Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7b8eb478dee398996e46b5ca61429b5e0276dd3e558ebb59905b7d7d2bbbc7
+oid sha256:7951377064e5d7309b7b8acf18d5fbdef3053539e3f9dfa2d4d1c125a3198ed6
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2235febfe01e8fa55790f6801f745956fd4d8341709470b0c0f88802ad23dff
+oid sha256:d42a0b0094406d0c0e1bb522097005e7823a069ed84f225ddd29417ab688a098
 size 60837186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df671da0647ad751ae2dccc6766dc5c327b7edaf01aa92e7029489aace41976b
+oid sha256:c49c7b2195a6f4c9565b45a455152418a4b3a1b0bdd12af559e16beee43e8b9f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.697143793106079,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.14678899082568808,
+  "best_metric": 2.5815908908843994,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.22018348623853212,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 42.316,
       "eval_steps_per_second": 10.671,
       "step": 20
+    },
+    {
+      "epoch": 0.15412844036697249,
+      "grad_norm": 1.463902473449707,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.0289,
+      "step": 21
+    },
+    {
+      "epoch": 0.1761467889908257,
+      "grad_norm": 1.6114941835403442,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.8876,
+      "step": 24
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "eval_loss": 2.6056313514709473,
+      "eval_runtime": 2.7128,
+      "eval_samples_per_second": 42.392,
+      "eval_steps_per_second": 10.69,
+      "step": 25
+    },
+    {
+      "epoch": 0.1981651376146789,
+      "grad_norm": 1.7031934261322021,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.769,
+      "step": 27
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 1.8348661661148071,
+      "learning_rate": 0.0,
+      "loss": 2.8255,
+      "step": 30
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "eval_loss": 2.5815908908843994,
+      "eval_runtime": 2.7124,
+      "eval_samples_per_second": 42.397,
+      "eval_steps_per_second": 10.692,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 628996844814336.0,
+  "total_flos": 939612570648576.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null