Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9452f322ca3384a4e52d1934832f00fcb3906df3756c174f94b35cde211840ba
+oid sha256:ea02b41977dcbe728810af9510373e2dced42ac1d1553cfa656747c51729421e
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db849b217cb5e090274b3016e2689b94d621840424db260653d825a1f620fd6d
+oid sha256:0a06097bc3f13c8e5649cb342669c84131f5199a8788ed417fbd6cf94b782300
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb03f6e06c4f854c18200af13daa9f76836886e39e6a5928d7bb1c168c3ae31
+oid sha256:09472c02903d849a19f046181704fa3e85086097ad0dc0dc06c368eca4e25a9f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ce832add10e6bde7261d2ed7cacbed3048ca2ccc7172d9929fc563bf23dcded
+oid sha256:0cbab91a0e9028aa1322a2514ed0adaf49f81e18787d12651d4c7a242c8bd971
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86851dcae410bff46cb95c702da6376e190aa35d8fa050d4593600386b477667
+oid sha256:f87147552b1e00d6b763dcc5a5b67eef883700debe5435194b1bab70810981c7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbddf9f8c80a9e253ab1a103cc7120b4d079ad3b6eb4a7e51e1aa843a43ba3e2
+oid sha256:3f3e47be7ad69357c61b5259ec0881d5d9ce51f68cd351ea5fcf2e19e1366598
 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": 1.7455496788024902,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.1382978723404253,
+  "epoch": 3.0797872340425534,
   "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": 53.157,
       "eval_steps_per_second": 13.821,
       "step": 25
+    },
+    {
+      "epoch": 2.223404255319149,
+      "grad_norm": 0.18386214971542358,
+      "learning_rate": 2.7881441362933468e-05,
+      "loss": 0.4926,
+      "step": 26
+    },
+    {
+      "epoch": 2.3085106382978724,
+      "grad_norm": 0.2846694588661194,
+      "learning_rate": 2.4683696035904928e-05,
+      "loss": 1.9249,
+      "step": 27
+    },
+    {
+      "epoch": 2.393617021276596,
+      "grad_norm": 0.40197649598121643,
+      "learning_rate": 2.1744598725070347e-05,
+      "loss": 2.0293,
+      "step": 28
+    },
+    {
+      "epoch": 2.478723404255319,
+      "grad_norm": 0.21188139915466309,
+      "learning_rate": 1.9089224772389225e-05,
+      "loss": 0.7225,
+      "step": 29
+    },
+    {
+      "epoch": 2.5638297872340425,
+      "grad_norm": 0.25818443298339844,
+      "learning_rate": 1.674022889216737e-05,
+      "loss": 1.9215,
+      "step": 30
+    },
+    {
+      "epoch": 2.648936170212766,
+      "grad_norm": 0.4542253315448761,
+      "learning_rate": 1.4717651889022202e-05,
+      "loss": 1.9208,
+      "step": 31
+    },
+    {
+      "epoch": 2.7340425531914896,
+      "grad_norm": 0.29611721634864807,
+      "learning_rate": 1.3038749676803994e-05,
+      "loss": 1.176,
+      "step": 32
+    },
+    {
+      "epoch": 2.8191489361702127,
+      "grad_norm": 0.27275022864341736,
+      "learning_rate": 1.1717846057223144e-05,
+      "loss": 1.8955,
+      "step": 33
+    },
+    {
+      "epoch": 2.904255319148936,
+      "grad_norm": 0.6470306515693665,
+      "learning_rate": 1.076621051422442e-05,
+      "loss": 2.0274,
+      "step": 34
+    },
+    {
+      "epoch": 2.9893617021276597,
+      "grad_norm": 0.5650705695152283,
+      "learning_rate": 1.019196206672345e-05,
+      "loss": 1.638,
+      "step": 35
+    },
+    {
+      "epoch": 3.0797872340425534,
+      "grad_norm": 0.15843090415000916,
+      "learning_rate": 1e-05,
+      "loss": 1.2924,
+      "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": 3.91521434075136e+16,
+  "total_flos": 5.637908650681958e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null