Training in progress, step 237, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ac93c930d5a289e0a603bd4ca9821cb2fe7c62a3a3c5c3310c5f44fc0cf24c
+oid sha256:6289224c77c8a31a68628836f62cbb43232847e3b3eb435bf0ed4f0ab70a0166
 size 1195486552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a91b6dc80a4a365a9bda620bd225fed5e866a11489219eca48b921435ceed6c
+oid sha256:c1912f8042471d11afc7b0d1cad12151bf0e741188c63400bb14ed6a6a1c2037
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00dd7b7defb892dd0775dc51bbf68a8c179a96e9e94ca7f2f38209949c0c2e74
+oid sha256:cb42424353538278a6b269cde93b96dfa1823b48f223f843d67ff8f812fcfcb0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6902df8566c998c38360e138b1bfa129e83a9012a2638e0b255cac476fbd4e74
+oid sha256:bdf6723a440ab64c79d301fd99b67bcbe6a2cbf20500030c1c40ee35cccbf908
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.8633633852005005,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.8456659619450317,
+  "epoch": 1.0021141649048626,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 237,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,27 @@
       "eval_samples_per_second": 15.258,
       "eval_steps_per_second": 3.815,
       "step": 200
+    },
+    {
+      "epoch": 0.8879492600422833,
+      "grad_norm": 5.115078449249268,
+      "learning_rate": 1.0719158868709316e-05,
+      "loss": 3.8714,
+      "step": 210
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 6.137579441070557,
+      "learning_rate": 4.29374479686329e-06,
+      "loss": 3.8645,
+      "step": 220
+    },
+    {
+      "epoch": 0.9725158562367865,
+      "grad_norm": 7.499491214752197,
+      "learning_rate": 7.321295075359002e-07,
+      "loss": 3.5654,
+      "step": 230
     }
   ],
   "logging_steps": 10,
@@ -210,12 +231,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.684826094134886e+16,
+  "total_flos": 4.371259110457344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null