Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b2424a71cea18de581f78b96b7eb168655bfc1e32aabaac7527d5ba405dcb7a
+oid sha256:5b94f932d12b843419a49a74e1323eb97903457e3e7b00c9593bc670ab852b9a
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfc5697c657b67d25983201b7bd9e2e79ff1d7b3db9eca7a256d435aef7cf9e9
+oid sha256:b6b919fbc595adb6b5da7de93da0fbc7b46ffacaa95b8da1ba92e71818b17237
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d05cda5c9dc6d3ed46c7a03219972bf7ef81079ca3d8a728c7ab4833f02fd0
+oid sha256:d32af183c0e92aa107384c13951b90bec47c74d076a9a9d79662ce0d1e8bd1b6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e7a6f39dc2cb60786f2a6cce8e3a7b19e2137fcc580bc70abb54ef0f3ee5837
+oid sha256:67f1eb4bf3e99c9816add38cbce08fff9ffcf4ece0dc0175666c986499f35077
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bc38fe83bbb498992167f0781e677fe4556c4cbed9e9a97627fa0bd74965ee6
+oid sha256:a0ffe98311bc66a0f61b67df99e904e2faf13113b871a73a5baa7f7cdb8e2b9f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7b5f99c468397a73527b2881efdcf29974de5c1ce7775d362f9bcbe881e8649
+oid sha256:78029acfc9f170953dcea2b44a11e591e9d4055b2b8cbaf2b3aa62309a3d6c53
 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": 10.375181198120117,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0345214464486062,
+  "best_metric": 10.3732271194458,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0690428928972124,
   "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": 882.34,
       "eval_steps_per_second": 110.315,
       "step": 25
+    },
+    {
+      "epoch": 0.03590230430655045,
+      "grad_norm": 0.04664011299610138,
+      "learning_rate": 5e-05,
+      "loss": 10.3719,
+      "step": 26
+    },
+    {
+      "epoch": 0.03728316216449469,
+      "grad_norm": 0.05778327211737633,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.375,
+      "step": 27
+    },
+    {
+      "epoch": 0.03866402002243894,
+      "grad_norm": 0.058514900505542755,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3731,
+      "step": 28
+    },
+    {
+      "epoch": 0.04004487788038319,
+      "grad_norm": 0.05111503601074219,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3747,
+      "step": 29
+    },
+    {
+      "epoch": 0.04142573573832744,
+      "grad_norm": 0.05608419328927994,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3708,
+      "step": 30
+    },
+    {
+      "epoch": 0.04280659359627168,
+      "grad_norm": 0.05180015042424202,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3723,
+      "step": 31
+    },
+    {
+      "epoch": 0.04418745145421593,
+      "grad_norm": 0.05850755050778389,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3715,
+      "step": 32
+    },
+    {
+      "epoch": 0.04556830931216018,
+      "grad_norm": 0.06536441296339035,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3722,
+      "step": 33
+    },
+    {
+      "epoch": 0.04694916717010443,
+      "grad_norm": 0.07440488785505295,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.371,
+      "step": 34
+    },
+    {
+      "epoch": 0.04833002502804867,
+      "grad_norm": 0.05948636308312416,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3782,
+      "step": 35
+    },
+    {
+      "epoch": 0.04971088288599292,
+      "grad_norm": 0.07729078829288483,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3717,
+      "step": 36
+    },
+    {
+      "epoch": 0.05109174074393717,
+      "grad_norm": 0.08918135613203049,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3685,
+      "step": 37
+    },
+    {
+      "epoch": 0.05247259860188142,
+      "grad_norm": 0.07335370033979416,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3754,
+      "step": 38
+    },
+    {
+      "epoch": 0.053853456459825665,
+      "grad_norm": 0.06451977044343948,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3683,
+      "step": 39
+    },
+    {
+      "epoch": 0.055234314317769914,
+      "grad_norm": 0.060118626803159714,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3729,
+      "step": 40
+    },
+    {
+      "epoch": 0.056615172175714164,
+      "grad_norm": 0.07454778999090195,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3741,
+      "step": 41
+    },
+    {
+      "epoch": 0.05799603003365841,
+      "grad_norm": 0.05518777668476105,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3729,
+      "step": 42
+    },
+    {
+      "epoch": 0.059376887891602656,
+      "grad_norm": 0.07119714468717575,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3775,
+      "step": 43
+    },
+    {
+      "epoch": 0.060757745749546906,
+      "grad_norm": 0.05778723955154419,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3726,
+      "step": 44
+    },
+    {
+      "epoch": 0.062138603607491155,
+      "grad_norm": 0.06477804481983185,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3738,
+      "step": 45
+    },
+    {
+      "epoch": 0.0635194614654354,
+      "grad_norm": 0.05684743449091911,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3747,
+      "step": 46
+    },
+    {
+      "epoch": 0.06490031932337965,
+      "grad_norm": 0.07884101569652557,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.372,
+      "step": 47
+    },
+    {
+      "epoch": 0.0662811771813239,
+      "grad_norm": 0.08536732941865921,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3673,
+      "step": 48
+    },
+    {
+      "epoch": 0.06766203503926814,
+      "grad_norm": 0.08748302608728409,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3732,
+      "step": 49
+    },
+    {
+      "epoch": 0.0690428928972124,
+      "grad_norm": 0.09697441756725311,
+      "learning_rate": 0.0,
+      "loss": 10.3802,
+      "step": 50
+    },
+    {
+      "epoch": 0.0690428928972124,
+      "eval_loss": 10.3732271194458,
+      "eval_runtime": 5.4793,
+      "eval_samples_per_second": 890.444,
+      "eval_steps_per_second": 111.328,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null