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:c92d4c7896e11345b2b7c4827d397a458a5d2d9d5f55c52ca5f5f8755221472e
+oid sha256:2f0be3c6539c8ba9dfb9b98ab5c726979efe34551c8169d0667cb293fecf1058
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08edc2a91eccab3e32730f5faa4997ea48ebd8270ebdce507af60652bb527dfc
+oid sha256:b04f13664c386fba0e0cfff814eccd6270e7a8d370bc3aa87df261ee4dfaaf7a
 size 91850618

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7e5a12693f00be90f0da9a98492cc0f44532f9b4cd3b4845e8a211e8f495e8
+oid sha256:35c4ed318008823573f1f1875684431e4b29c12e73ec81f84fbcf08f8559c62e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
+oid sha256:71a96715f430c2eb0d6104363f54769b2c1bdb005671dc81f0d67833a84ba743
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.243114471435547,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.07436787307882994,
+  "epoch": 0.08263097008758882,
   "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": 58.021,
       "eval_steps_per_second": 14.505,
       "step": 450
+    },
+    {
+      "epoch": 0.07602049248058172,
+      "grad_norm": 1.7526087760925293,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 2.1468,
+      "step": 460
+    },
+    {
+      "epoch": 0.0776731118823335,
+      "grad_norm": 2.405139684677124,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 2.1875,
+      "step": 470
+    },
+    {
+      "epoch": 0.07932573128408528,
+      "grad_norm": 3.5313682556152344,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 2.0859,
+      "step": 480
+    },
+    {
+      "epoch": 0.08097835068583706,
+      "grad_norm": 4.306454658508301,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 2.1371,
+      "step": 490
+    },
+    {
+      "epoch": 0.08263097008758882,
+      "grad_norm": 8.32631778717041,
+      "learning_rate": 0.0,
+      "loss": 2.3284,
+      "step": 500
+    },
+    {
+      "epoch": 0.08263097008758882,
+      "eval_loss": 2.2516839504241943,
+      "eval_runtime": 43.6921,
+      "eval_samples_per_second": 58.317,
+      "eval_steps_per_second": 14.579,
+      "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": 1.13234235359232e+16,
+  "total_flos": 1.25746305564672e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null