Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a0eaab48ac193df31802415907fa0f640d6af08101925b0a834de31a4422943
+oid sha256:c0865b4b56419ca2ead8238b34a607cda13f8ae224ab442ac9dc05d9f5d4bb09
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:088e3c9191f258e09b2ec1a80f58a2ba94b428630e6509e0c69fa717d39c392c
+oid sha256:f13f51be6184d3115a0765b75c23536fdc4f2c0a6cc26194dfd8121e1646db0e
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746c8ace5725ad3d438e000faf387386ccc56665c7250eadabfa17b0080e291b
+oid sha256:7c9592c9881495b060eb8ea776721557f93de67e5427f88c7cd8e22cd3f50edc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:056fa6cc6db2d79d6f7ef38efc89ab23d9ac7e81508d61e12de9e7f0282d284b
+oid sha256:01242aca8f97a463b8ddb7d9e724438dd2e293ac7aa43dece004ecd34204873d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b37a68f901ea047ab33fa67cdaffc37bfe19b429cbc8bc768bdb7886d2366bc7
+oid sha256:f36653a110da9abc045e44c64eaea6b950e620bde4587ee961708b6fd1ce747f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542470bac628b56ec7385098a4f93cc5b21f76d0407bba958705a37b76b88c74
+oid sha256:18b3a82e1cdde9b7172583b9a65f8dcf9759f013894590bb24399142965bd77a
 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": 11.930814743041992,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.49566294919454773,
+  "best_metric": 11.930197715759277,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.9913258983890955,
   "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": 243.069,
       "eval_steps_per_second": 30.741,
       "step": 25
+    },
+    {
+      "epoch": 0.5154894671623296,
+      "grad_norm": 0.023722823709249496,
+      "learning_rate": 5e-05,
+      "loss": 11.9321,
+      "step": 26
+    },
+    {
+      "epoch": 0.5353159851301115,
+      "grad_norm": 0.029193179681897163,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9326,
+      "step": 27
+    },
+    {
+      "epoch": 0.5551425030978935,
+      "grad_norm": 0.029724499210715294,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9332,
+      "step": 28
+    },
+    {
+      "epoch": 0.5749690210656754,
+      "grad_norm": 0.03591114282608032,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9309,
+      "step": 29
+    },
+    {
+      "epoch": 0.5947955390334573,
+      "grad_norm": 0.03057137131690979,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9321,
+      "step": 30
+    },
+    {
+      "epoch": 0.6146220570012392,
+      "grad_norm": 0.032220229506492615,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9313,
+      "step": 31
+    },
+    {
+      "epoch": 0.6344485749690211,
+      "grad_norm": 0.032921236008405685,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9307,
+      "step": 32
+    },
+    {
+      "epoch": 0.654275092936803,
+      "grad_norm": 0.04445214569568634,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9299,
+      "step": 33
+    },
+    {
+      "epoch": 0.6741016109045849,
+      "grad_norm": 0.03545578941702843,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.93,
+      "step": 34
+    },
+    {
+      "epoch": 0.6939281288723668,
+      "grad_norm": 0.03545760363340378,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9299,
+      "step": 35
+    },
+    {
+      "epoch": 0.7137546468401487,
+      "grad_norm": 0.04920024797320366,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9295,
+      "step": 36
+    },
+    {
+      "epoch": 0.7335811648079306,
+      "grad_norm": 0.06207504868507385,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9269,
+      "step": 37
+    },
+    {
+      "epoch": 0.7534076827757125,
+      "grad_norm": 0.03247861936688423,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9312,
+      "step": 38
+    },
+    {
+      "epoch": 0.7732342007434945,
+      "grad_norm": 0.03084028698503971,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9317,
+      "step": 39
+    },
+    {
+      "epoch": 0.7930607187112764,
+      "grad_norm": 0.03489547595381737,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9312,
+      "step": 40
+    },
+    {
+      "epoch": 0.8128872366790583,
+      "grad_norm": 0.03439491242170334,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.932,
+      "step": 41
+    },
+    {
+      "epoch": 0.8327137546468402,
+      "grad_norm": 0.04392773285508156,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9317,
+      "step": 42
+    },
+    {
+      "epoch": 0.8525402726146221,
+      "grad_norm": 0.037023965269327164,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9313,
+      "step": 43
+    },
+    {
+      "epoch": 0.872366790582404,
+      "grad_norm": 0.04017459973692894,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9304,
+      "step": 44
+    },
+    {
+      "epoch": 0.8921933085501859,
+      "grad_norm": 0.034759581089019775,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9293,
+      "step": 45
+    },
+    {
+      "epoch": 0.9120198265179678,
+      "grad_norm": 0.03923869878053665,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9295,
+      "step": 46
+    },
+    {
+      "epoch": 0.9318463444857497,
+      "grad_norm": 0.04526235908269882,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9299,
+      "step": 47
+    },
+    {
+      "epoch": 0.9516728624535316,
+      "grad_norm": 0.04564972221851349,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9289,
+      "step": 48
+    },
+    {
+      "epoch": 0.9714993804213135,
+      "grad_norm": 0.047993697226047516,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9268,
+      "step": 49
+    },
+    {
+      "epoch": 0.9913258983890955,
+      "grad_norm": 0.04707922041416168,
+      "learning_rate": 0.0,
+      "loss": 11.9271,
+      "step": 50
+    },
+    {
+      "epoch": 0.9913258983890955,
+      "eval_loss": 11.930197715759277,
+      "eval_runtime": 1.3493,
+      "eval_samples_per_second": 251.982,
+      "eval_steps_per_second": 31.868,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null