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:bc4f46cbd1a1d41c95e4dd264eedd11c8097f5d6ec8f75f341ec931cbe204960
+oid sha256:e78485518d0a9a939ca3285b8b9e330dd952d52b5d81e822bc33287fbd1dd4d8
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4cc49b3eaef1db79e81ea3dd8a62e0cdc7a8236ed61d5b77726319c6ef0d9ef
+oid sha256:c26bb82ac90bcffda20b0a0b28c7c8b8a08e8fb34adf09910c7d9f4992707229
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a040638dd6d7b0b0bcbcffa081cfc9a4a6cf70d4142af7ee6b8add82bebcc6b7
+oid sha256:94a036c28141fe1e94f4d10c850d25450c454e205d6ac7932e4586c762882285
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2aeb9073e8ab0044be3c6c415f57936fc8d86575a16118d9e42630bc4086d7f
+oid sha256:d33709179138dd5205ed79521d65e1849c08fd93aeba54b3332394fda576223c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8bdc16b14086f1fb9258691679e4c13e5ee45604f658361606aef160bb5dd63
+oid sha256:aa0093cdaded2fce494f3149cfcc307c827a5c0e547e7b0a57b4171a06652f4a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75962c1c6281f3ec35ca71535523bcba82ea962a6ad254f219d05cfdf0df4a9e
+oid sha256:06dbc65da15d8b650b87257e90349a1538e642735bf17e84ccc883be57eeafe5
 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": 0.48176026344299316,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.136842105263158,
+  "epoch": 3.0789473684210527,
   "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": 32.422,
       "eval_steps_per_second": 8.43,
       "step": 25
+    },
+    {
+      "epoch": 2.221052631578947,
+      "grad_norm": 0.2521531283855438,
+      "learning_rate": 2.7881441362933468e-05,
+      "loss": 0.4739,
+      "step": 26
+    },
+    {
+      "epoch": 2.305263157894737,
+      "grad_norm": 0.2974882423877716,
+      "learning_rate": 2.4683696035904928e-05,
+      "loss": 0.5741,
+      "step": 27
+    },
+    {
+      "epoch": 2.389473684210526,
+      "grad_norm": 0.254207581281662,
+      "learning_rate": 2.1744598725070347e-05,
+      "loss": 0.4982,
+      "step": 28
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 0.2415657490491867,
+      "learning_rate": 1.9089224772389225e-05,
+      "loss": 0.5196,
+      "step": 29
+    },
+    {
+      "epoch": 2.557894736842105,
+      "grad_norm": 0.2914498746395111,
+      "learning_rate": 1.674022889216737e-05,
+      "loss": 0.5687,
+      "step": 30
+    },
+    {
+      "epoch": 2.6421052631578945,
+      "grad_norm": 0.24279502034187317,
+      "learning_rate": 1.4717651889022202e-05,
+      "loss": 0.4589,
+      "step": 31
+    },
+    {
+      "epoch": 2.7263157894736842,
+      "grad_norm": 0.28355467319488525,
+      "learning_rate": 1.3038749676803994e-05,
+      "loss": 0.5528,
+      "step": 32
+    },
+    {
+      "epoch": 2.8105263157894735,
+      "grad_norm": 0.23004592955112457,
+      "learning_rate": 1.1717846057223144e-05,
+      "loss": 0.4843,
+      "step": 33
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.2817566692829132,
+      "learning_rate": 1.076621051422442e-05,
+      "loss": 0.6326,
+      "step": 34
+    },
+    {
+      "epoch": 2.9789473684210526,
+      "grad_norm": 0.3518288731575012,
+      "learning_rate": 1.019196206672345e-05,
+      "loss": 0.6554,
+      "step": 35
+    },
+    {
+      "epoch": 3.0789473684210527,
+      "grad_norm": 0.27997156977653503,
+      "learning_rate": 1e-05,
+      "loss": 0.5919,
+      "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": 6.30424133917737e+16,
+  "total_flos": 9.092146379567923e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null