Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d5a7bdf7fb2be71ca14518f2cb4bc315bf4ef259ac99a38b09454f10565fa80
+oid sha256:62f4ef38c260665fb4eb76a4bdb2718e7f10da4fbc9b8de796aa24dbb03bc34d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d549a3bb6f2be99d978180591e8900552710225268245cdfa5d81706f8092f
+oid sha256:7a2fc26269165ec207e3f3f5c00de7a9beee7b95a350016a7940c06d32c47d2e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa91133351808aacad3e45f05aebdf1a2981ac4aa08431c95904a973b1b12d5
+oid sha256:62ed3fd3312f96c17ea93ab3f7344a9def6141fa3d024e167875cba869f24ea5
 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": 1.8693417310714722,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0010486989578554107,
+  "best_metric": 1.8543736934661865,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.001573048436783116,
   "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": 17.312,
       "eval_steps_per_second": 8.656,
       "step": 20
+    },
+    {
+      "epoch": 0.0011011339057481811,
+      "grad_norm": 0.8859915137290955,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.8701,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012584387494264928,
+      "grad_norm": 0.7678781747817993,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.7947,
+      "step": 24
+    },
+    {
+      "epoch": 0.0013108736973192633,
+      "eval_loss": 1.8585127592086792,
+      "eval_runtime": 463.8324,
+      "eval_samples_per_second": 17.312,
+      "eval_steps_per_second": 8.656,
+      "step": 25
+    },
+    {
+      "epoch": 0.0014157435931048043,
+      "grad_norm": 0.8636906743049622,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.7815,
+      "step": 27
+    },
+    {
+      "epoch": 0.001573048436783116,
+      "grad_norm": 1.0358920097351074,
+      "learning_rate": 0.0,
+      "loss": 1.8157,
+      "step": 30
+    },
+    {
+      "epoch": 0.001573048436783116,
+      "eval_loss": 1.8543736934661865,
+      "eval_runtime": 464.0763,
+      "eval_samples_per_second": 17.303,
+      "eval_steps_per_second": 8.652,
+      "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": 7418872835604480.0,
+  "total_flos": 1.1221045163851776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null