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:f47e42b362ed56bdf483bdc988fccadcffa16c8ea56750599888696f3b089d44
+oid sha256:30ead605a9a817d7c038ed7d5e84dc86d3ce6af2e6f26892e56eb859b65ad6af
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27cedb782c97afa2f4ee60b1bf30be0ea2d35d9e92c377fdc76cb506d4a7f334
+oid sha256:704b582509407f12980d5724789d533c4aa16020392f2606455cdb20552ae01f
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2399f5d3aca3aeb6d996b65307b4efe36759ea5d6daccbb743a2abd8643631c5
+oid sha256:00553df14a27ac71379a0ae3ad02586ee64960f6a9f325f3917bd59e23b64c77
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e541a94286f7925995b2a337f7da41c6794a444355dbb60b10424702f17542
+oid sha256:81e6de750f04f3f90f8df7387650a7eaf2b8e1ad43fb293835038ea26763acb2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7593304440055f9b3f24d3e62e5bb35221904a4a5cda4f188da9e01106bb336
+oid sha256:c1e4779396be6e622b4919af598492707aa94e6ebace22de461cb46dca3a75c5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b562bc2436246791701dd54a13da9146d78ffa50a55a706566c2d2c0faaf78ea
+oid sha256:20974f4a1c6ac3f4d8f193131db18916fd8ff8ba35bf0c83ed196e403259d84f
 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": 0.16990284621715546,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5673758865248227,
+  "best_metric": 0.09525119513273239,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1347517730496455,
   "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": 28.572,
       "eval_steps_per_second": 3.656,
       "step": 25
+    },
+    {
+      "epoch": 0.5900709219858156,
+      "grad_norm": 1.0504887104034424,
+      "learning_rate": 5e-05,
+      "loss": 0.1402,
+      "step": 26
+    },
+    {
+      "epoch": 0.6127659574468085,
+      "grad_norm": 0.6791476607322693,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1174,
+      "step": 27
+    },
+    {
+      "epoch": 0.6354609929078014,
+      "grad_norm": 0.574073851108551,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1246,
+      "step": 28
+    },
+    {
+      "epoch": 0.6581560283687943,
+      "grad_norm": 0.8718014359474182,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1079,
+      "step": 29
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.8603816032409668,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1175,
+      "step": 30
+    },
+    {
+      "epoch": 0.7035460992907802,
+      "grad_norm": 0.7203976511955261,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1024,
+      "step": 31
+    },
+    {
+      "epoch": 0.7262411347517731,
+      "grad_norm": 0.6164019703865051,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0965,
+      "step": 32
+    },
+    {
+      "epoch": 0.7489361702127659,
+      "grad_norm": 0.4194211959838867,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0835,
+      "step": 33
+    },
+    {
+      "epoch": 0.7716312056737589,
+      "grad_norm": 1.5366965532302856,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3735,
+      "step": 34
+    },
+    {
+      "epoch": 0.7943262411347518,
+      "grad_norm": 0.730464518070221,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0878,
+      "step": 35
+    },
+    {
+      "epoch": 0.8170212765957446,
+      "grad_norm": 0.671379566192627,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0951,
+      "step": 36
+    },
+    {
+      "epoch": 0.8397163120567376,
+      "grad_norm": 0.6115317344665527,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0982,
+      "step": 37
+    },
+    {
+      "epoch": 0.8624113475177305,
+      "grad_norm": 0.5566378235816956,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0809,
+      "step": 38
+    },
+    {
+      "epoch": 0.8851063829787233,
+      "grad_norm": 0.5277712345123291,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0827,
+      "step": 39
+    },
+    {
+      "epoch": 0.9078014184397163,
+      "grad_norm": 0.65236896276474,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0913,
+      "step": 40
+    },
+    {
+      "epoch": 0.9304964539007092,
+      "grad_norm": 0.4440590441226959,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0578,
+      "step": 41
+    },
+    {
+      "epoch": 0.9531914893617022,
+      "grad_norm": 0.6070952415466309,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0818,
+      "step": 42
+    },
+    {
+      "epoch": 0.975886524822695,
+      "grad_norm": 0.5152663588523865,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0693,
+      "step": 43
+    },
+    {
+      "epoch": 0.9985815602836879,
+      "grad_norm": 0.532758891582489,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0815,
+      "step": 44
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 5.1196417808532715,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6883,
+      "step": 45
+    },
+    {
+      "epoch": 1.0439716312056737,
+      "grad_norm": 1.095219373703003,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1155,
+      "step": 46
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.7534624934196472,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0801,
+      "step": 47
+    },
+    {
+      "epoch": 1.0893617021276596,
+      "grad_norm": 1.4827603101730347,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0699,
+      "step": 48
+    },
+    {
+      "epoch": 1.1120567375886525,
+      "grad_norm": 1.102303385734558,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0714,
+      "step": 49
+    },
+    {
+      "epoch": 1.1347517730496455,
+      "grad_norm": 0.5766385197639465,
+      "learning_rate": 0.0,
+      "loss": 0.0585,
+      "step": 50
+    },
+    {
+      "epoch": 1.1347517730496455,
+      "eval_loss": 0.09525119513273239,
+      "eval_runtime": 10.142,
+      "eval_samples_per_second": 29.284,
+      "eval_steps_per_second": 3.747,
+      "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": 3.1688050632923546e+17,
+  "total_flos": 6.212826358674883e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null