Training in progress, step 32, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9647282502e43ed681430e77823b4ba804e714b8401e5bf5d12cf717c91f0d
+oid sha256:0e7a5c80b259ec1b4717d71fee50ed46000459382a99c2cea50a99f7a52f2f96
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d44c4094b530e951087f57d38dc24baf31ab1cafec4c1d70c9e8554ddfe8702
+oid sha256:b38b26a07a23bb8971ba6a069540914cf8be302f2205ecfaf24a07b6c3d166f6
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7f529fa0ca46a2fc7df048e62f4a6a160ee0abc9228610baf1f873e581b575
+oid sha256:c8b83d60e3bd7c770c94c7581c71569dd7212f834da6dd4807638eee44db31a8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d7dfe37fd91c64517ee3e36c11c3fae0466d740fca64d2cac13b48d07f91cac
+oid sha256:3fce5ad4cacf86f298445bc321ddca0c2867c0596bccb538356cad22111ad6ee
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b0120a70950f4d7cbc6380fce58797e960908be06fcb451a5a9265f2ac3436
+oid sha256:ccab18dc58cf8768b739d1ca503830678fbafcb8080ce561bbcfd691e8d76982
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dab923b8546218d478e39f5a5fe9230eae2e7db16d726a0af741de61e1ae86b2
+oid sha256:32a98567e49c9f240d2b97202509959994309a2039698fdd420b0fc60f705020
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b21ff4242f9f91d137e15c0f4fbae1aea3032edb3ddf39816bcc96ae6607b8
+oid sha256:a387b210316633d05904a757c86d6d5b1f723a9084c82125f530fbd1f5f4ae32
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6539015173912048,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.364705882352941,
+  "epoch": 3.0294117647058822,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,55 @@
       "eval_samples_per_second": 57.894,
       "eval_steps_per_second": 7.237,
       "step": 25
+    },
+    {
+      "epoch": 2.458823529411765,
+      "grad_norm": 0.14100024104118347,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.5238,
+      "step": 26
+    },
+    {
+      "epoch": 2.552941176470588,
+      "grad_norm": 0.09745590388774872,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4364,
+      "step": 27
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.12731899321079254,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.4703,
+      "step": 28
+    },
+    {
+      "epoch": 2.7411764705882353,
+      "grad_norm": 0.10433598607778549,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3853,
+      "step": 29
+    },
+    {
+      "epoch": 2.835294117647059,
+      "grad_norm": 0.11452948302030563,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.5038,
+      "step": 30
+    },
+    {
+      "epoch": 2.9294117647058826,
+      "grad_norm": 0.13775578141212463,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.5232,
+      "step": 31
+    },
+    {
+      "epoch": 3.0294117647058822,
+      "grad_norm": 0.14986667037010193,
+      "learning_rate": 0.0,
+      "loss": 0.6791,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -221,12 +270,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1201992933874074e+17,
+  "total_flos": 1.4336879040554598e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null