Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22d23155ccbff0e4fe36910397735570d4d4c6e176f8c83ba56b5892554aeed5
+oid sha256:080cbad3934f5f9921e75f7b48b97289374df9e759fac31d258942cd274ecb09
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a98b1f1696989013e2c21051d5a59f92b75c0d5a5b148f576b639128ddb0f631
+oid sha256:9fa241c6d6b5cbb5275356cfeca1febdee0bc5f35c71d0de76f998f16015e9cf
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e548b6da801e7ff142902652ab119029b4077272a832275abe76a1178a875c61
+oid sha256:22cb67b983042bc28f2680c1e710edf2d26d300b14652a1bf0b416ec8182058f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b7295d0dc45e03678fd5a047b5dc4afb2813472336498e18ef124e47b6ccd72
+oid sha256:52cae3e92a1b9b06ef87ff98e1c3ef6a1b822d6302c61670df9561416b3057e6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:462105510cc09b10ff0704163dfcc7260442930b7c0e4ea929c1cecd2aa7056c
+oid sha256:c5972103896842fb9fa41980ca8045b82cd9e925b3735305be8aa9b99e33deaa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3c9966e6923ced444cbdb1340e21f99b920a5d6eb26f3eb9c714fb830f79bcd
+oid sha256:e5e12da69c4eeb43b9d008fcfe07cbc6f43dc7aab9da000d8fd8ba511dc986e7
 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": 0.3243732452392578,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.041275410174388606,
+  "best_metric": 0.29708796739578247,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08255082034877721,
   "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": 26.798,
       "eval_steps_per_second": 3.355,
       "step": 25
+    },
+    {
+      "epoch": 0.042926426581364155,
+      "grad_norm": 0.10008738189935684,
+      "learning_rate": 5e-05,
+      "loss": 0.2265,
+      "step": 26
+    },
+    {
+      "epoch": 0.0445774429883397,
+      "grad_norm": 0.11355409026145935,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3318,
+      "step": 27
+    },
+    {
+      "epoch": 0.04622845939531524,
+      "grad_norm": 0.09922956675291061,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3443,
+      "step": 28
+    },
+    {
+      "epoch": 0.04787947580229079,
+      "grad_norm": 0.08054020255804062,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3249,
+      "step": 29
+    },
+    {
+      "epoch": 0.04953049220926633,
+      "grad_norm": 0.08450499176979065,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3489,
+      "step": 30
+    },
+    {
+      "epoch": 0.05118150861624187,
+      "grad_norm": 0.09624389559030533,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3536,
+      "step": 31
+    },
+    {
+      "epoch": 0.05283252502321742,
+      "grad_norm": 0.10854283720254898,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3573,
+      "step": 32
+    },
+    {
+      "epoch": 0.05448354143019296,
+      "grad_norm": 0.09736617654561996,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3333,
+      "step": 33
+    },
+    {
+      "epoch": 0.05613455783716851,
+      "grad_norm": 0.0933280810713768,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.329,
+      "step": 34
+    },
+    {
+      "epoch": 0.05778557424414405,
+      "grad_norm": 0.10208204388618469,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2832,
+      "step": 35
+    },
+    {
+      "epoch": 0.05943659065111959,
+      "grad_norm": 0.08625288307666779,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1621,
+      "step": 36
+    },
+    {
+      "epoch": 0.06108760705809514,
+      "grad_norm": 0.08310309797525406,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1118,
+      "step": 37
+    },
+    {
+      "epoch": 0.06273862346507068,
+      "grad_norm": 0.08370844274759293,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2181,
+      "step": 38
+    },
+    {
+      "epoch": 0.06438963987204623,
+      "grad_norm": 0.08878277242183685,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2772,
+      "step": 39
+    },
+    {
+      "epoch": 0.06604065627902177,
+      "grad_norm": 0.09928658604621887,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3036,
+      "step": 40
+    },
+    {
+      "epoch": 0.06769167268599732,
+      "grad_norm": 0.08427450805902481,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3139,
+      "step": 41
+    },
+    {
+      "epoch": 0.06934268909297286,
+      "grad_norm": 0.08152101188898087,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3079,
+      "step": 42
+    },
+    {
+      "epoch": 0.0709937054999484,
+      "grad_norm": 0.09090898931026459,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3204,
+      "step": 43
+    },
+    {
+      "epoch": 0.07264472190692395,
+      "grad_norm": 0.08596403151750565,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3383,
+      "step": 44
+    },
+    {
+      "epoch": 0.07429573831389949,
+      "grad_norm": 0.07474559545516968,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3143,
+      "step": 45
+    },
+    {
+      "epoch": 0.07594675472087505,
+      "grad_norm": 0.07625479996204376,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3256,
+      "step": 46
+    },
+    {
+      "epoch": 0.07759777112785059,
+      "grad_norm": 0.08517799526453018,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3103,
+      "step": 47
+    },
+    {
+      "epoch": 0.07924878753482613,
+      "grad_norm": 0.08896566182374954,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2409,
+      "step": 48
+    },
+    {
+      "epoch": 0.08089980394180167,
+      "grad_norm": 0.07853224873542786,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1056,
+      "step": 49
+    },
+    {
+      "epoch": 0.08255082034877721,
+      "grad_norm": 0.21440893411636353,
+      "learning_rate": 0.0,
+      "loss": 0.3215,
+      "step": 50
+    },
+    {
+      "epoch": 0.08255082034877721,
+      "eval_loss": 0.29708796739578247,
+      "eval_runtime": 152.8033,
+      "eval_samples_per_second": 26.708,
+      "eval_steps_per_second": 3.344,
+      "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": 3.127523877752668e+17,
+  "total_flos": 6.299421435609743e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null