Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8ed75181f42815b1dfe5b1d6e6f01f2005717acec739ea0ec1c60326e955dd0
+oid sha256:0bf07beee4f2ee8fe687aafb2ef13743f96ab934c078080bb59c2395824e4ab8
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa8e9380e1d51e8beeadfc08fab10aa1377eb0ad6e32cd61d6320b95d12fa339
+oid sha256:8373fc223d3bc5b82c130587cc2f88c55f91c97f543860391f4a58eaf28ec936
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa1dedb20f725f787018db8a45f7e48a6271b0484d15dcfc310d023360e592e
+oid sha256:10faf1a5933381912aded690d1653f800b9114982ecd991fec4b5fba1e91a3bd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee9cb28e154991209e6625681b25f78638efe0e6066de2ece71b0fec87387c59
+oid sha256:ce16955e61abda6f2a7169290b9b633c6a443b032699be0bbd0aedbd64aa61cb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab18ea5791e1e6fbf1bdb6f4499791eac7bf07f100b1d20d05d3b691a4ae445
+oid sha256:5e75d508505595a6608697728915cc4a562c8b7b2a3ef4026abcef67bb43bc56
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be5b90241f583c7142966a7a90b0d123f36f36636a36b02bc77a42db42dccc1e
+oid sha256:ea526550cb3257d5c977660c5678b9569654e7d35f79bf7ff05c1e9baca0cb3b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15de33a07e410afa052feec00b24cad4d6056805cfcd7c6c03a494df63f2b5f5
+oid sha256:107b29f33410c4cf71ccbd6fb26eaba4a14fa0e5d150736df6162f13a57a19d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2730916738510132,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 3.0602836879432624,
+  "epoch": 3.2872340425531914,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,20 @@
       "eval_samples_per_second": 45.355,
       "eval_steps_per_second": 11.792,
       "step": 25
+    },
+    {
+      "epoch": 3.173758865248227,
+      "grad_norm": 0.3071691393852234,
+      "learning_rate": 1.0354838440848503e-05,
+      "loss": 0.1519,
+      "step": 26
+    },
+    {
+      "epoch": 3.2872340425531914,
+      "grad_norm": 0.2735120356082916,
+      "learning_rate": 1e-05,
+      "loss": 0.1463,
+      "step": 27
     }
   ],
   "logging_steps": 1,
@@ -221,12 +235,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.1240447254528e+16,
+  "total_flos": 8.773968303489024e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null