Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b8274b7b8cd71e49d2b599a387db85b8fedf404e5025a1c45bb1ac06f94ee55
+oid sha256:bddb591dd22935a3e0d559e6adf1b4174ce7b93dc6722ed542558dcfc20538aa
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2552b8459bf7cbb2779f617325e89097ab9d145874ff16454dc892331451008
+oid sha256:1a390e1adc3a99af969604c0aa5f1ce833d2801a2a6da5b7af38e1568dd11ff1
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566ad250dadb2969fbeaff50c43f06da9e7fd5f6031b4ebb62475514887b0b84
+oid sha256:6a1b45fdaf77c6390fdb0f6bfbdc29ecaf0fe6cafe4297c4df8596312c542af8
 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": 0.5128282308578491,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0025516713447307987,
+  "best_metric": 0.5025247931480408,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.003827507017096198,
   "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": 45.498,
       "eval_steps_per_second": 11.38,
       "step": 20
+    },
+    {
+      "epoch": 0.0026792549119673387,
+      "grad_norm": 0.24153533577919006,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5416,
+      "step": 21
+    },
+    {
+      "epoch": 0.0030620056136769582,
+      "grad_norm": 0.26265910267829895,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.5897,
+      "step": 24
+    },
+    {
+      "epoch": 0.003189589180913498,
+      "eval_loss": 0.5043231248855591,
+      "eval_runtime": 146.6634,
+      "eval_samples_per_second": 45.008,
+      "eval_steps_per_second": 11.257,
+      "step": 25
+    },
+    {
+      "epoch": 0.003444756315386578,
+      "grad_norm": 0.2601350247859955,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.6327,
+      "step": 27
+    },
+    {
+      "epoch": 0.003827507017096198,
+      "grad_norm": 0.24494047462940216,
+      "learning_rate": 0.0,
+      "loss": 0.5807,
+      "step": 30
+    },
+    {
+      "epoch": 0.003827507017096198,
+      "eval_loss": 0.5025247931480408,
+      "eval_runtime": 145.4545,
+      "eval_samples_per_second": 45.382,
+      "eval_steps_per_second": 11.351,
+      "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": 1441908601651200.0,
+  "total_flos": 2162862902476800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null