Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a68ed6b15cb88b0fa22d5594ded7417b6a8e99d85eece995b0681aafa79a356
+oid sha256:deac835b157a7c4e8bc45a2804dce4a7e6ad2e01a0245d62e55c9776e9e87078
 size 859909312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3ac863536aca2d657b8c120563226c5c798868ffe78107c0df158ce7179b8ce
+oid sha256:af290f7942dbb85369bdd96c457503fcf34363ab0f7f3e0899d591d987b2ffc9
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c9c444c60a99e5ca9bec1f0629070fb2a0661b12a95995b7fb08a345fc211c7
+oid sha256:5b0ba6119a419f4bdccd0f03de1d3eb9e80e5075c32450d2b815421d84499201
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8174bec7257736d616204abc32d3d70eede34b421ad59a7d1ad16cc3f9843cbf
+oid sha256:b41c784b838763746cc271484dce1236d76d2a27dc75623224afeaeffb0b6d5e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205859cf74135b886639c07c63c93ae3237146f29e8162392e406bf8c38431c0
+oid sha256:83ae03e1586e8a628dd0eab82ed3bb5c49697645d414bda48238c2db9a361198
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebd71b8dffc2c366ea9a52c657adceafef629644a56b313c2f507d899c9f2339
+oid sha256:2a215ee2f3cc7c04153c450a4dc49d8a3e3624764062e79042cf65c7563f9583
 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": 0.6939923167228699,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6462035541195477,
+  "best_metric": 0.6489943265914917,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.3021001615508885,
   "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": 32.883,
       "eval_steps_per_second": 4.158,
       "step": 25
+    },
+    {
+      "epoch": 0.6720516962843296,
+      "grad_norm": 2.508800745010376,
+      "learning_rate": 5e-05,
+      "loss": 0.628,
+      "step": 26
+    },
+    {
+      "epoch": 0.6978998384491115,
+      "grad_norm": 2.8532986640930176,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5209,
+      "step": 27
+    },
+    {
+      "epoch": 0.7237479806138933,
+      "grad_norm": 3.32419490814209,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6523,
+      "step": 28
+    },
+    {
+      "epoch": 0.7495961227786753,
+      "grad_norm": 1.6802136898040771,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.0802,
+      "step": 29
+    },
+    {
+      "epoch": 0.7754442649434572,
+      "grad_norm": 1.3012361526489258,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0615,
+      "step": 30
+    },
+    {
+      "epoch": 0.8012924071082391,
+      "grad_norm": 1.8923187255859375,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7458,
+      "step": 31
+    },
+    {
+      "epoch": 0.827140549273021,
+      "grad_norm": 2.164623975753784,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6567,
+      "step": 32
+    },
+    {
+      "epoch": 0.8529886914378029,
+      "grad_norm": 2.3818938732147217,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6405,
+      "step": 33
+    },
+    {
+      "epoch": 0.8788368336025848,
+      "grad_norm": 2.1383883953094482,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5945,
+      "step": 34
+    },
+    {
+      "epoch": 0.9046849757673667,
+      "grad_norm": 2.281585693359375,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5481,
+      "step": 35
+    },
+    {
+      "epoch": 0.9305331179321487,
+      "grad_norm": 2.466137647628784,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4819,
+      "step": 36
+    },
+    {
+      "epoch": 0.9563812600969306,
+      "grad_norm": 2.864682912826538,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4667,
+      "step": 37
+    },
+    {
+      "epoch": 0.9822294022617124,
+      "grad_norm": 3.9639532566070557,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6574,
+      "step": 38
+    },
+    {
+      "epoch": 1.0177705977382876,
+      "grad_norm": 2.692258596420288,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5385,
+      "step": 39
+    },
+    {
+      "epoch": 1.0436187399030694,
+      "grad_norm": 1.938528060913086,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7774,
+      "step": 40
+    },
+    {
+      "epoch": 1.0694668820678515,
+      "grad_norm": 2.162245988845825,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5262,
+      "step": 41
+    },
+    {
+      "epoch": 1.0953150242326333,
+      "grad_norm": 1.9805015325546265,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4586,
+      "step": 42
+    },
+    {
+      "epoch": 1.121163166397415,
+      "grad_norm": 2.3543405532836914,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4878,
+      "step": 43
+    },
+    {
+      "epoch": 1.1470113085621971,
+      "grad_norm": 2.19230318069458,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4103,
+      "step": 44
+    },
+    {
+      "epoch": 1.172859450726979,
+      "grad_norm": 2.6225059032440186,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4584,
+      "step": 45
+    },
+    {
+      "epoch": 1.198707592891761,
+      "grad_norm": 2.018688678741455,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.297,
+      "step": 46
+    },
+    {
+      "epoch": 1.2245557350565428,
+      "grad_norm": 2.281841993331909,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3342,
+      "step": 47
+    },
+    {
+      "epoch": 1.2504038772213248,
+      "grad_norm": 1.823398232460022,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.583,
+      "step": 48
+    },
+    {
+      "epoch": 1.2762520193861067,
+      "grad_norm": 2.1011440753936768,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1869,
+      "step": 49
+    },
+    {
+      "epoch": 1.3021001615508885,
+      "grad_norm": 2.315281391143799,
+      "learning_rate": 0.0,
+      "loss": 0.7053,
+      "step": 50
+    },
+    {
+      "epoch": 1.3021001615508885,
+      "eval_loss": 0.6489943265914917,
+      "eval_runtime": 7.9368,
+      "eval_samples_per_second": 32.885,
+      "eval_steps_per_second": 4.158,
+      "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": 2.829012279754752e+17,
+  "total_flos": 5.658024559509504e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null