Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861ab745682694f78266a4fc1e90b3f9a43f17b70c614719240b34e5c31340f3
+oid sha256:f0297c820bceffdd6bb26200f035cdf49c5804e02036a7aab5730dc9f309983f
 size 9450352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d95bdb5908e873eddb021f20e5fab289709e88005b2b50136fe0dd08f4e0b16d
+oid sha256:50f96ae09dc4a06dfbd16afce7ac7dc3f8299f4d0a44ce6f13cda89c80a4b8b3
 size 4906490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da1a7bcd39b722467e48cffd358fb3f0ba544f3bd970efd28c3ffdeed3cba30
+oid sha256:8f861110b10b7cae8997e8c76ce37a824d2ffd06c800c3ccee7f1510bf1e6368
 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": 2.1459875106811523,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.055299539170506916,
+  "epoch": 0.07373271889400922,
   "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": 128.882,
       "eval_steps_per_second": 32.277,
       "step": 150
+    },
+    {
+      "epoch": 0.05898617511520737,
+      "grad_norm": 6141.27783203125,
+      "learning_rate": 0.000184829028536405,
+      "loss": 5.7739,
+      "step": 160
+    },
+    {
+      "epoch": 0.06267281105990784,
+      "grad_norm": 5252.96923828125,
+      "learning_rate": 0.00017943154018357726,
+      "loss": 6.1322,
+      "step": 170
+    },
+    {
+      "epoch": 0.0663594470046083,
+      "grad_norm": 3136.222900390625,
+      "learning_rate": 0.00017368360859750824,
+      "loss": 7.6432,
+      "step": 180
+    },
+    {
+      "epoch": 0.07004608294930875,
+      "grad_norm": 1761.0489501953125,
+      "learning_rate": 0.00016761323712310527,
+      "loss": 8.9134,
+      "step": 190
+    },
+    {
+      "epoch": 0.07373271889400922,
+      "grad_norm": 1086.85205078125,
+      "learning_rate": 0.00016125,
+      "loss": 9.8258,
+      "step": 200
+    },
+    {
+      "epoch": 0.07373271889400922,
+      "eval_loss": 4.759106159210205,
+      "eval_runtime": 8.8624,
+      "eval_samples_per_second": 128.859,
+      "eval_steps_per_second": 32.271,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 464666178355200.0,
+  "total_flos": 619554904473600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null