Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9492aca336c619277b9c91c7ce508e2a3579a83b2ac2cf3822c9bbd5909ed22c
+oid sha256:2b8b801b0b9ad4ebbb81a189b61b96186d0dd4d1a4edba8ee2f566aba9da0eba
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eab0fa9af9a1cee1b3c1157275512445db0b6d0de66c7d65a67dd6d1a8818362
+oid sha256:9b9ee058044f2791e76e1fed2bd6671f944e31a08814056007eaba0930a6bdb3
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:250279917ab713639baee9854688e328bfb525e83e41a8b40901c70c59796ac9
+oid sha256:516e4f6bf156e53f470da37a786b79ef571eda1afba2b9b57d79861a9ac07c28
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d2b9cd8b76db862d8f36c96267d64ff69a21d07ce7f6eb4a0887810e44a8eb
+oid sha256:043092824777602976966449c2a2a96527a878ad10507a3b4d0f461ea2b8d14e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.791038155555725,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.38461538461538464,
+  "epoch": 0.42735042735042733,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 29.595,
       "eval_steps_per_second": 7.444,
       "step": 450
+    },
+    {
+      "epoch": 0.39316239316239315,
+      "grad_norm": 1.864538311958313,
+      "learning_rate": 3.912568710229791e-06,
+      "loss": 1.8847,
+      "step": 460
+    },
+    {
+      "epoch": 0.4017094017094017,
+      "grad_norm": 1.4721766710281372,
+      "learning_rate": 2.2070923258856255e-06,
+      "loss": 1.6806,
+      "step": 470
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 2.251706600189209,
+      "learning_rate": 9.829250571013935e-07,
+      "loss": 1.8125,
+      "step": 480
+    },
+    {
+      "epoch": 0.4188034188034188,
+      "grad_norm": 2.2963836193084717,
+      "learning_rate": 2.4603092375775605e-07,
+      "loss": 1.7681,
+      "step": 490
+    },
+    {
+      "epoch": 0.42735042735042733,
+      "grad_norm": 2.7665841579437256,
+      "learning_rate": 0.0,
+      "loss": 1.7633,
+      "step": 500
+    },
+    {
+      "epoch": 0.42735042735042733,
+      "eval_loss": 1.7948764562606812,
+      "eval_runtime": 16.6507,
+      "eval_samples_per_second": 29.608,
+      "eval_steps_per_second": 7.447,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.14419829538816e+16,
+  "total_flos": 3.4935536615424e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null