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:fb57b7fa396e2eb8f8991b109f4cb70b2c1c72a6fb1ff610f2db98f584bd6180
+oid sha256:2bf1a87ccc5febdebb5c1ce4955575243eee0c0d78ce31acf1eb240eb2ac660b
 size 864368280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fab2ec0d3d528f77dc067bee26e2f5700661ca56cb6b997103b861b75932cf7
+oid sha256:e6540de8a861ead74092ecb18251e582a9ac464a58ec81dc8ddc18a8c3e7f56d
 size 439588164

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12cfd4f79db4be2e29dc687397d17ec4ab28e7b32633f28db7202d2eefe936e3
+oid sha256:6a023cb8ac48a2c723af348d77533b29e94a440e45d63d0889f6cd9158e5262a
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96aa36799c943a9bfefa20f32f650908880b1404c454cf725bf5d9ee2c75343e
+oid sha256:126a95bf1277ff34f610ecef71ab3da4221c5fdf57145767d775e04c91223794
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.727027177810669,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.006293134190598058,
+  "epoch": 0.008390845587464077,
   "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": 11.083,
       "eval_steps_per_second": 2.772,
       "step": 150
+    },
+    {
+      "epoch": 0.0067126764699712614,
+      "grad_norm": 3.6152729988098145,
+      "learning_rate": 0.0001813903489357277,
+      "loss": 1.7279,
+      "step": 160
+    },
+    {
+      "epoch": 0.007132218749344465,
+      "grad_norm": 2.7611238956451416,
+      "learning_rate": 0.00017609327897085954,
+      "loss": 1.7047,
+      "step": 170
+    },
+    {
+      "epoch": 0.0075517610287176695,
+      "grad_norm": 3.315603256225586,
+      "learning_rate": 0.00017045228564685694,
+      "loss": 1.8601,
+      "step": 180
+    },
+    {
+      "epoch": 0.007971303308090873,
+      "grad_norm": 4.356021881103516,
+      "learning_rate": 0.0001644948513161638,
+      "loss": 1.8429,
+      "step": 190
+    },
+    {
+      "epoch": 0.008390845587464077,
+      "grad_norm": 6.690892219543457,
+      "learning_rate": 0.00015825,
+      "loss": 1.5689,
+      "step": 200
+    },
+    {
+      "epoch": 0.008390845587464077,
+      "eval_loss": 1.9429612159729004,
+      "eval_runtime": 452.8314,
+      "eval_samples_per_second": 11.081,
+      "eval_steps_per_second": 2.771,
+      "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": 1.679086225195008e+16,
+  "total_flos": 2.203800670568448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null