Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed0b90cd7b0a461a75dc122c5ee4bba79b70c61f7d84458286612093c66b05d
+oid sha256:7d4d228bc58ec7c69fcf1a6fc182d5c6a8b769f1280965c728afdfdf87fb785c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155802a4abb9e673a057b3feaf79675bb377de6daf86110dcfc690ab8e5e6ce3
+oid sha256:35f0a162b746546c58d3c47b377e3833fb6f15ccf2856549a1b3c119d6b1eff3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe2d93083d442b1cc689b68c0cf096441aebfd2677037101b902692f6601bbf
+oid sha256:f09b31c1192105e11820d0e0ce9f1b9885b06b37f25b191c18ab59e790dd459a
 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": 1.7805674076080322,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03129890453834116,
+  "best_metric": 1.7267839908599854,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.046948356807511735,
   "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": 15.575,
       "eval_steps_per_second": 3.901,
       "step": 20
+    },
+    {
+      "epoch": 0.03286384976525822,
+      "grad_norm": 8.659530639648438,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.949,
+      "step": 21
+    },
+    {
+      "epoch": 0.03755868544600939,
+      "grad_norm": 8.718548774719238,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 6.5662,
+      "step": 24
+    },
+    {
+      "epoch": 0.03912363067292645,
+      "eval_loss": 1.7352848052978516,
+      "eval_runtime": 34.6384,
+      "eval_samples_per_second": 15.561,
+      "eval_steps_per_second": 3.897,
+      "step": 25
+    },
+    {
+      "epoch": 0.04225352112676056,
+      "grad_norm": 8.553363800048828,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 6.6039,
+      "step": 27
+    },
+    {
+      "epoch": 0.046948356807511735,
+      "grad_norm": 9.443631172180176,
+      "learning_rate": 0.0,
+      "loss": 6.6292,
+      "step": 30
+    },
+    {
+      "epoch": 0.046948356807511735,
+      "eval_loss": 1.7267839908599854,
+      "eval_runtime": 34.6173,
+      "eval_samples_per_second": 15.57,
+      "eval_steps_per_second": 3.9,
+      "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": 1.406258997362688e+16,
+  "total_flos": 2.109388496044032e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null