1.4041570438799076,
+      "grad_norm": 0.5840333104133606,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4209,
+      "step": 38
+    },
+    {
+      "epoch": 1.4411085450346421,
+      "grad_norm": 0.7051689624786377,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.4098,
+      "step": 39
+    },
+    {
+      "epoch": 1.4780600461893765,
+      "grad_norm": 0.703649640083313,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.2392,
+      "step": 40
+    },
+    {
+      "epoch": 1.5150115473441108,
+      "grad_norm": 0.5681647658348083,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2953,
+      "step": 41
+    },
+    {
+      "epoch": 1.5519630484988451,
+      "grad_norm": 0.5803612470626831,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5462,
+      "step": 42
+    },
+    {
+      "epoch": 1.5889145496535797,
+      "grad_norm": 0.5447371602058411,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.5298,
+      "step": 43
+    },
+    {
+      "epoch": 1.625866050808314,
+      "grad_norm": 0.5576654076576233,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3899,
+      "step": 44
+    },
+    {
+      "epoch": 1.6628175519630486,
+      "grad_norm": 0.5950343608856201,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4301,
+      "step": 45
+    },
+    {
+      "epoch": 1.699769053117783,
+      "grad_norm": 0.7155903577804565,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2867,
+      "step": 46
+    },
+    {
+      "epoch": 1.7367205542725173,
+      "grad_norm": 0.738254964351654,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2506,
+      "step": 47
+    },
+    {
+      "epoch": 1.7736720554272516,
+      "grad_norm": 0.5283464789390564,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.3485,
+      "step": 48
+    },
+    {
+      "epoch": 1.8106235565819861,
+      "grad_norm": 0.5948820114135742,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.4925,
+      "step": 49
+    },
+    {
+      "epoch": 1.8475750577367207,
+      "grad_norm": 0.5409876704216003,
+      "learning_rate": 0.0,
+      "loss": 1.3948,
+      "step": 50
+    },
+    {
+      "epoch": 1.8475750577367207,
+      "eval_loss": 1.3839502334594727,
+      "eval_runtime": 5.5701,
+      "eval_samples_per_second": 32.674,
+      "eval_steps_per_second": 4.129,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.822877455843328e+17,
+  "total_flos": 5.645754911686656e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null