Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:169c8839c41a53a63e0653183ab356f7516d5a7179f67bd0e9da1c04d2243533
+oid sha256:809bf69aaa97978f4767d365b438d36ce701f6c435e183319d23016ae1e31746
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948f7ff5e6cfa7284227aedb583ca919f1843d9d4fe10a4632e47e10c46dd803
+oid sha256:cc142d1d90fc1390b680a642408b8ab8ec17c1ff5c932a102b4900559108bfb0
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1b753b9926b8ae2045cbef7140cce167fe7433b726921c2aa69762229388d5
+oid sha256:7b3b7b2cdb3f84734525b0f24330e990a1454e4617aa5d1b7733d33927fa8fd8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ea3e7c6d8f46849bef9ca653e8e84a2edc961b4cd619054adfe590a6debb8d
+oid sha256:b6a56689992d410fba7a1c2f988f1166365b613e75c657738c82860aefce2af3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adda770c1a74de064716392f5758e30f15a6cfd2b7d1522f2d17235fd8be26bd
+oid sha256:ca5a0771add369f35c022ef36659bfd1d7a314d1423d21451d9f75d63a44f03f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed053d10c93a9e3973c4886939456ce2e80d22443d87bed2a5bc85feec54dc4c
+oid sha256:2941400d84f7b777ecd670207afc661bf15e296b4247a6993f75f682e641685d
 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": 1.55069100856781,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006003211718269274,
+  "best_metric": 1.5269875526428223,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.012006423436538549,
   "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": 24.217,
       "eval_steps_per_second": 3.027,
       "step": 25
+    },
+    {
+      "epoch": 0.006243340187000045,
+      "grad_norm": 0.08969517797231674,
+      "learning_rate": 5e-05,
+      "loss": 1.2936,
+      "step": 26
+    },
+    {
+      "epoch": 0.006483468655730816,
+      "grad_norm": 0.11303842067718506,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3628,
+      "step": 27
+    },
+    {
+      "epoch": 0.006723597124461587,
+      "grad_norm": 0.12476766109466553,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.451,
+      "step": 28
+    },
+    {
+      "epoch": 0.006963725593192358,
+      "grad_norm": 0.15192772448062897,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4926,
+      "step": 29
+    },
+    {
+      "epoch": 0.007203854061923129,
+      "grad_norm": 0.1468016803264618,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.428,
+      "step": 30
+    },
+    {
+      "epoch": 0.0074439825306539,
+      "grad_norm": 0.16281750798225403,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.5421,
+      "step": 31
+    },
+    {
+      "epoch": 0.007684110999384671,
+      "grad_norm": 0.17703953385353088,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5468,
+      "step": 32
+    },
+    {
+      "epoch": 0.007924239468115442,
+      "grad_norm": 0.1892644166946411,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.5334,
+      "step": 33
+    },
+    {
+      "epoch": 0.008164367936846212,
+      "grad_norm": 0.2066446989774704,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5535,
+      "step": 34
+    },
+    {
+      "epoch": 0.008404496405576984,
+      "grad_norm": 0.22278033196926117,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6071,
+      "step": 35
+    },
+    {
+      "epoch": 0.008644624874307755,
+      "grad_norm": 0.31610944867134094,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.7292,
+      "step": 36
+    },
+    {
+      "epoch": 0.008884753343038525,
+      "grad_norm": 0.3492298722267151,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.822,
+      "step": 37
+    },
+    {
+      "epoch": 0.009124881811769297,
+      "grad_norm": 0.11775483191013336,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3414,
+      "step": 38
+    },
+    {
+      "epoch": 0.009365010280500068,
+      "grad_norm": 0.11511360853910446,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.3609,
+      "step": 39
+    },
+    {
+      "epoch": 0.009605138749230838,
+      "grad_norm": 0.14886504411697388,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3542,
+      "step": 40
+    },
+    {
+      "epoch": 0.00984526721796161,
+      "grad_norm": 0.12947678565979004,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3978,
+      "step": 41
+    },
+    {
+      "epoch": 0.01008539568669238,
+      "grad_norm": 0.14663155376911163,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4352,
+      "step": 42
+    },
+    {
+      "epoch": 0.010325524155423151,
+      "grad_norm": 0.151982843875885,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.5166,
+      "step": 43
+    },
+    {
+      "epoch": 0.010565652624153923,
+      "grad_norm": 0.1591339111328125,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.528,
+      "step": 44
+    },
+    {
+      "epoch": 0.010805781092884693,
+      "grad_norm": 0.17459267377853394,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.589,
+      "step": 45
+    },
+    {
+      "epoch": 0.011045909561615464,
+      "grad_norm": 0.1837066113948822,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5155,
+      "step": 46
+    },
+    {
+      "epoch": 0.011286038030346236,
+      "grad_norm": 0.19872833788394928,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.5935,
+      "step": 47
+    },
+    {
+      "epoch": 0.011526166499077006,
+      "grad_norm": 0.23636873066425323,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6234,
+      "step": 48
+    },
+    {
+      "epoch": 0.011766294967807777,
+      "grad_norm": 0.260368287563324,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7284,
+      "step": 49
+    },
+    {
+      "epoch": 0.012006423436538549,
+      "grad_norm": 0.39386460185050964,
+      "learning_rate": 0.0,
+      "loss": 1.8102,
+      "step": 50
+    },
+    {
+      "epoch": 0.012006423436538549,
+      "eval_loss": 1.5269875526428223,
+      "eval_runtime": 1156.4327,
+      "eval_samples_per_second": 24.261,
+      "eval_steps_per_second": 3.033,
+      "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": 5.117377125715804e+17,
+  "total_flos": 1.0234754251431608e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null