Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3abff778d54438bb17495b059632d97b9d2604b420b6e9ff0cc9374a3ccf74eb
+oid sha256:4ae0146c66a60a0cb1ce7115e6edae3cf657a24bbaeb116513a45a34ddd41c07
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1effca4ddd64161fd89675c9225804a29aaabc8579121b6971d0f6874faf3b3f
+oid sha256:fda284a4cc20a8472ce5f330be62ae9315ae4168230a67cda1c84d4456c1eccd
 size 36136276

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c6f238611396d9f96297b1e06baa5eeda0b0d735ecd23298e4080362cc5ca4
+oid sha256:9096e87d19a47259ffba755014e2f00f382bb23b8044b40675d5698f9a55ab4d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a982b0cf4aa3113be3ccf8c7c44abbcbdbc330e78e6392b70eb543df2118de5
+oid sha256:705cabf5cbc3a6ab0feb67c77b9b453d59efcc939ce90d310af96e621810f990
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 3.285201072692871,
   "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.049128840383906795,
+  "epoch": 0.05614724615303634,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,28 @@
       "eval_samples_per_second": 34.786,
       "eval_steps_per_second": 17.393,
       "step": 350
+    },
+    {
+      "epoch": 0.0505325215377327,
+      "grad_norm": 4.121219635009766,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.416,
+      "step": 360
+    },
+    {
+      "epoch": 0.05614724615303634,
+      "grad_norm": 15.960735321044922,
+      "learning_rate": 0.0,
+      "loss": 3.3604,
+      "step": 400
+    },
+    {
+      "epoch": 0.05614724615303634,
+      "eval_loss": 3.2854654788970947,
+      "eval_runtime": 172.9851,
+      "eval_samples_per_second": 34.685,
+      "eval_steps_per_second": 17.343,
+      "step": 400
     }
   ],
   "logging_steps": 40,
@@ -141,7 +163,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -150,12 +172,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6459707464089600.0,
+  "total_flos": 7382522816102400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null