Training in progress, step 192, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d297b2cb938066dc3d631e0ee85eb769b114a5d70ee0f51a02b59d951dbfcec
+oid sha256:877f3a8fcc78e5546bf55e912fb49995dd4888e04b69fa1179ef815dc514dc08
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b722ca51d321c49f3d9eb200032d410a79e1d855463d1b752b6f5970501f9576
+oid sha256:0812750347011757ac8a85ad004f987ca93c762af2c5b916e28944e39c8a799b
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0efa48fa530c4947fbb91587963e040e247c4d20441125d8123d0c104b6d44ca
+oid sha256:edfa161081f25360ef999094cd406d4c7aba4d6f417a122659b6869958b9e162
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4cb97dbd9e874d62d876f3ad4cd4f75d9f58f10e69aebe9a0b6324f5a4073f
+oid sha256:1c838d9e0012b59184c191237b58d821c094b7da772daafc5185514fe73e9c8a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0718849897384644,
-  "best_model_checkpoint": "miner_id_24/checkpoint-96",
-  "epoch": 0.5161290322580645,
+  "best_metric": 0.9115006923675537,
+  "best_model_checkpoint": "miner_id_24/checkpoint-192",
+  "epoch": 1.032258064516129,
   "eval_steps": 96,
-  "global_step": 96,
+  "global_step": 192,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 23.025,
       "eval_steps_per_second": 0.733,
       "step": 96
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 1.5161734819412231,
+      "learning_rate": 0.00039997559251058097,
+      "loss": 1.8322,
+      "step": 192
+    },
+    {
+      "epoch": 1.032258064516129,
+      "eval_loss": 0.9115006923675537,
+      "eval_runtime": 6.8277,
+      "eval_samples_per_second": 22.995,
+      "eval_steps_per_second": 0.732,
+      "step": 192
     }
   ],
   "logging_steps": 96,
@@ -58,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1271985447174144e+16,
+  "total_flos": 6.250325216329728e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null