Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3f44e0054c93223b2bcde14d67276b4dfc5599cd910ad975097920dbaab366
+oid sha256:b571d861df41d198c8ee8dd283043f63aaeea4e1283cca3a246547b0df6b96b7
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a60bdb1cc01b6146b35dcd62cf6c52f7eca52fec8e7a094a1ed0137f1163c6
+oid sha256:54e193fae975fcdff055ddc93be73b9a5ab3d4ab2eeea7134bdc4ea68b857355
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1aac90f7d53314b4722c14395be160e56d2c91dd51cb60edf304b768548b426
+oid sha256:b847ef1c9bae9f9d9c599d21852e685a54c9673b712b029fea4bdecd1baf9f62
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adfca5899676853cbc920913cf25efecf5bc38bfce7953f08154d296cc3d2821
+oid sha256:8ac85a94c7f151e47884b0b37d47f9067f646fd558648b18c9fea4f5f070ddcd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06cde34a9d8e3c9f6a8db6fe50955c05a3ff11a2c96ad67eb2195c78fdc3c2c
+oid sha256:5515cc24d4b91fb88255babe4a890191d6ffe000fdd522426a7fd3556fff1a1a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02587007e4ffde9a3d6264108931e8c403cbc8b836c00bffbeec482ed0d681e6
+oid sha256:71a07af1cfccd148abeec0035a8445bdd6674de4c628ad7f45e15b0f21ee82a1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d490043b81d92f2523c5e5743bd899586cd05324668f1c6287fc78466d4341
+oid sha256:83bde02f2e7b736ca94b9c51f0320881be685bc5601886de1775bb4eb0e0862b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.0945186614990234,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2334217506631298,
+  "epoch": 3.222811671087533,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,83 @@
       "eval_samples_per_second": 7.974,
       "eval_steps_per_second": 2.073,
       "step": 25
+    },
+    {
+      "epoch": 2.3183023872679045,
+      "grad_norm": 0.08641119301319122,
+      "learning_rate": 2.7881441362933468e-05,
+      "loss": 2.8185,
+      "step": 26
+    },
+    {
+      "epoch": 2.4031830238726792,
+      "grad_norm": 0.08306525647640228,
+      "learning_rate": 2.4683696035904928e-05,
+      "loss": 2.1871,
+      "step": 27
+    },
+    {
+      "epoch": 2.4880636604774535,
+      "grad_norm": 0.06848848611116409,
+      "learning_rate": 2.1744598725070347e-05,
+      "loss": 1.7206,
+      "step": 28
+    },
+    {
+      "epoch": 2.5729442970822283,
+      "grad_norm": 0.07960382103919983,
+      "learning_rate": 1.9089224772389225e-05,
+      "loss": 2.5779,
+      "step": 29
+    },
+    {
+      "epoch": 2.6578249336870026,
+      "grad_norm": 0.08648785203695297,
+      "learning_rate": 1.674022889216737e-05,
+      "loss": 2.1333,
+      "step": 30
+    },
+    {
+      "epoch": 2.7427055702917773,
+      "grad_norm": 0.06665050983428955,
+      "learning_rate": 1.4717651889022202e-05,
+      "loss": 1.879,
+      "step": 31
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.07692303508520126,
+      "learning_rate": 1.3038749676803994e-05,
+      "loss": 2.4009,
+      "step": 32
+    },
+    {
+      "epoch": 2.9124668435013263,
+      "grad_norm": 0.10234280675649643,
+      "learning_rate": 1.1717846057223144e-05,
+      "loss": 2.1553,
+      "step": 33
+    },
+    {
+      "epoch": 3.053050397877984,
+      "grad_norm": 0.1816321313381195,
+      "learning_rate": 1.076621051422442e-05,
+      "loss": 3.9239,
+      "step": 34
+    },
+    {
+      "epoch": 3.1379310344827585,
+      "grad_norm": 0.07805649191141129,
+      "learning_rate": 1.019196206672345e-05,
+      "loss": 2.3547,
+      "step": 35
+    },
+    {
+      "epoch": 3.222811671087533,
+      "grad_norm": 0.07166720926761627,
+      "learning_rate": 1e-05,
+      "loss": 1.5117,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -221,12 +298,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.145953126492406e+17,
+  "total_flos": 5.985801431154688e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null