Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc7a0e7b55b8aede53778a0517c0e5fbd27a99e55ae3d6facc2449243b0c81e
+oid sha256:bf8d389ec21b3c635d906ac8af15c831402df989789c5a6e00d28375f409393e
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:796ec8fd271799327e64f346919fc80f821dc549a3d1570050f0b0bba578fe6b
+oid sha256:cc9203935ce43238bb6986f308591b16b16854378821169cee2705ff2fe557be
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb99407b8c7f762fb0034c6d3f2cadb39ea4e17466a860fb021da632045b8e83
+oid sha256:ab7ea1689b1769115cb5f8193ebc89c012db84a87e90f9d403d8518330ea4747
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06bb6ae5abee75c83235d2cefe1cb8b73e744f4f5837a3a63215d739fcb981a
+oid sha256:46baed438ed1800d62df5e26951f8f58faeabeb5fc2dd656b5ba27e169ca6ce1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d7cd158b9543f102db961f6dbba5e52714a50ab3729db2c738f736453b58ed1
+oid sha256:0f2eef028618b0c7d758cfa86dfe0a91ee25173276de97fd5070f119f9119364
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57b9eb72f4572777b380d3a203a8db64f383e201fe0192501d2fc9bb516edf77
+oid sha256:7f544184735c97c8219f90ae16e6417a058337d976f710c0331970a28866a40f
 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": 0.15904709696769714,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02957267484844004,
+  "best_metric": 0.15517795085906982,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05914534969688008,
   "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": 22.298,
       "eval_steps_per_second": 2.788,
       "step": 25
+    },
+    {
+      "epoch": 0.030755581842377644,
+      "grad_norm": 0.11360311508178711,
+      "learning_rate": 5e-05,
+      "loss": 0.1298,
+      "step": 26
+    },
+    {
+      "epoch": 0.03193848883631525,
+      "grad_norm": 0.13283145427703857,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1454,
+      "step": 27
+    },
+    {
+      "epoch": 0.033121395830252844,
+      "grad_norm": 0.13941703736782074,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1489,
+      "step": 28
+    },
+    {
+      "epoch": 0.03430430282419045,
+      "grad_norm": 0.15467329323291779,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1467,
+      "step": 29
+    },
+    {
+      "epoch": 0.03548720981812805,
+      "grad_norm": 0.1567084640264511,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1547,
+      "step": 30
+    },
+    {
+      "epoch": 0.03667011681206565,
+      "grad_norm": 0.1724080890417099,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1601,
+      "step": 31
+    },
+    {
+      "epoch": 0.03785302380600325,
+      "grad_norm": 0.1829661726951599,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1651,
+      "step": 32
+    },
+    {
+      "epoch": 0.03903593079994085,
+      "grad_norm": 0.16755975782871246,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1355,
+      "step": 33
+    },
+    {
+      "epoch": 0.040218837793878456,
+      "grad_norm": 0.22333097457885742,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1725,
+      "step": 34
+    },
+    {
+      "epoch": 0.04140174478781606,
+      "grad_norm": 0.20624902844429016,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1475,
+      "step": 35
+    },
+    {
+      "epoch": 0.04258465178175366,
+      "grad_norm": 0.2575368285179138,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1906,
+      "step": 36
+    },
+    {
+      "epoch": 0.04376755877569126,
+      "grad_norm": 0.29051071405410767,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1885,
+      "step": 37
+    },
+    {
+      "epoch": 0.04495046576962886,
+      "grad_norm": 0.13400967419147491,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1131,
+      "step": 38
+    },
+    {
+      "epoch": 0.046133372763566466,
+      "grad_norm": 0.12060488760471344,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1296,
+      "step": 39
+    },
+    {
+      "epoch": 0.04731627975750407,
+      "grad_norm": 0.13372822105884552,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1443,
+      "step": 40
+    },
+    {
+      "epoch": 0.048499186751441666,
+      "grad_norm": 0.15063360333442688,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1547,
+      "step": 41
+    },
+    {
+      "epoch": 0.04968209374537927,
+      "grad_norm": 0.15621814131736755,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1441,
+      "step": 42
+    },
+    {
+      "epoch": 0.05086500073931687,
+      "grad_norm": 0.15441331267356873,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1262,
+      "step": 43
+    },
+    {
+      "epoch": 0.052047907733254475,
+      "grad_norm": 0.17183248698711395,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1568,
+      "step": 44
+    },
+    {
+      "epoch": 0.05323081472719207,
+      "grad_norm": 0.1854199767112732,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1609,
+      "step": 45
+    },
+    {
+      "epoch": 0.054413721721129675,
+      "grad_norm": 0.19609281420707703,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.159,
+      "step": 46
+    },
+    {
+      "epoch": 0.05559662871506728,
+      "grad_norm": 0.2056037038564682,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1503,
+      "step": 47
+    },
+    {
+      "epoch": 0.05677953570900488,
+      "grad_norm": 0.21327050030231476,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.141,
+      "step": 48
+    },
+    {
+      "epoch": 0.05796244270294248,
+      "grad_norm": 0.27148258686065674,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1656,
+      "step": 49
+    },
+    {
+      "epoch": 0.05914534969688008,
+      "grad_norm": 0.39363518357276917,
+      "learning_rate": 0.0,
+      "loss": 0.1781,
+      "step": 50
+    },
+    {
+      "epoch": 0.05914534969688008,
+      "eval_loss": 0.15517795085906982,
+      "eval_runtime": 255.3396,
+      "eval_samples_per_second": 22.304,
+      "eval_steps_per_second": 2.788,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null