Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0108cadad64780633e96871d3ab69bac9c83fa17557621072508cd491099708
+oid sha256:719865b916dc66c4d799c94d6d1a7046858f7349cda0e31096b2212c63f878d1
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131ecb3c46af51e033834b7a329808d0b83e6570e092277bf6d435ee16c29050
+oid sha256:e04ab3cdb3df520b4ca43e9d1d2122712e1c3ff2a15fcc895b53ff8eb2111d9b
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40de42716ded527a0c7450fad6fab5d6bb459ea281de1a9420594b73caf2b7e9
+oid sha256:392b4eed71998652587467f22fda0a0157082f3d193822052b698291a1911853
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6fb6e348d2ae9bec3cb027a5c2fdc5c04bb7ce35b8c531d5584d075655ab86
+oid sha256:bec34512699a29a98ce3e82761bd561339b6bf1472332d165db3a829af4d9952
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091f964e5203e3c7f005847e58dbd6fcc62009017c6d39da80abfe435fe8f335
+oid sha256:c747399b8bf2dc853df742fe955d75215efe573ad7d9ceb43f635192ac4191d4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68ae244b1eb403cc5102ee2c72d1df6c99734874654c1b86e4d40bcec5cc5acc
+oid sha256:dfcc7bb0267d5c70b406b8ffe467901ae3fbba38ba89d664e11233619ae2e656
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b53322a9e0770f1aa889f3dc8eda417cbde627f634c75503b1e43849ff496ab
+oid sha256:d50872ebe2ae52bfb0e335aaa2e28a3dac724479a77b01ce7ef36e8156017c85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6919782757759094,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.048780487804878,
+  "epoch": 3.1902439024390246,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,104 @@
       "eval_samples_per_second": 29.083,
       "eval_steps_per_second": 7.562,
       "step": 25
+    },
+    {
+      "epoch": 2.126829268292683,
+      "grad_norm": 0.15212808549404144,
+      "learning_rate": 3.474083148320469e-05,
+      "loss": 0.3673,
+      "step": 26
+    },
+    {
+      "epoch": 2.204878048780488,
+      "grad_norm": 0.22316193580627441,
+      "learning_rate": 3.1406172239924584e-05,
+      "loss": 0.4834,
+      "step": 27
+    },
+    {
+      "epoch": 2.2829268292682925,
+      "grad_norm": 0.1796901971101761,
+      "learning_rate": 2.8241507066307104e-05,
+      "loss": 0.636,
+      "step": 28
+    },
+    {
+      "epoch": 2.3609756097560974,
+      "grad_norm": 0.14367538690567017,
+      "learning_rate": 2.5269637447446348e-05,
+      "loss": 0.3709,
+      "step": 29
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": 0.16765695810317993,
+      "learning_rate": 2.2511975772046403e-05,
+      "loss": 0.4021,
+      "step": 30
+    },
+    {
+      "epoch": 2.5170731707317073,
+      "grad_norm": 0.1606360524892807,
+      "learning_rate": 1.9988391055670233e-05,
+      "loss": 0.6083,
+      "step": 31
+    },
+    {
+      "epoch": 2.5951219512195123,
+      "grad_norm": 0.12848107516765594,
+      "learning_rate": 1.771706578402711e-05,
+      "loss": 0.3334,
+      "step": 32
+    },
+    {
+      "epoch": 2.6731707317073172,
+      "grad_norm": 0.17367133498191833,
+      "learning_rate": 1.5714364907746536e-05,
+      "loss": 0.4383,
+      "step": 33
+    },
+    {
+      "epoch": 2.7512195121951217,
+      "grad_norm": 0.15716971457004547,
+      "learning_rate": 1.3994717932533891e-05,
+      "loss": 0.6039,
+      "step": 34
+    },
+    {
+      "epoch": 2.8292682926829267,
+      "grad_norm": 0.1574130654335022,
+      "learning_rate": 1.257051495425121e-05,
+      "loss": 0.3731,
+      "step": 35
+    },
+    {
+      "epoch": 2.9073170731707316,
+      "grad_norm": 0.18796025216579437,
+      "learning_rate": 1.1452017387992552e-05,
+      "loss": 0.4538,
+      "step": 36
+    },
+    {
+      "epoch": 3.0341463414634147,
+      "grad_norm": 0.3865165114402771,
+      "learning_rate": 1.064728403435312e-05,
+      "loss": 1.1283,
+      "step": 37
+    },
+    {
+      "epoch": 3.1121951219512196,
+      "grad_norm": 0.12527284026145935,
+      "learning_rate": 1.0162113015586309e-05,
+      "loss": 0.3601,
+      "step": 38
+    },
+    {
+      "epoch": 3.1902439024390246,
+      "grad_norm": 0.17297080159187317,
+      "learning_rate": 1e-05,
+      "loss": 0.4422,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -221,12 +319,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.519459600243098e+16,
+  "total_flos": 1.0058973260546048e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null