Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa242f40f668d188e11dbb4d8616605710dfd87676eb9fe938a4b884fb32b20
+oid sha256:b6696c6f611e067bb79e66781b80793a73274282a97282f006aa966cfbea7fb6
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35273a1b2ff4c2e6e0c065ea988f352814c3975b4046867aec0ac8f41ca14950
+oid sha256:6222dd08735b61bc42abef273188b447fb16c1fc1594cf3a10e5e325173057ab
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c0e8f4b614c838b27dac55a3e9668dfe900a69fd26ebb1bb3d4022bcbbead8
+oid sha256:83c8e177e0cd8f66ff32c7ed98e3e6d5d8c98d49bde07019600ada7e23decb40
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd78cca64e58239f128d6b2471c45f06e2bdbe30d4636636453ee316adfd1766
+oid sha256:c3c2cf515a8add534ac829b5c76a40910ab9a503c13277cfffa62747d4444b9d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56949786a561d9dfada81ba9ed3444e6b8ca37dc9a15ca80c97e464d87904e26
+oid sha256:bedadea56b5fe8f7fd9dff52005e887336c2ae6481987e62e040f0c4fc6d44e9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d131f504625e8d452a061cd1fae713317779aed0488c5107ed56fb43745b4362
+oid sha256:31a4093d928277b077ac95cbe8111749f91a882ed65ca015597e60222428b923
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cddcb24aadae81d07278497a6396e07c439ca4a7b8ebe0bf20ff2146c0295bff
+oid sha256:5cb4304039a2941ec395778b262c969aa296bcf9a2f204c43c675b3e30a23811
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0031893253326416,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.5660377358490565,
+  "epoch": 3.0943396226415096,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,41 @@
       "eval_samples_per_second": 7.503,
       "eval_steps_per_second": 1.951,
       "step": 25
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.18223722279071808,
+      "learning_rate": 1.4456400944391146e-05,
+      "loss": 0.9384,
+      "step": 26
+    },
+    {
+      "epoch": 2.767295597484277,
+      "grad_norm": 0.1712333709001541,
+      "learning_rate": 1.252525013612346e-05,
+      "loss": 0.8976,
+      "step": 27
+    },
+    {
+      "epoch": 2.867924528301887,
+      "grad_norm": 0.1786852926015854,
+      "learning_rate": 1.1128243951817937e-05,
+      "loss": 0.91,
+      "step": 28
+    },
+    {
+      "epoch": 2.968553459119497,
+      "grad_norm": 0.21840958297252655,
+      "learning_rate": 1.0282950554804085e-05,
+      "loss": 1.1865,
+      "step": 29
+    },
+    {
+      "epoch": 3.0943396226415096,
+      "grad_norm": 0.17944976687431335,
+      "learning_rate": 1e-05,
+      "loss": 0.9459,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +256,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4025520594078925e+17,
+  "total_flos": 1.679578899551355e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null