Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621bc95ad03f4c88feed88fed6a1354f0b7280b677fe4fffd9a5a0fadad4d78e
+oid sha256:f90732d95f61647712fd9aaf41f20d0fc290bc93f6e7f33ceff75c2ef7db5c79
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec105e40333d3cd8b463f549d2357c8c2a4474c6c85f91b9996fffdf0abb996
+oid sha256:70346f37ffedd0a59f788469ff9b6c9fa3085171565ebd67d6b37d0697889259
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed78196928f9981c36baba3e4783d3045f83b4ae2a681b5169822ace1086ac8
+oid sha256:aad6a49caf3b13dc28b8df31e31b7b1939d04c46aef6753c8908441eb0061d08
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faac1eef4b3a4873ab366fa720d15397ab685b96d9d88a66a96b25a9e89b430c
+oid sha256:0d7ae916f94808f77165cc48f9cf96a91a98efb3aa1e4fee4c425886427ae26b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797be33b8e43cd615514df9fb734d4d20d5b946c8c92db137379d5d94c0da016
+oid sha256:79e7718edcbe6e0ae2a564a1867af334b630310338fe5ae0e8a31f82184bb58e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:054678afacfc60051c8380d0be448c3cbccc140ed10b512841ddf1b10e15c098
+oid sha256:3ee3511b7ad6892c794e4d90bff5605b777afbc099467182cb9700af883a7bd6
 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": 2.1838388442993164,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3194888178913738,
+  "best_metric": 1.9678517580032349,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6389776357827476,
   "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": 49.711,
       "eval_steps_per_second": 6.226,
       "step": 25
+    },
+    {
+      "epoch": 0.33226837060702874,
+      "grad_norm": 3.169137716293335,
+      "learning_rate": 5e-05,
+      "loss": 2.7858,
+      "step": 26
+    },
+    {
+      "epoch": 0.3450479233226837,
+      "grad_norm": 3.18146014213562,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.6343,
+      "step": 27
+    },
+    {
+      "epoch": 0.35782747603833864,
+      "grad_norm": 2.7009081840515137,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.3969,
+      "step": 28
+    },
+    {
+      "epoch": 0.3706070287539936,
+      "grad_norm": 2.587928056716919,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.4911,
+      "step": 29
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 2.225165367126465,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.435,
+      "step": 30
+    },
+    {
+      "epoch": 0.3961661341853035,
+      "grad_norm": 2.1750922203063965,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.2844,
+      "step": 31
+    },
+    {
+      "epoch": 0.40894568690095845,
+      "grad_norm": 2.649970531463623,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.2681,
+      "step": 32
+    },
+    {
+      "epoch": 0.4217252396166134,
+      "grad_norm": 2.4825990200042725,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.1948,
+      "step": 33
+    },
+    {
+      "epoch": 0.43450479233226835,
+      "grad_norm": 2.7616539001464844,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0973,
+      "step": 34
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 2.5977234840393066,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8398,
+      "step": 35
+    },
+    {
+      "epoch": 0.46006389776357826,
+      "grad_norm": 2.591003656387329,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4759,
+      "step": 36
+    },
+    {
+      "epoch": 0.4728434504792332,
+      "grad_norm": 3.1910948753356934,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0956,
+      "step": 37
+    },
+    {
+      "epoch": 0.48562300319488816,
+      "grad_norm": 2.328935146331787,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2579,
+      "step": 38
+    },
+    {
+      "epoch": 0.4984025559105431,
+      "grad_norm": 1.9119290113449097,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.339,
+      "step": 39
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 2.0242035388946533,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.3039,
+      "step": 40
+    },
+    {
+      "epoch": 0.5239616613418531,
+      "grad_norm": 2.0701210498809814,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.4307,
+      "step": 41
+    },
+    {
+      "epoch": 0.536741214057508,
+      "grad_norm": 1.8572293519973755,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2061,
+      "step": 42
+    },
+    {
+      "epoch": 0.549520766773163,
+      "grad_norm": 2.0586934089660645,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.3343,
+      "step": 43
+    },
+    {
+      "epoch": 0.5623003194888179,
+      "grad_norm": 2.266606092453003,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.4235,
+      "step": 44
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 2.0915160179138184,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.1905,
+      "step": 45
+    },
+    {
+      "epoch": 0.5878594249201278,
+      "grad_norm": 2.243063449859619,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.0259,
+      "step": 46
+    },
+    {
+      "epoch": 0.6006389776357828,
+      "grad_norm": 2.2916998863220215,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.8449,
+      "step": 47
+    },
+    {
+      "epoch": 0.6134185303514377,
+      "grad_norm": 2.2355592250823975,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5529,
+      "step": 48
+    },
+    {
+      "epoch": 0.6261980830670927,
+      "grad_norm": 2.450639009475708,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5336,
+      "step": 49
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 2.254504680633545,
+      "learning_rate": 0.0,
+      "loss": 0.4683,
+      "step": 50
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "eval_loss": 1.9678517580032349,
+      "eval_runtime": 10.6005,
+      "eval_samples_per_second": 49.715,
+      "eval_steps_per_second": 6.226,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null