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:fcb14aa78c5ed9cbb0a350c56420d0c6ebeb14ee575adfb4b0c86341832ff1fe
+oid sha256:41893bb8250a26abf45ba78cb341e62c8bed89fd8ede85ebac1b51a137b0b402
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab92a74a8b0ded0f61071c9e53773917537ae69006d18f36fafbb94d09e7730c
+oid sha256:1db2271d58a346676a75f100f1969a46dbbc2695056f0859926fd6fb861fd28b
 size 1101572914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e000e41d0f3601590a27af4933955fff41de65cd3443c80edaf6b69d5a959e
+oid sha256:1a0a00087eb3c73565a5e7659050eec3c28004753253073e8a768d0d68a1103a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ec54ba2bb3e3177d50d11f10e77cd9d81a6f23f2eccdd2308f4dcbee8338ed
+oid sha256:ff9c64feeb3508ebd014c93f61624dae021b83b994a76220fe573db67fd1dbd8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca8f33fb3e9e205c8d8336f89c6a908e0356295dd4a53762dc86b5e8d919efe
+oid sha256:853d5c9f961d2afca8720b3cf594a48fca77e0a43dd1e97de32f40ad0cd386b2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f198bdd3dc62f137990ee555502b2f36750ceef3232c5c4aa76222cc8fc0bbe
+oid sha256:90f9859ffacad44f2f7f635bc9f1c3c8ff497e8a7ea14c60606236503011310b
 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": 0.8958792090415955,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1189767995240928,
+  "best_metric": 0.8883944749832153,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2379535990481856,
   "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": 20.284,
       "eval_steps_per_second": 2.535,
       "step": 25
+    },
+    {
+      "epoch": 0.12373587150505651,
+      "grad_norm": 0.06783010810613632,
+      "learning_rate": 5e-05,
+      "loss": 0.9153,
+      "step": 26
+    },
+    {
+      "epoch": 0.12849494348602022,
+      "grad_norm": 0.07227343320846558,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8956,
+      "step": 27
+    },
+    {
+      "epoch": 0.13325401546698393,
+      "grad_norm": 0.07904611527919769,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9182,
+      "step": 28
+    },
+    {
+      "epoch": 0.13801308744794766,
+      "grad_norm": 0.09701425582170486,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9184,
+      "step": 29
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.08786777406930923,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9125,
+      "step": 30
+    },
+    {
+      "epoch": 0.14753123140987506,
+      "grad_norm": 0.09096773713827133,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9311,
+      "step": 31
+    },
+    {
+      "epoch": 0.1522903033908388,
+      "grad_norm": 0.11408884078264236,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.9289,
+      "step": 32
+    },
+    {
+      "epoch": 0.1570493753718025,
+      "grad_norm": 0.15218205749988556,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9567,
+      "step": 33
+    },
+    {
+      "epoch": 0.1618084473527662,
+      "grad_norm": 0.20700477063655853,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9074,
+      "step": 34
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.22459229826927185,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8929,
+      "step": 35
+    },
+    {
+      "epoch": 0.17132659131469363,
+      "grad_norm": 0.32070913910865784,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8587,
+      "step": 36
+    },
+    {
+      "epoch": 0.17608566329565734,
+      "grad_norm": 0.32868361473083496,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.739,
+      "step": 37
+    },
+    {
+      "epoch": 0.18084473527662107,
+      "grad_norm": 0.07443515211343765,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8533,
+      "step": 38
+    },
+    {
+      "epoch": 0.18560380725758477,
+      "grad_norm": 0.06598573178052902,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8563,
+      "step": 39
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 0.07651586085557938,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8885,
+      "step": 40
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.07768841832876205,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8773,
+      "step": 41
+    },
+    {
+      "epoch": 0.1998810232004759,
+      "grad_norm": 0.07910151034593582,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8896,
+      "step": 42
+    },
+    {
+      "epoch": 0.2046400951814396,
+      "grad_norm": 0.08720927685499191,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8922,
+      "step": 43
+    },
+    {
+      "epoch": 0.20939916716240334,
+      "grad_norm": 0.09212902188301086,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9412,
+      "step": 44
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.10514264553785324,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9794,
+      "step": 45
+    },
+    {
+      "epoch": 0.21891731112433074,
+      "grad_norm": 0.11232054978609085,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9759,
+      "step": 46
+    },
+    {
+      "epoch": 0.22367638310529447,
+      "grad_norm": 0.12903393805027008,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9303,
+      "step": 47
+    },
+    {
+      "epoch": 0.22843545508625818,
+      "grad_norm": 0.1691906899213791,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9317,
+      "step": 48
+    },
+    {
+      "epoch": 0.23319452706722188,
+      "grad_norm": 0.257378488779068,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8242,
+      "step": 49
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.3668021261692047,
+      "learning_rate": 0.0,
+      "loss": 0.8088,
+      "step": 50
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.8883944749832153,
+      "eval_runtime": 69.8325,
+      "eval_samples_per_second": 20.277,
+      "eval_steps_per_second": 2.535,
+      "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": 5.555785010511872e+17,
+  "total_flos": 1.1111570021023744e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null