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:c96562d3a60b11e534c6c19023929f5c800654c7ff0e76b0ee20d32ef06a2e1b
+oid sha256:6e0fff409a045148e473d2f5b7ed122acefa05512d76f9e6df4db46d33192af4
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b67f94540cd9d23537f2b662685a3722a0d0ded25cdf856d387b97b74ef53ef
+oid sha256:0e1fcc5e9d2a83f615cd50681db5e31eb86446fdee2d45e615468885203467ba
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c3a273cc848b511ec2e10fbd46e20d653ada565feeda407513d0f9ea6fb5c75
+oid sha256:c72d0c38151f4029511bff5d2321526ce34ef28fd4afbb6fd0768648e0d24860
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:567028b2e968ac95087978071532012f89f2ee035d73b03d90bd31c1ad2165e9
+oid sha256:e74f267288fb4a1df08b32f97444ae5cf95c3132a17f17fe2908efac0277d50e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4ca4692528ea9a220faab38a2bdf346ccd8ff0b1ef090cd3e682c579f0ba7b
+oid sha256:a5df49a923da119c9d4b384e98ee730af3de7b1413bda9e2c918cc4a8596c914
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86dffd431f1c2175dc3fd14a6ea11432aa41055786ebbc0abd4386dcbcec8d4d
+oid sha256:40b2a05d8a4a0e806d68e44134b15a2fcab5ec6d446d58fd47466adaec606fbf
 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": 0.5152596831321716,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09530617107457708,
+  "best_metric": 0.5070595741271973,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.19061234214915415,
   "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": 16.724,
       "eval_steps_per_second": 2.09,
       "step": 25
+    },
+    {
+      "epoch": 0.09911841791756017,
+      "grad_norm": 0.10818018019199371,
+      "learning_rate": 5e-05,
+      "loss": 0.546,
+      "step": 26
+    },
+    {
+      "epoch": 0.10293066476054324,
+      "grad_norm": 0.11384043097496033,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5618,
+      "step": 27
+    },
+    {
+      "epoch": 0.10674291160352632,
+      "grad_norm": 0.11418091505765915,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5233,
+      "step": 28
+    },
+    {
+      "epoch": 0.11055515844650941,
+      "grad_norm": 0.12104526162147522,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.538,
+      "step": 29
+    },
+    {
+      "epoch": 0.11436740528949249,
+      "grad_norm": 0.11738970875740051,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5143,
+      "step": 30
+    },
+    {
+      "epoch": 0.11817965213247558,
+      "grad_norm": 0.1219177395105362,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5443,
+      "step": 31
+    },
+    {
+      "epoch": 0.12199189897545866,
+      "grad_norm": 0.12566395103931427,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5024,
+      "step": 32
+    },
+    {
+      "epoch": 0.12580414581844174,
+      "grad_norm": 0.12906301021575928,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5055,
+      "step": 33
+    },
+    {
+      "epoch": 0.12961639266142483,
+      "grad_norm": 0.1359078735113144,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.533,
+      "step": 34
+    },
+    {
+      "epoch": 0.13342863950440792,
+      "grad_norm": 0.13142311573028564,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5115,
+      "step": 35
+    },
+    {
+      "epoch": 0.13724088634739098,
+      "grad_norm": 0.14356505870819092,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4999,
+      "step": 36
+    },
+    {
+      "epoch": 0.14105313319037407,
+      "grad_norm": 0.15357092022895813,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4806,
+      "step": 37
+    },
+    {
+      "epoch": 0.14486538003335717,
+      "grad_norm": 0.1159888505935669,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5599,
+      "step": 38
+    },
+    {
+      "epoch": 0.14867762687634023,
+      "grad_norm": 0.09829525649547577,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4968,
+      "step": 39
+    },
+    {
+      "epoch": 0.15248987371932332,
+      "grad_norm": 0.11236710846424103,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5106,
+      "step": 40
+    },
+    {
+      "epoch": 0.1563021205623064,
+      "grad_norm": 0.10919924080371857,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5101,
+      "step": 41
+    },
+    {
+      "epoch": 0.1601143674052895,
+      "grad_norm": 0.11482226848602295,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.542,
+      "step": 42
+    },
+    {
+      "epoch": 0.16392661424827257,
+      "grad_norm": 0.1178121492266655,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4985,
+      "step": 43
+    },
+    {
+      "epoch": 0.16773886109125566,
+      "grad_norm": 0.11335285007953644,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4961,
+      "step": 44
+    },
+    {
+      "epoch": 0.17155110793423875,
+      "grad_norm": 0.12047620117664337,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5196,
+      "step": 45
+    },
+    {
+      "epoch": 0.1753633547772218,
+      "grad_norm": 0.12417250871658325,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5104,
+      "step": 46
+    },
+    {
+      "epoch": 0.1791756016202049,
+      "grad_norm": 0.1260678768157959,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5061,
+      "step": 47
+    },
+    {
+      "epoch": 0.182987848463188,
+      "grad_norm": 0.13256168365478516,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4891,
+      "step": 48
+    },
+    {
+      "epoch": 0.1868000953061711,
+      "grad_norm": 0.13964025676250458,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5236,
+      "step": 49
+    },
+    {
+      "epoch": 0.19061234214915415,
+      "grad_norm": 0.15629474818706512,
+      "learning_rate": 0.0,
+      "loss": 0.4982,
+      "step": 50
+    },
+    {
+      "epoch": 0.19061234214915415,
+      "eval_loss": 0.5070595741271973,
+      "eval_runtime": 101.8332,
+      "eval_samples_per_second": 17.362,
+      "eval_steps_per_second": 2.17,
+      "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": 2.987771858905989e+17,
+  "total_flos": 5.979273768059535e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null