Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e8b59a814c9a088f6b9062440659bccc8fc289625fd1ff2e5b3c52147998cd
+oid sha256:d60acf8dcdcddeb62b78640b8365bd45d762ea5c3866998aa0be50add19d2809
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8889c11567294a3dfe42417a85989fcd84a90c7cb2632f1841d04ba92d392ee0
+oid sha256:ec65fbdf54f303f0bbfc7f6e2f24f4ad7574352f8d75e7c896ac4762adb45837
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b18fd526770faca31d6b68eaac69de0bf5165319660d891f391c0303ed73e314
+oid sha256:3f704cbed04a35a8d02bf4d57aa505157b25d4a6cec9754224cd1a7fed92ae36
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0585a94ca770852d904d0a057ee7d0f13731dc026d439d9add35f155aff77fb2
+oid sha256:7a29a98d7724cf179d3beb2d49a34c568e23cf47a86cb77f3cd39efdcdbcc2de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.639454960823059,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.07286859363614283,
+  "epoch": 0.09715812484819043,
   "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": 16.753,
       "eval_steps_per_second": 4.193,
       "step": 150
+    },
+    {
+      "epoch": 0.07772649987855235,
+      "grad_norm": 15.678354263305664,
+      "learning_rate": 0.00018310968873606635,
+      "loss": 3.1187,
+      "step": 160
+    },
+    {
+      "epoch": 0.08258440612096186,
+      "grad_norm": 27.940187454223633,
+      "learning_rate": 0.0001777624095772184,
+      "loss": 2.4375,
+      "step": 170
+    },
+    {
+      "epoch": 0.08744231236337138,
+      "grad_norm": 22.329130172729492,
+      "learning_rate": 0.0001720679471221826,
+      "loss": 3.5057,
+      "step": 180
+    },
+    {
+      "epoch": 0.09230021860578091,
+      "grad_norm": 21.67806053161621,
+      "learning_rate": 0.00016605404421963453,
+      "loss": 3.6538,
+      "step": 190
+    },
+    {
+      "epoch": 0.09715812484819043,
+      "grad_norm": 19.599658966064453,
+      "learning_rate": 0.00015975,
+      "loss": 3.1059,
+      "step": 200
+    },
+    {
+      "epoch": 0.09715812484819043,
+      "eval_loss": 1.7558817863464355,
+      "eval_runtime": 51.7429,
+      "eval_samples_per_second": 16.756,
+      "eval_steps_per_second": 4.194,
+      "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": 2.68312126685184e+16,
+  "total_flos": 3.57749502246912e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null