Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cfbd39b7ac79532cd8d92fec301b3b43c9837b950065cf50e0de46f5a5a449c
+oid sha256:911dbfe44d50f4d8130c8d7a920b83209ba9c03c2395975964b243e6d6ec093c
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00129469eb1b552809b18ff0e65b98599c16ffa8a73099758248dd3322a8945
+oid sha256:9e7d74b2eff201f85581eddf21dfa17016ec6d247c8298640249e3935608c2ef
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f86ae94331bcb349af862c171646fbc441829210d72fc90c5ace8301ccb75c51
+oid sha256:971c814cc33b88bf8e31c70fe4640c59c1a3867a8ebf4516040f466d4549b560
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd62d399a2450f21c7bec0f65f92f467b6df40bae3ff61b19e25062ffc80260
+oid sha256:292f236c37f22c287cc737dd1428bf82b9a9008a84eb2f517544aab166f8a97f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1258819103240967,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.05092514004413512,
+  "epoch": 0.0679001867255135,
   "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": 16.897,
       "eval_steps_per_second": 4.234,
       "step": 150
+    },
+    {
+      "epoch": 0.0543201493804108,
+      "grad_norm": 8.494623184204102,
+      "learning_rate": 0.00018654836833674362,
+      "loss": 2.1427,
+      "step": 160
+    },
+    {
+      "epoch": 0.05771515871668647,
+      "grad_norm": 7.212603569030762,
+      "learning_rate": 0.0001811006707899361,
+      "loss": 2.1089,
+      "step": 170
+    },
+    {
+      "epoch": 0.06111016805296215,
+      "grad_norm": 5.974452495574951,
+      "learning_rate": 0.0001752992700728339,
+      "loss": 2.1381,
+      "step": 180
+    },
+    {
+      "epoch": 0.06450517738923782,
+      "grad_norm": 8.32110595703125,
+      "learning_rate": 0.00016917243002657602,
+      "loss": 2.073,
+      "step": 190
+    },
+    {
+      "epoch": 0.0679001867255135,
+      "grad_norm": 17.76694107055664,
+      "learning_rate": 0.00016275,
+      "loss": 2.0969,
+      "step": 200
+    },
+    {
+      "epoch": 0.0679001867255135,
+      "eval_loss": 1.2275766134262085,
+      "eval_runtime": 73.4095,
+      "eval_samples_per_second": 16.905,
+      "eval_steps_per_second": 4.237,
+      "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": 2.692065004408013e+16,
+  "total_flos": 3.5953824975814656e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null