Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e90661a53e78d4f93c2d1c9aca2d7dd32bf4de0eff6bf1794d40f20b5805bfe
+oid sha256:7034402b52a078dc57aa47fa43015a35a3c84773ca85c73fdb3d0e4923ca92b1
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06603a9e50d4b5cc13bd2887b1c543a00b279f1f75c5630d82bb7f52b2cb0248
+oid sha256:32ec34b4a5bd75aa7a13f7783108f8e7392b910150a5a09879f11524ce72198f
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a31843f8d75cad9b880d17baf7045ca9db2af7fa93e671e6bb2bb245a45b0ac
+oid sha256:03a378b9449480751f968837dfd6fb4d8adbd9471ebcc3dfce977efb3b10dc3e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4516e89989e97ee2db4ff2e39b77ba9d9c65ab0d6181d856ab1d95f8c7d73d52
+oid sha256:7d4c272214adf09c18e78eaafefe012a36735cad966aa9554ca28535286aa1d7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31bdf181e934c0dcaefd2577c5c77739e812fe65ffbfc3283dfe61a54deac020
+oid sha256:36f844e459b8f8b1d562bea38226f29a294ab69d2629204cc78d7f4ffccd210c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d25fb687f7e1a6e1899ce5036ae749c8b4ab68acffa6d943b5c6cb2a6d107c
+oid sha256:f5b869f128e367f1e55bdc8821fa4e9c955ef137fe286035ed8b6e008d89cf9f
 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": 2.4557041342632147e-06,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08103727714748785,
+  "best_metric": 6.914133336977102e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1620745542949757,
   "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": 34.783,
       "eval_steps_per_second": 4.35,
       "step": 25
+    },
+    {
+      "epoch": 0.08427876823338736,
+      "grad_norm": 0.00037847296334803104,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.08752025931928688,
+      "grad_norm": 0.0007350973319262266,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.09076175040518639,
+      "grad_norm": 0.00028547627152875066,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.0940032414910859,
+      "grad_norm": 0.001375210820697248,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.09724473257698542,
+      "grad_norm": 0.00023330787371378392,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.10048622366288493,
+      "grad_norm": 0.0001925993274198845,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.10372771474878444,
+      "grad_norm": 0.00047052462468855083,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.10696920583468396,
+      "grad_norm": 0.00018358287343289703,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.11021069692058347,
+      "grad_norm": 0.00017277876031585038,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.11345218800648298,
+      "grad_norm": 0.00012110326497349888,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.1166936790923825,
+      "grad_norm": 0.00024205473891925067,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.11993517017828201,
+      "grad_norm": 0.00011354075832059607,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.12317666126418152,
+      "grad_norm": 0.0005192770040594041,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.12641815235008103,
+      "grad_norm": 0.0003913133987225592,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.12965964343598055,
+      "grad_norm": 0.00033951568184420466,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.13290113452188007,
+      "grad_norm": 0.0006607458344660699,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.13614262560777957,
+      "grad_norm": 0.00010146438580704853,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.1393841166936791,
+      "grad_norm": 0.00011652489774860442,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.1426256077795786,
+      "grad_norm": 0.0008265106589533389,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.1458670988654781,
+      "grad_norm": 0.00017233270045835525,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.14910858995137763,
+      "grad_norm": 0.0009055504924617708,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.15235008103727715,
+      "grad_norm": 0.0006764665013179183,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.15559157212317667,
+      "grad_norm": 0.0003485048655420542,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.15883306320907617,
+      "grad_norm": 9.563385538058355e-05,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.1620745542949757,
+      "grad_norm": 0.0006619396153837442,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.1620745542949757,
+      "eval_loss": 6.914133336977102e-07,
+      "eval_runtime": 59.8999,
+      "eval_samples_per_second": 34.708,
+      "eval_steps_per_second": 4.341,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null