Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4905d3787467974cdd015f79f09ab59a64d09468799b86c75b7f662c0c8d2b
+oid sha256:9bc0466b09703d9ed94641b5c6cc8117ec8799c7ee6495e54cfc66a27ab85f80
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1e9e90715ac979a7ebb96bbf92b39afad2062c9f74cad4e8c7c8384845893d3
+oid sha256:02dc0feb0d8d507065a22387830ac38e843826503fb1ca98fa644d9d78f2d0aa
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94131ce147a64ce538e8a6dce011d7ca96cc2164c42f6ab9a2d2e247d673cc9
+oid sha256:439c3e08c5868d8cbcb56767cc0b0e3a9854aed8039db084ccbc32776d1a8df1
 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": 1.8064364194869995,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01037344398340249,
+  "best_metric": 1.6079975366592407,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.015560165975103735,
   "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": 34.994,
       "eval_steps_per_second": 8.748,
       "step": 20
+    },
+    {
+      "epoch": 0.010892116182572614,
+      "grad_norm": 3.8534629344940186,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.8446,
+      "step": 21
+    },
+    {
+      "epoch": 0.012448132780082987,
+      "grad_norm": 3.3622231483459473,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 6.5087,
+      "step": 24
+    },
+    {
+      "epoch": 0.012966804979253113,
+      "eval_loss": 1.6369980573654175,
+      "eval_runtime": 46.6288,
+      "eval_samples_per_second": 34.828,
+      "eval_steps_per_second": 8.707,
+      "step": 25
+    },
+    {
+      "epoch": 0.014004149377593362,
+      "grad_norm": 3.1091933250427246,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 6.8985,
+      "step": 27
+    },
+    {
+      "epoch": 0.015560165975103735,
+      "grad_norm": 2.932851791381836,
+      "learning_rate": 0.0,
+      "loss": 6.8303,
+      "step": 30
+    },
+    {
+      "epoch": 0.015560165975103735,
+      "eval_loss": 1.6079975366592407,
+      "eval_runtime": 46.5653,
+      "eval_samples_per_second": 34.876,
+      "eval_steps_per_second": 8.719,
+      "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": 2433797811339264.0,
+  "total_flos": 3635673273729024.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null