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:bb0809b3231ae2f5f4538ee2cc89834ae56d1bf82fa0078d9bbb69fe85329c4e
+oid sha256:27ddb08cfc06b6e6e72c83349771415e36ce418c42b11b1b6ab86d344da73509
 size 116744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d841a8091e2081fd92f1b94095eadf2fc9117539770f519408b8d40e11e7db0e
+oid sha256:d2c7022d6970c829c327b0881db03bdd0617eb7a613c93ad2c57a9c28d26d16a
 size 243310

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5becd69b928f760cbad8d38057cc5adccf0f9da02cc5e9a3fcde2020e3171777
+oid sha256:8b66eee4a837929ce2ad1eef845a816b883dae23161ae63a87655b990a22b719
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97853ccc6263aab55e6cbb8496f1e99b9abe2985c3208a54a97fa0b4b3fd6113
+oid sha256:506b794a28ffd40ee45f3615dcb20278d4a08aa6d4eebd36e97d0d62fb4b119d
 size 14512

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": 10.366927146911621,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0655307994757536,
+  "best_metric": 10.362140655517578,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1310615989515072,
   "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": 285.191,
       "eval_steps_per_second": 142.651,
       "step": 25
+    },
+    {
+      "epoch": 0.06815203145478375,
+      "grad_norm": 0.1623561531305313,
+      "learning_rate": 5e-05,
+      "loss": 10.3683,
+      "step": 26
+    },
+    {
+      "epoch": 0.07077326343381389,
+      "grad_norm": 0.17901892960071564,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3674,
+      "step": 27
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.1762312948703766,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3656,
+      "step": 28
+    },
+    {
+      "epoch": 0.07601572739187418,
+      "grad_norm": 0.1903190165758133,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3669,
+      "step": 29
+    },
+    {
+      "epoch": 0.07863695937090433,
+      "grad_norm": 0.1848573386669159,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3663,
+      "step": 30
+    },
+    {
+      "epoch": 0.08125819134993446,
+      "grad_norm": 0.18325059115886688,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3657,
+      "step": 31
+    },
+    {
+      "epoch": 0.08387942332896461,
+      "grad_norm": 0.1889919489622116,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3634,
+      "step": 32
+    },
+    {
+      "epoch": 0.08650065530799476,
+      "grad_norm": 0.1892346739768982,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3626,
+      "step": 33
+    },
+    {
+      "epoch": 0.0891218872870249,
+      "grad_norm": 0.19453836977481842,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3631,
+      "step": 34
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.17738911509513855,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3635,
+      "step": 35
+    },
+    {
+      "epoch": 0.09436435124508519,
+      "grad_norm": 0.16948333382606506,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3618,
+      "step": 36
+    },
+    {
+      "epoch": 0.09698558322411534,
+      "grad_norm": 0.17923924326896667,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3618,
+      "step": 37
+    },
+    {
+      "epoch": 0.09960681520314547,
+      "grad_norm": 0.1823878139257431,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3624,
+      "step": 38
+    },
+    {
+      "epoch": 0.10222804718217562,
+      "grad_norm": 0.19330978393554688,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3604,
+      "step": 39
+    },
+    {
+      "epoch": 0.10484927916120576,
+      "grad_norm": 0.17833343148231506,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3609,
+      "step": 40
+    },
+    {
+      "epoch": 0.10747051114023591,
+      "grad_norm": 0.1904785931110382,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3615,
+      "step": 41
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.19946472346782684,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.361,
+      "step": 42
+    },
+    {
+      "epoch": 0.1127129750982962,
+      "grad_norm": 0.19477544724941254,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3609,
+      "step": 43
+    },
+    {
+      "epoch": 0.11533420707732635,
+      "grad_norm": 0.18421031534671783,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3613,
+      "step": 44
+    },
+    {
+      "epoch": 0.11795543905635648,
+      "grad_norm": 0.19371140003204346,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3606,
+      "step": 45
+    },
+    {
+      "epoch": 0.12057667103538663,
+      "grad_norm": 0.2036082148551941,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3612,
+      "step": 46
+    },
+    {
+      "epoch": 0.12319790301441677,
+      "grad_norm": 0.22913643717765808,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3594,
+      "step": 47
+    },
+    {
+      "epoch": 0.1258191349934469,
+      "grad_norm": 0.2641303241252899,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3592,
+      "step": 48
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.3073554039001465,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3595,
+      "step": 49
+    },
+    {
+      "epoch": 0.1310615989515072,
+      "grad_norm": 0.3996570110321045,
+      "learning_rate": 0.0,
+      "loss": 10.3695,
+      "step": 50
+    },
+    {
+      "epoch": 0.1310615989515072,
+      "eval_loss": 10.362140655517578,
+      "eval_runtime": 9.0469,
+      "eval_samples_per_second": 284.187,
+      "eval_steps_per_second": 142.149,
+      "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": 42284875776000.0,
+  "total_flos": 84569751552000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null