Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b0593faa5d92012718da98c7f59c3347170797d0b06d5ecf0b2d92caa46ba6
+oid sha256:a4feeee63feae218500ef29cdb38dd15bf9f926f20c53962e21fac01af657fd6
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e2987cb177edd690c7fa55d0a7cea74ca0ecae17d8eae2f2b7c383046443c2
+oid sha256:069066be3080c53cbb2ef54eb2da9c449109914e91e13b2c526e16eeb5ceb167
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f1e4638e4fc1ddc72397305d9aa28bfce6667f8ef230124f8813bb545f247e
+oid sha256:c8e56324a533c9ccea5b2f857f7f48d88b55f1f92441115e7d5f370f8f6090a8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c29f038464dc1c5a45f9dd2531ba362139e22cb77565466d7b0b19878608e6
+oid sha256:00761536f05fd1f2889e9e68b806d195c2bef7938449efcfb2661c17b6fb9555
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463a79d83e704bd0cddfdcb9f1bcbd6868045c9aece412a6f83846060fd79aa7
+oid sha256:eeae482e0c1bf6289d00634ca5e8169b508ef8ab280b956b4627ab0947fd4021
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b8843cfc1a03e4a47db51937ec40dee050d06527b4b24531ebabdeafcc4370
+oid sha256:6d70a598a247c61f81c41dbde3ca1689f68c17b7146bc0ec7e448e504fd937e6
 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": 2.492065906524658,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.23952095808383234,
+  "best_metric": 2.109326124191284,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.47904191616766467,
   "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": 32.948,
       "eval_steps_per_second": 4.119,
       "step": 25
+    },
+    {
+      "epoch": 0.24910179640718563,
+      "grad_norm": 6.6661577224731445,
+      "learning_rate": 5e-05,
+      "loss": 2.0216,
+      "step": 26
+    },
+    {
+      "epoch": 0.25868263473053893,
+      "grad_norm": 6.830226898193359,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.2535,
+      "step": 27
+    },
+    {
+      "epoch": 0.2682634730538922,
+      "grad_norm": 5.6001410484313965,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.0359,
+      "step": 28
+    },
+    {
+      "epoch": 0.2778443113772455,
+      "grad_norm": 5.429553985595703,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.1816,
+      "step": 29
+    },
+    {
+      "epoch": 0.2874251497005988,
+      "grad_norm": 5.00969934463501,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8676,
+      "step": 30
+    },
+    {
+      "epoch": 0.2970059880239521,
+      "grad_norm": 6.511794567108154,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1724,
+      "step": 31
+    },
+    {
+      "epoch": 0.3065868263473054,
+      "grad_norm": 6.313398838043213,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.0962,
+      "step": 32
+    },
+    {
+      "epoch": 0.3161676646706587,
+      "grad_norm": 5.252542018890381,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9694,
+      "step": 33
+    },
+    {
+      "epoch": 0.325748502994012,
+      "grad_norm": 6.663439750671387,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3892,
+      "step": 34
+    },
+    {
+      "epoch": 0.33532934131736525,
+      "grad_norm": 6.385496139526367,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.2523,
+      "step": 35
+    },
+    {
+      "epoch": 0.3449101796407186,
+      "grad_norm": 7.271178722381592,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.374,
+      "step": 36
+    },
+    {
+      "epoch": 0.35449101796407184,
+      "grad_norm": 7.476476192474365,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.754,
+      "step": 37
+    },
+    {
+      "epoch": 0.36407185628742517,
+      "grad_norm": 5.532874584197998,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0447,
+      "step": 38
+    },
+    {
+      "epoch": 0.37365269461077844,
+      "grad_norm": 3.851936101913452,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.6564,
+      "step": 39
+    },
+    {
+      "epoch": 0.38323353293413176,
+      "grad_norm": 3.787240743637085,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.9061,
+      "step": 40
+    },
+    {
+      "epoch": 0.39281437125748503,
+      "grad_norm": 4.067002296447754,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.9444,
+      "step": 41
+    },
+    {
+      "epoch": 0.4023952095808383,
+      "grad_norm": 4.330122470855713,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.7166,
+      "step": 42
+    },
+    {
+      "epoch": 0.4119760479041916,
+      "grad_norm": 4.514286518096924,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.8661,
+      "step": 43
+    },
+    {
+      "epoch": 0.4215568862275449,
+      "grad_norm": 4.644809246063232,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9604,
+      "step": 44
+    },
+    {
+      "epoch": 0.4311377245508982,
+      "grad_norm": 4.697016716003418,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.9133,
+      "step": 45
+    },
+    {
+      "epoch": 0.4407185628742515,
+      "grad_norm": 4.961589336395264,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.8272,
+      "step": 46
+    },
+    {
+      "epoch": 0.4502994011976048,
+      "grad_norm": 4.9489665031433105,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.0222,
+      "step": 47
+    },
+    {
+      "epoch": 0.4598802395209581,
+      "grad_norm": 5.845571517944336,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.2451,
+      "step": 48
+    },
+    {
+      "epoch": 0.4694610778443114,
+      "grad_norm": 5.190147876739502,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.4345,
+      "step": 49
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 9.36916732788086,
+      "learning_rate": 0.0,
+      "loss": 2.7436,
+      "step": 50
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "eval_loss": 2.109326124191284,
+      "eval_runtime": 21.3715,
+      "eval_samples_per_second": 32.941,
+      "eval_steps_per_second": 4.118,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null