Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3672b828410a1ef685cdf346708db7f089664128e37e98368dd2ea4eb073bfd7
+oid sha256:1ec8e0f1498a8954ea4662a61e5fc807c972535bf7810ee07eca3cfd1d8fc14c
 size 844180648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7241722f7ced76aa1c71ca6ba81628ec7a9aed271df173c1646c87d84e93b6fe
+oid sha256:6e8f2b21bbc4544f29b561935a109a97fb517e2d9f7aaeb03e177eb443cbfbb6
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2ee3b736894d0d1dfe5afeb66a46833771b98e8f644fe76732c549a014ff07
+oid sha256:674f11bf9868288503c116c5ddf49749b209c7c56e6e0ac6f2e661bbfe928869
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cba17338024e8f3153fb525c472e54eb708d9bee546799848c0ed0a31bc50fc8
+oid sha256:615eb5f88d27f3d01be139934fe571b450bf8a7cba0a3ebd0c21d813adf36b58
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94feb2fca805aa76a724a1fca2a36f2a6f48c0fc0c43df461a359dd80682dad8
+oid sha256:bca98e9749f18399546b1ee85cb8f019a236ae746ef81dec06be6bbba7580053
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be0663a5347fcac93947a1ed5127049a891ea7948135e8a3c94e7a4fb2c80a8
+oid sha256:a31175e7f66326aeffcf03f74a0c2ae6aaaf7bc32ddc30a11ad3b1f796033217
 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": 0.1451548933982849,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06817794443497528,
+  "best_metric": 0.1398579329252243,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13635588886995056,
   "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": 16.974,
       "eval_steps_per_second": 2.123,
       "step": 25
+    },
+    {
+      "epoch": 0.0709050622123743,
+      "grad_norm": 0.35424989461898804,
+      "learning_rate": 5e-05,
+      "loss": 0.1402,
+      "step": 26
+    },
+    {
+      "epoch": 0.07363217998977331,
+      "grad_norm": 0.8786327838897705,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1679,
+      "step": 27
+    },
+    {
+      "epoch": 0.07635929776717232,
+      "grad_norm": 0.3818786144256592,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1432,
+      "step": 28
+    },
+    {
+      "epoch": 0.07908641554457133,
+      "grad_norm": 0.20813222229480743,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1409,
+      "step": 29
+    },
+    {
+      "epoch": 0.08181353332197035,
+      "grad_norm": 0.11854073405265808,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1374,
+      "step": 30
+    },
+    {
+      "epoch": 0.08454065109936935,
+      "grad_norm": 0.2889731228351593,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1413,
+      "step": 31
+    },
+    {
+      "epoch": 0.08726776887676836,
+      "grad_norm": 0.2108319252729416,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1411,
+      "step": 32
+    },
+    {
+      "epoch": 0.08999488665416738,
+      "grad_norm": 0.1877073049545288,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1409,
+      "step": 33
+    },
+    {
+      "epoch": 0.09272200443156639,
+      "grad_norm": 0.16740399599075317,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1412,
+      "step": 34
+    },
+    {
+      "epoch": 0.0954491222089654,
+      "grad_norm": 0.2124919891357422,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1409,
+      "step": 35
+    },
+    {
+      "epoch": 0.0981762399863644,
+      "grad_norm": 0.12486357986927032,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1392,
+      "step": 36
+    },
+    {
+      "epoch": 0.10090335776376343,
+      "grad_norm": 0.18787531554698944,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1371,
+      "step": 37
+    },
+    {
+      "epoch": 0.10363047554116243,
+      "grad_norm": 0.04871739074587822,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1379,
+      "step": 38
+    },
+    {
+      "epoch": 0.10635759331856144,
+      "grad_norm": 0.07164865732192993,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.139,
+      "step": 39
+    },
+    {
+      "epoch": 0.10908471109596046,
+      "grad_norm": 0.04980754479765892,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1351,
+      "step": 40
+    },
+    {
+      "epoch": 0.11181182887335947,
+      "grad_norm": 0.21772225201129913,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1418,
+      "step": 41
+    },
+    {
+      "epoch": 0.11453894665075848,
+      "grad_norm": 0.25015074014663696,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1437,
+      "step": 42
+    },
+    {
+      "epoch": 0.11726606442815748,
+      "grad_norm": 0.02500380203127861,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1348,
+      "step": 43
+    },
+    {
+      "epoch": 0.1199931822055565,
+      "grad_norm": 0.0305391326546669,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1343,
+      "step": 44
+    },
+    {
+      "epoch": 0.12272029998295551,
+      "grad_norm": 0.14004138112068176,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1392,
+      "step": 45
+    },
+    {
+      "epoch": 0.12544741776035453,
+      "grad_norm": 0.02942681685090065,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1334,
+      "step": 46
+    },
+    {
+      "epoch": 0.12817453553775354,
+      "grad_norm": 0.19898109138011932,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1411,
+      "step": 47
+    },
+    {
+      "epoch": 0.13090165331515255,
+      "grad_norm": 0.22045519948005676,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1412,
+      "step": 48
+    },
+    {
+      "epoch": 0.13362877109255156,
+      "grad_norm": 0.1419573575258255,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1391,
+      "step": 49
+    },
+    {
+      "epoch": 0.13635588886995056,
+      "grad_norm": 0.052116479724645615,
+      "learning_rate": 0.0,
+      "loss": 0.1363,
+      "step": 50
+    },
+    {
+      "epoch": 0.13635588886995056,
+      "eval_loss": 0.1398579329252243,
+      "eval_runtime": 145.2684,
+      "eval_samples_per_second": 17.003,
+      "eval_steps_per_second": 2.127,
+      "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": 2.629553998528512e+17,
+  "total_flos": 5.259107997057024e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null