Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac9fbb6f11ff468b4af176ef8986b21678d1b41437d5d858a5f58de97f6ba3b
+oid sha256:991d42f874d11dd7f685f12c44d997ee37d1294b9c1942a2ef1c866f4b0be971
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d83fc5363e3e786aa11089e1a8eb02cb5b7a1931a3cb0c977ceedc8fc1faaac
+oid sha256:9ad4c67cbd52d97c89f217975ad88698b15efeae1065f62a8d511a29d891ddb8
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a920341f8db11fdc2a3c97cba3df2042ccd0bcf8f95ab8ca8c32c36f41bc256
+oid sha256:4ccc884acd19b8a23e74071ab1c8930e4c49c6a544ce2691cea49c49a59e71c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123a052b8c41ff421cc6f9fbb2d14ef7b3db0d5e386f93b396eda4258e764d4c
+oid sha256:268aeb7b294c90cd83aa86854c13d1f13a76d08ba75be276a0b5b8f8a3905924
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.029171528588098017,
+  "epoch": 0.058343057176196034,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 185.037,
       "eval_steps_per_second": 46.387,
       "step": 50
+    },
+    {
+      "epoch": 0.03500583430571762,
+      "grad_norm": 2.9545175493694842e-05,
+      "learning_rate": 0.00021174178932754136,
+      "loss": 23.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.040840140023337225,
+      "grad_norm": 7.258558616740629e-05,
+      "learning_rate": 0.00021096841528660647,
+      "loss": 23.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.046674445740956826,
+      "grad_norm": 6.44875253783539e-05,
+      "learning_rate": 0.0002096836456777834,
+      "loss": 23.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.052508751458576426,
+      "grad_norm": 8.886439900379628e-05,
+      "learning_rate": 0.00020789373976946182,
+      "loss": 23.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.058343057176196034,
+      "grad_norm": 0.00012685952242463827,
+      "learning_rate": 0.0002056074178033063,
+      "loss": 23.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.058343057176196034,
+      "eval_loss": 11.5,
+      "eval_runtime": 4.0392,
+      "eval_samples_per_second": 178.75,
+      "eval_steps_per_second": 44.811,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1007376236544.0,
+  "total_flos": 2004778450944.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null