Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6141b01e103c0873ad508bd22b21b6044fa2666efd2fa1ef39eb351a0876715a
+oid sha256:9cfbd39b7ac79532cd8d92fec301b3b43c9837b950065cf50e0de46f5a5a449c
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0128ac5cc03d9430e10ddfd23e9300f2c39e0e8fa559e7d95c4fd4698648ea33
+oid sha256:b00129469eb1b552809b18ff0e65b98599c16ffa8a73099758248dd3322a8945
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87139ef07524e118be27838b4a139df74b6f02f5b608c763bc5b926db857de4e
+oid sha256:f86ae94331bcb349af862c171646fbc441829210d72fc90c5ace8301ccb75c51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e210a21e913c947efb876777b0844134f18a0e5dd3ba1625ccf5a578844563e
+oid sha256:2cd62d399a2450f21c7bec0f65f92f467b6df40bae3ff61b19e25062ffc80260
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1258819103240967,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.03395009336275675,
+  "epoch": 0.05092514004413512,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 16.864,
       "eval_steps_per_second": 4.226,
       "step": 100
+    },
+    {
+      "epoch": 0.03734510269903242,
+      "grad_norm": 6.313995838165283,
+      "learning_rate": 0.00020761968215422217,
+      "loss": 2.0996,
+      "step": 110
+    },
+    {
+      "epoch": 0.0407401120353081,
+      "grad_norm": 7.566165924072266,
+      "learning_rate": 0.00020429981382519356,
+      "loss": 2.104,
+      "step": 120
+    },
+    {
+      "epoch": 0.04413512137158377,
+      "grad_norm": 8.9271240234375,
+      "learning_rate": 0.00020051321843297219,
+      "loss": 2.0573,
+      "step": 130
+    },
+    {
+      "epoch": 0.04753013070785945,
+      "grad_norm": 10.48095989227295,
+      "learning_rate": 0.0001962783438896818,
+      "loss": 2.1817,
+      "step": 140
+    },
+    {
+      "epoch": 0.05092514004413512,
+      "grad_norm": 31.889493942260742,
+      "learning_rate": 0.0001916158220784091,
+      "loss": 2.0493,
+      "step": 150
+    },
+    {
+      "epoch": 0.05092514004413512,
+      "eval_loss": 1.2741807699203491,
+      "eval_runtime": 73.4449,
+      "eval_samples_per_second": 16.897,
+      "eval_steps_per_second": 4.234,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7976912487907328e+16,
+  "total_flos": 2.692065004408013e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null