Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de312a8e99302e407350ebbec58756a087c45b23dc22ecd5cbaf2bf255638aa
+oid sha256:ec12c9880ca9278de2fd154e2cec12e50b3ce03645100d9aefd09317e446c2ec
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76c4e7dd175d1171233199ac5270115297bfa975d16ffbc4bbc1e069e1c71096
+oid sha256:4708c75106f3317c6b5057284ce8b3fc9a7dbe40061f0d6dcfca2976a00512e6
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41665902630196f54d3bb1edfb2e49940aea6b83aae2e61e59c5648fef9e424c
+oid sha256:f8b5daeff2c604fbc5db6562bda0b1a93f0aa77f364615e478712a03bb721857
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f2e88614aff46cd1ada70fbc3b2ec41b24cceb0ef1b4801de4a83c39b9b26bc
+oid sha256:1782a34e31686f496476697aa213a8a4eb0ce51a76589caf9070e07b3ee2de6a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4174914360046387,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.08643042350907519,
+  "best_metric": 1.3707703351974487,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.11524056467876692,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 16.181,
       "eval_steps_per_second": 4.051,
       "step": 150
+    },
+    {
+      "epoch": 0.09219245174301353,
+      "grad_norm": 0.5915709733963013,
+      "learning_rate": 0.000184829028536405,
+      "loss": 1.8188,
+      "step": 160
+    },
+    {
+      "epoch": 0.09795447997695189,
+      "grad_norm": 0.8901687860488892,
+      "learning_rate": 0.00017943154018357726,
+      "loss": 1.5977,
+      "step": 170
+    },
+    {
+      "epoch": 0.10371650821089023,
+      "grad_norm": 1.0244994163513184,
+      "learning_rate": 0.00017368360859750824,
+      "loss": 1.3397,
+      "step": 180
+    },
+    {
+      "epoch": 0.10947853644482858,
+      "grad_norm": 1.4333339929580688,
+      "learning_rate": 0.00016761323712310527,
+      "loss": 1.184,
+      "step": 190
+    },
+    {
+      "epoch": 0.11524056467876692,
+      "grad_norm": 1.4265000820159912,
+      "learning_rate": 0.00016125,
+      "loss": 0.7475,
+      "step": 200
+    },
+    {
+      "epoch": 0.11524056467876692,
+      "eval_loss": 1.3707703351974487,
+      "eval_runtime": 44.8927,
+      "eval_samples_per_second": 16.283,
+      "eval_steps_per_second": 4.076,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.708774936641536e+16,
+  "total_flos": 3.626263221633024e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null