Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848a524531caa4e11419dd9f3a40f09b50a70595287b686efad1b7229be8972b
+oid sha256:b4430b38ce64083146d9128644b5b7ded0244c1fc3774e3775dd199dc2466472
 size 578923560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241ba3a342a5bdcb131614a18fd3cfa233d16c589ab027e683dad5ad71cc543e
+oid sha256:3cd1df9ec6950c33b5ed46ed5daeda6a78c5a264dae8414b87b930e5f1a67812
 size 1158239442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48bb3204bc101a38c038d0bf99e55243e521edf9dab9a5a61025d4766f582cc
+oid sha256:c0c2247e01eb7bf6f93fe03f12c01386c0207526b5990c39229e2a91fec11610
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6eed008e4b8325bd0cb0fbda3cca6311b14ad45223277b30ccb50d5316f5141
+oid sha256:3afe595f3fe7831d10d7d72a74650ae1649dcd6909d369ee6b9fc49da351d0ca
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e9ccb5ed95fd1751fe14c4098151e6f0b8d3bb570d6005b8c2b65c23f70525
+oid sha256:901a984b700660af49ed4306aba0c72e4aa00f9cdda5aa6363692cbf48917da1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f3f7f69eb0c65b7decf3939e2f5b1bb319946249bcf799a07c2881fc0a3a6a2
+oid sha256:08e4aa49208e120d453092cebc041f5475048d845193374e3591826e944a162d
 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": 0.888064980506897,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5805515239477503,
+  "best_metric": 0.8603118658065796,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1611030478955007,
   "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": 20.257,
       "eval_steps_per_second": 2.584,
       "step": 25
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "grad_norm": 0.5614883303642273,
+      "learning_rate": 5e-05,
+      "loss": 0.8565,
+      "step": 26
+    },
+    {
+      "epoch": 0.6269956458635704,
+      "grad_norm": 0.6048403978347778,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8667,
+      "step": 27
+    },
+    {
+      "epoch": 0.6502177068214804,
+      "grad_norm": 0.5841188430786133,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.89,
+      "step": 28
+    },
+    {
+      "epoch": 0.6734397677793904,
+      "grad_norm": 0.5607112646102905,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8729,
+      "step": 29
+    },
+    {
+      "epoch": 0.6966618287373004,
+      "grad_norm": 0.5376509428024292,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8794,
+      "step": 30
+    },
+    {
+      "epoch": 0.7198838896952104,
+      "grad_norm": 0.5627703666687012,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8813,
+      "step": 31
+    },
+    {
+      "epoch": 0.7431059506531205,
+      "grad_norm": 0.6090062260627747,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.841,
+      "step": 32
+    },
+    {
+      "epoch": 0.7663280116110305,
+      "grad_norm": 0.5763826966285706,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8806,
+      "step": 33
+    },
+    {
+      "epoch": 0.7895500725689405,
+      "grad_norm": 0.6495899558067322,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8241,
+      "step": 34
+    },
+    {
+      "epoch": 0.8127721335268505,
+      "grad_norm": 0.5492468476295471,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8429,
+      "step": 35
+    },
+    {
+      "epoch": 0.8359941944847605,
+      "grad_norm": 0.519008457660675,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8832,
+      "step": 36
+    },
+    {
+      "epoch": 0.8592162554426706,
+      "grad_norm": 0.5007856488227844,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8834,
+      "step": 37
+    },
+    {
+      "epoch": 0.8824383164005806,
+      "grad_norm": 0.5180608034133911,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8838,
+      "step": 38
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 0.5399318337440491,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.855,
+      "step": 39
+    },
+    {
+      "epoch": 0.9288824383164006,
+      "grad_norm": 0.577284574508667,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8981,
+      "step": 40
+    },
+    {
+      "epoch": 0.9521044992743106,
+      "grad_norm": 0.6111936569213867,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8761,
+      "step": 41
+    },
+    {
+      "epoch": 0.9753265602322206,
+      "grad_norm": 0.5520212650299072,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8957,
+      "step": 42
+    },
+    {
+      "epoch": 0.9985486211901307,
+      "grad_norm": 0.5935046672821045,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8572,
+      "step": 43
+    },
+    {
+      "epoch": 1.0217706821480406,
+      "grad_norm": 2.43267560005188,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8794,
+      "step": 44
+    },
+    {
+      "epoch": 1.0449927431059507,
+      "grad_norm": 0.47028273344039917,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7591,
+      "step": 45
+    },
+    {
+      "epoch": 1.0682148040638606,
+      "grad_norm": 0.48551949858665466,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8037,
+      "step": 46
+    },
+    {
+      "epoch": 1.0914368650217707,
+      "grad_norm": 0.4666672348976135,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8321,
+      "step": 47
+    },
+    {
+      "epoch": 1.1146589259796806,
+      "grad_norm": 0.47201839089393616,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7327,
+      "step": 48
+    },
+    {
+      "epoch": 1.1378809869375908,
+      "grad_norm": 0.5046037435531616,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7715,
+      "step": 49
+    },
+    {
+      "epoch": 1.1611030478955007,
+      "grad_norm": 0.5255216956138611,
+      "learning_rate": 0.0,
+      "loss": 0.8312,
+      "step": 50
+    },
+    {
+      "epoch": 1.1611030478955007,
+      "eval_loss": 0.8603118658065796,
+      "eval_runtime": 14.3151,
+      "eval_samples_per_second": 20.258,
+      "eval_steps_per_second": 2.585,
+      "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": 5.270391176791327e+17,
+  "total_flos": 1.0547313194953605e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null